input
stringlengths 3.23k
13.3k
| output
sequencelengths 1
3
| id
stringlengths 40
40
|
|---|---|---|
Definition: In this task, you will be presented with a context from an academic paper and you have to write an answerable question based on the context. Your questions can be extractive, abstractive, or yes-no questions.
Positive Example 1 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: how was the dataset built?
Positive Example 2 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language are the tweets?
Negative Example 1 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language is tweets?
Negative Example 2 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: What is the size of the dataset?
Now complete the following example -
Input: As a warm-up procedure, the first 100 posts were annotated by two annotators (the author and the supervisor) and the results compared. The remainder of the annotation task was performed by the author, resulting in 3600 annotated samples.
Output:
| [
"Who were the annotators?"
] | task461-73d405fdc9064681a58162bc685542bd |
Definition: In this task, you will be presented with a context from an academic paper and you have to write an answerable question based on the context. Your questions can be extractive, abstractive, or yes-no questions.
Positive Example 1 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: how was the dataset built?
Positive Example 2 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language are the tweets?
Negative Example 1 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language is tweets?
Negative Example 2 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: What is the size of the dataset?
Now complete the following example -
Input: The D2V model has been rated 80 times as "bad relevance" while the pmra returned only 24 times badly relevant documents.
Output:
| [
"How better are results for pmra algorithm than Doc2Vec in human evaluation? "
] | task461-d0c57ef61e3b404d905726c85a7560b2 |
Definition: In this task, you will be presented with a context from an academic paper and you have to write an answerable question based on the context. Your questions can be extractive, abstractive, or yes-no questions.
Positive Example 1 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: how was the dataset built?
Positive Example 2 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language are the tweets?
Negative Example 1 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language is tweets?
Negative Example 2 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: What is the size of the dataset?
Now complete the following example -
Input: We chose Conditional Copy (CC) model as our baseline, which is the best model in Wiseman.
Output:
| [
"What is the strong baseline?"
] | task461-b4d6609f5f1b471391844121ef6b3995 |
Definition: In this task, you will be presented with a context from an academic paper and you have to write an answerable question based on the context. Your questions can be extractive, abstractive, or yes-no questions.
Positive Example 1 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: how was the dataset built?
Positive Example 2 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language are the tweets?
Negative Example 1 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language is tweets?
Negative Example 2 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: What is the size of the dataset?
Now complete the following example -
Input: Figure FIGREF9 illustrates the overall architecture of the proposed Attentional Encoder Network (AEN), which mainly consists of an embedding layer, an attentional encoder layer, a target-specific attention layer, and an output layer. Embedding layer has two types: GloVe embedding and BERT embedding. Accordingly, the models are named AEN-GloVe and AEN-BERT.
Output:
| [
"How is their model different from BERT?"
] | task461-9aabc3749cc44fd9be5c9a7b23e7f43a |
Definition: In this task, you will be presented with a context from an academic paper and you have to write an answerable question based on the context. Your questions can be extractive, abstractive, or yes-no questions.
Positive Example 1 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: how was the dataset built?
Positive Example 2 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language are the tweets?
Negative Example 1 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language is tweets?
Negative Example 2 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: What is the size of the dataset?
Now complete the following example -
Input: We train a single layer LSTM with a 150-dimensional hidden state for hate / not hate classification. The input dimensionality is set to 100 and GloVe BIBREF26 embeddings are used as word input representations.
Output:
| [
"What unimodal detection models were used?"
] | task461-2c0a7e8dd58a4c96844b592c5a9a3dbb |
Definition: In this task, you will be presented with a context from an academic paper and you have to write an answerable question based on the context. Your questions can be extractive, abstractive, or yes-no questions.
Positive Example 1 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: how was the dataset built?
Positive Example 2 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language are the tweets?
Negative Example 1 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language is tweets?
Negative Example 2 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: What is the size of the dataset?
Now complete the following example -
Input: Furthermore, we employ two different parsers for comparison: 1) the PCFGLA-based parser, viz. Berkeley parser BIBREF5 , and 2) a minimal span-based neural parser BIBREF6 .
Output:
| [
"What is the baseline model for the agreement-based mode?"
] | task461-bebea98d86044390ad6fbcdbdc8dd37d |
Definition: In this task, you will be presented with a context from an academic paper and you have to write an answerable question based on the context. Your questions can be extractive, abstractive, or yes-no questions.
Positive Example 1 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: how was the dataset built?
Positive Example 2 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language are the tweets?
Negative Example 1 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language is tweets?
Negative Example 2 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: What is the size of the dataset?
Now complete the following example -
Input: In order to make the corpus collection easier and faster, we adopted a semi-automatic procedure based on sequential neural models BIBREF19, BIBREF20. Instead, since tokens are transcribed at morpheme level, we split Arabish tokens into characters, and Arabic tokens into morphemes, and we treated each token itself as a sequence. Our model learns thus to map Arabish characters into Arabic morphemes. With this model we automatically transcribed into Arabic morphemes, roughly, 5,000 additional tokens, corresponding to the second annotation block. Manual transcription plus a
Output:
| [
"How does the semi-automatic construction process work?"
] | task461-05e9fe21eda34b46a6f6e239b66d4dd6 |
Definition: In this task, you will be presented with a context from an academic paper and you have to write an answerable question based on the context. Your questions can be extractive, abstractive, or yes-no questions.
Positive Example 1 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: how was the dataset built?
Positive Example 2 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language are the tweets?
Negative Example 1 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language is tweets?
Negative Example 2 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: What is the size of the dataset?
Now complete the following example -
Input: hierarchical In this paper, we work with the dataset of the 2019 GermEval shared task on hierarchical text classification BIBREF0 and use the predefined set of labels to evaluate our approach to this classification task.
Output:
| [
"What dataset do they use?"
] | task461-cbee6fa56d14407a820a80ec96f57d79 |
Definition: In this task, you will be presented with a context from an academic paper and you have to write an answerable question based on the context. Your questions can be extractive, abstractive, or yes-no questions.
Positive Example 1 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: how was the dataset built?
Positive Example 2 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language are the tweets?
Negative Example 1 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language is tweets?
Negative Example 2 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: What is the size of the dataset?
Now complete the following example -
Input: We collected a total of 657 ratings by 14 volunteers, 5 Italian and 9 non-Italian listeners, spread over the 24 clips and three testing conditions.
Output:
| [
"How many people are employed for the subjective evaluation?"
] | task461-0e9248f4ba7249fe84025efc5e9146d6 |
Definition: In this task, you will be presented with a context from an academic paper and you have to write an answerable question based on the context. Your questions can be extractive, abstractive, or yes-no questions.
Positive Example 1 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: how was the dataset built?
Positive Example 2 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language are the tweets?
Negative Example 1 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language is tweets?
Negative Example 2 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: What is the size of the dataset?
Now complete the following example -
Input: We focus here on the Europarl domain, for which we have ample data in several languages, and use as in-domain training data the Europarl corpus BIBREF5 for two translation directions: English INLINEFORM0 German and English INLINEFORM1 French.
Output:
| [
"what language pairs are explored?"
] | task461-1dfbd996ea004067ad40edf3f1d3fe18 |
Definition: In this task, you will be presented with a context from an academic paper and you have to write an answerable question based on the context. Your questions can be extractive, abstractive, or yes-no questions.
Positive Example 1 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: how was the dataset built?
Positive Example 2 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language are the tweets?
Negative Example 1 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language is tweets?
Negative Example 2 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: What is the size of the dataset?
Now complete the following example -
Input: Here is a list of architectures for which reference implementations and pretrained weights are currently provided in Transformers. These models fall into two main categories: generative models (GPT, GPT-2, Transformer-XL, XLNet, XLM) and models for language understanding (Bert, DistilBert, RoBERTa, XLM).
BERT (BIBREF13) is a bi-directional Transformer-based encoder pretrained with a linear combination of masked language modeling and next sentence prediction objectives.
RoBERTa (BIBREF5) is a replication study of BERT which showed that carefully tuning hyper-parameters and training data size lead to significantly improved results on language understanding.
DistilBERT (BIBREF32) is a smaller, faster, cheaper and lighter version BERT pretrained with knowledge distillation.
GPT (BIBREF34) and GPT2 (BIBREF9) are two large auto-regressive language models pretrained with language modeling. GPT2 showcased zero-shot task transfer capabilities on various tasks such as machine translation or reading comprehension.
Transformer-XL (BIBREF35) introduces architectural modifications enabling Transformers to learn dependency beyond a fixed length without disrupting temporal coherence via segment-level recurrence and relative positional encoding schemes.
XLNet (BIBREF4) builds upon Transformer-XL and proposes an auto-regressive pretraining scheme combining BERT's bi-directional context flow with auto-regressive language modeling by maximizing the expected likelihood over permutations of the word sequence.
XLM (BIBREF8) shows the effectiveness of pretrained representations for cross-lingual language modeling (both on monolingual data and parallel data) and cross-lingual language understanding.
We systematically release the model with the corresponding pretraining heads (language modeling, next sentence prediction for BERT) for adaptation using the pretraining objectives. Some models fine-tuned on downstream tasks such as SQuAD1.1 are also available. Overall, more than 30 pretrained weights are provided through the library including more than 10 models pretrained in languages other than English. Some of these non-English pretrained models are multi-lingual models (with two of them being trained on more than 100 languages) .
Output:
| [
"What state-of-the-art general-purpose pretrained models are made available under the unified API? "
] | task461-dd8fa7de23554871afac50c92753df7b |
Definition: In this task, you will be presented with a context from an academic paper and you have to write an answerable question based on the context. Your questions can be extractive, abstractive, or yes-no questions.
Positive Example 1 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: how was the dataset built?
Positive Example 2 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language are the tweets?
Negative Example 1 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language is tweets?
Negative Example 2 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: What is the size of the dataset?
Now complete the following example -
Input: CoVoST is currently built on that release and covers the following 11 languages: French, German, Dutch, Russian, Spanish, Italian, Turkish, Persian, Swedish, Mongolian and Chinese.
Output:
| [
"Is Arabic one of the 11 languages in CoVost?"
] | task461-ad04400f4fcc4cdeba40fea61a8414ba |
Definition: In this task, you will be presented with a context from an academic paper and you have to write an answerable question based on the context. Your questions can be extractive, abstractive, or yes-no questions.
Positive Example 1 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: how was the dataset built?
Positive Example 2 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language are the tweets?
Negative Example 1 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language is tweets?
Negative Example 2 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: What is the size of the dataset?
Now complete the following example -
Input: In this work we consider directed graphs. Let INLINEFORM0 represent a graph comprised of a set of vertices INLINEFORM1 and a set of edges ( INLINEFORM2 ), which are ordered pairs. Further, each edge can have a real-valued weight assigned. Let INLINEFORM3 represent a document comprised of tokens INLINEFORM4 . The order in which tokens in text appear is known, thus INLINEFORM5 is a totally ordered set. A potential way of constructing a graph from a document is by simply observing word co-occurrences. When two words co-occur, they are used as an edge. However, such approaches do not take into account the sequence nature of the words, meaning that the order is lost. We attempt to take this aspect into account as follows. The given corpus is traversed, and for each element INLINEFORM6 , its successor INLINEFORM7 , together with a given element, forms a directed edge INLINEFORM8 . Finally, such edges are weighted according to the number of times they appear in a given corpus. Thus the graph, constructed after traversing a given corpus, consists of all local neighborhoods (order one), merged into a single joint structure. Global contextual information is potentially kept intact (via weights), even though it needs to be detected via network analysis as proposed next.
Output:
| [
"How are graphs derived from a given text?"
] | task461-03c2a107404145bf8e903d4707f66c9c |
Definition: In this task, you will be presented with a context from an academic paper and you have to write an answerable question based on the context. Your questions can be extractive, abstractive, or yes-no questions.
Positive Example 1 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: how was the dataset built?
Positive Example 2 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language are the tweets?
Negative Example 1 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language is tweets?
Negative Example 2 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: What is the size of the dataset?
Now complete the following example -
Input: We assess the optimal number of topics that need to be specified for the STM analysis. We follow the recommendations of the original STM paper and focus on exclusivity and semantic coherence measures. Highly frequent words in a given topic that do not appear very often in other topics are viewed as making that topic exclusive. Following BIBREF8 we generate a set of candidate models ranging between 3 and 50 topics. We then plot the exclusivity and semantic coherence (numbers closer to 0 indicate higher coherence), with a linear regression overlaid (Figure FIGREF3 ). Models above the regression line have a “better” exclusivity-semantic coherence trade off. We select the 16-topic model, which has the largest positive residual in the regression fit, and provides higher exclusivity at the same level of semantic coherence. The topic quality is usually evaluated by highest probability words, which is presented in Figure FIGREF4 .
Output:
| [
"How are the main international development topics that states raise identified?"
] | task461-5132c49bd65c4be490845f4a4c3e613a |
Definition: In this task, you will be presented with a context from an academic paper and you have to write an answerable question based on the context. Your questions can be extractive, abstractive, or yes-no questions.
Positive Example 1 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: how was the dataset built?
Positive Example 2 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language are the tweets?
Negative Example 1 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language is tweets?
Negative Example 2 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: What is the size of the dataset?
Now complete the following example -
Input: The dataset from Twitter that we are using in our work, consists of a train set, a validation set and a test set. It was published for the "First workshop on categorizing different types of online harassment languages in social media". The whole dataset is divided into two categories, which are harassment and non-harassment tweets. Moreover, considering the type of the harassment, the tweets are divided into three sub-categories which are indirect harassment, sexual and physical harassment.
Output:
| [
"What types of online harassment are studied?"
] | task461-1b525676b70642668939bd71a4457233 |
Definition: In this task, you will be presented with a context from an academic paper and you have to write an answerable question based on the context. Your questions can be extractive, abstractive, or yes-no questions.
Positive Example 1 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: how was the dataset built?
Positive Example 2 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language are the tweets?
Negative Example 1 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language is tweets?
Negative Example 2 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: What is the size of the dataset?
Now complete the following example -
Input: For generating a poem from images we use an existing actor-critic architecture BIBREF1. For Shakespearizing modern English texts, we experimented with various types of sequence to sequence models. We use a sequence-to-sequence model which consists of a single layer unidrectional LSTM encoder and a single layer LSTM decoder and pre-trained retrofitted word embeddings shared between source and target sentences. Since a pair of corresponding Shakespeare and modern English sentences have significant vocabulary overlap we extend the sequence-to-sequence model mentioned above using pointer networks BIBREF11 that provide location based attention and have been used to enable copying of tokens directly from the input.
Output:
| [
"What models are used for painting embedding and what for language style transfer?"
] | task461-ea788955bf2d46158bbff4bd86499268 |
Definition: In this task, you will be presented with a context from an academic paper and you have to write an answerable question based on the context. Your questions can be extractive, abstractive, or yes-no questions.
Positive Example 1 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: how was the dataset built?
Positive Example 2 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language are the tweets?
Negative Example 1 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language is tweets?
Negative Example 2 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: What is the size of the dataset?
Now complete the following example -
Input: This results in three additional vectors corresponding to INLINEFORM3 , INLINEFORM4 and INLINEFORM5 difference vectors.
Results
Output:
| [
"How are the EAU text spans annotated?"
] | task461-5cde86c3b598442a8cc28bc9a6756aa3 |
Definition: In this task, you will be presented with a context from an academic paper and you have to write an answerable question based on the context. Your questions can be extractive, abstractive, or yes-no questions.
Positive Example 1 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: how was the dataset built?
Positive Example 2 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language are the tweets?
Negative Example 1 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language is tweets?
Negative Example 2 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: What is the size of the dataset?
Now complete the following example -
Input: In this work we train bilingual UWS models using the endangered language Mboshi as target and different well-resourced languages as aligned information. Results show that similar languages rank better in terms of segmentation performance, and that by combining the information learned by different models, segmentation is further improved. This might be due to the different language-dependent structures that are captured by using more than one language.
Output:
| [
"How does the well-resourced language impact the quality of the output?"
] | task461-987ccfd1b35c4ff0a81d63c63c7a0a5a |
Definition: In this task, you will be presented with a context from an academic paper and you have to write an answerable question based on the context. Your questions can be extractive, abstractive, or yes-no questions.
Positive Example 1 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: how was the dataset built?
Positive Example 2 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language are the tweets?
Negative Example 1 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language is tweets?
Negative Example 2 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: What is the size of the dataset?
Now complete the following example -
Input: The training dataset contains 2,815 examples, where 1,940 (i.e., 69%) are fake news and 1,968 (i.e., 70%) are click-baits; we further have 761 testing examples.
Output:
| [
"what datasets were used?"
] | task461-67d48091cc3d40ec8856fa1f6f252c37 |
Definition: In this task, you will be presented with a context from an academic paper and you have to write an answerable question based on the context. Your questions can be extractive, abstractive, or yes-no questions.
Positive Example 1 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: how was the dataset built?
Positive Example 2 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language are the tweets?
Negative Example 1 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language is tweets?
Negative Example 2 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: What is the size of the dataset?
Now complete the following example -
Input: As of June 2019, AA had $\sim $50K entries, however, this includes some number of entries that are not truly research publications (for example, forewords, prefaces, table of contents, programs, schedules, indexes, calls for papers/participation, lists of reviewers, lists of tutorial abstracts, invited talks, appendices, session information, obituaries, book reviews, newsletters, lists of proceedings, lifetime achievement awards, erratum, and notes). We discard them for the analyses here. (Note: CL journal includes position papers like squibs, letter to editor, opinion, etc. We do not discard them.) We are then left with 44,896 articles.
Output:
| [
"How many papers are used in experiment?"
] | task461-ac77ebc523264c31b8640da765dd1291 |
Definition: In this task, you will be presented with a context from an academic paper and you have to write an answerable question based on the context. Your questions can be extractive, abstractive, or yes-no questions.
Positive Example 1 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: how was the dataset built?
Positive Example 2 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language are the tweets?
Negative Example 1 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language is tweets?
Negative Example 2 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: What is the size of the dataset?
Now complete the following example -
Input: This chapter describes the underlying formalism of the theorem provers, as it is visible during an interactive proof trace, and present the general strategy followed by the theorem provers. The rest of this chapter is structured as follows. Section "Type-logical grammars" presents a general introduction to type-logical grammars and illustrates its basic concepts using the Lambek calculus, ending the section with some problems at the syntax-semantics interface for the Lambek calculus. Type-logical grammars are a family of grammar formalisms built on a foundation of logic and type theory. Type-logical grammars originated when BIBREF4 introduced his Syntactic Calculus (called the Lambek calculus, L, by later authors). Though Lambek built on the work of BIBREF5 , BIBREF6 and others, Lambek's main innovation was to cast the calculus as a logic, giving a sequent calculus and showing decidability by means of cut elimination.
Output:
| [
"What formalism does Grail use?"
] | task461-df5d2e54b6594dc38a003b5db64014b7 |
Definition: In this task, you will be presented with a context from an academic paper and you have to write an answerable question based on the context. Your questions can be extractive, abstractive, or yes-no questions.
Positive Example 1 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: how was the dataset built?
Positive Example 2 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language are the tweets?
Negative Example 1 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language is tweets?
Negative Example 2 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: What is the size of the dataset?
Now complete the following example -
Input: We validate our approach on the Gigaword corpus, which comprises of a training set of 3.8M article headlines (considered to be the full text) and titles (summaries), along with 200K validation pairs, and we report test performance on the same 2K set used in BIBREF7.
Output:
| [
"What dataset they use for evaluation?"
] | task461-bb7ff563703c49aaa6483a9d020ad9dc |
Definition: In this task, you will be presented with a context from an academic paper and you have to write an answerable question based on the context. Your questions can be extractive, abstractive, or yes-no questions.
Positive Example 1 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: how was the dataset built?
Positive Example 2 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language are the tweets?
Negative Example 1 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language is tweets?
Negative Example 2 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: What is the size of the dataset?
Now complete the following example -
Input: Among all available parameters to tune the D2V algorithm released by Gensim, six of them were selected for optimisation BIBREF14. The window_size parameter affects the size of the sliding window used to parse texts. The alpha parameter represents the learning rate of the network. The sample setting allows the model to reduce the importance given to high-frequency words. The dm parameter defines the training used architecture (PV-DM or PV-DBOW).
Output:
| [
"What Doc2Vec architectures other than PV-DBOW have been tried?"
] | task461-ea1e49b25d3843dba272af51ab2e03ca |
Definition: In this task, you will be presented with a context from an academic paper and you have to write an answerable question based on the context. Your questions can be extractive, abstractive, or yes-no questions.
Positive Example 1 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: how was the dataset built?
Positive Example 2 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language are the tweets?
Negative Example 1 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language is tweets?
Negative Example 2 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: What is the size of the dataset?
Now complete the following example -
Input: Yet, we noticed a common misbehavior for all our multimodal models: if the attention loose track of the objects in the picture and "gets lost", the model still takes it into account and somehow overrides the information brought by the text-based annotations. The translation is then totally mislead.
Output:
| [
"What misbehavior is identified?"
] | task461-e955d05b65f2421cb60acd54076a5520 |
Definition: In this task, you will be presented with a context from an academic paper and you have to write an answerable question based on the context. Your questions can be extractive, abstractive, or yes-no questions.
Positive Example 1 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: how was the dataset built?
Positive Example 2 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language are the tweets?
Negative Example 1 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language is tweets?
Negative Example 2 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: What is the size of the dataset?
Now complete the following example -
Input: We evaluated baselines and our model using accuracy as the metric on the ROCStories dataset, and summarized these results in Table 2 .
Output:
| [
"Which metrics are they evaluating with?"
] | task461-691a15904a4c40fbb84d0da47e813c3f |
Definition: In this task, you will be presented with a context from an academic paper and you have to write an answerable question based on the context. Your questions can be extractive, abstractive, or yes-no questions.
Positive Example 1 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: how was the dataset built?
Positive Example 2 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language are the tweets?
Negative Example 1 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language is tweets?
Negative Example 2 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: What is the size of the dataset?
Now complete the following example -
Input: The words are represented as fixed length vectors INLINEFORM0 resulting from the concatenation of GloVe pre-trained embeddings and DepecheMood BIBREF19 lexicon representation. Since we cannot directly concatenate token-based embeddings (provided in GloVe) with the lemma#PoS-based representation available in DepecheMood, we proceeded to re-build the latter in token-based form, applying the exact same methodology albeit with two differences: we started from a larger dataset (51.9K news articles instead of 25.3K) and used a frequency cut-off, i.e. keeping only those tokens that appear at least 5 times in the corpus.
Output:
| [
"How do they incorporate lexicon into the neural network?"
] | task461-1e1e9ba9eee942fe9c1a2a979f000ce4 |
Definition: In this task, you will be presented with a context from an academic paper and you have to write an answerable question based on the context. Your questions can be extractive, abstractive, or yes-no questions.
Positive Example 1 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: how was the dataset built?
Positive Example 2 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language are the tweets?
Negative Example 1 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language is tweets?
Negative Example 2 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: What is the size of the dataset?
Now complete the following example -
Input: Hate memes were retrieved from Google Images with a downloading tool. We used the following queries to collect a total of 1,695 hate memes: racist meme (643 memes), jew meme (551 memes), and muslim meme (501 Memes). Non-hate memes were obtained from the Reddit Memes Dataset .
Output:
| [
"What is the source of memes?"
] | task461-b0e2766557c145b880947ea4f60b657d |
Definition: In this task, you will be presented with a context from an academic paper and you have to write an answerable question based on the context. Your questions can be extractive, abstractive, or yes-no questions.
Positive Example 1 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: how was the dataset built?
Positive Example 2 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language are the tweets?
Negative Example 1 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language is tweets?
Negative Example 2 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: What is the size of the dataset?
Now complete the following example -
Input: Next, for emergent language, we show that the MASC architecture can achieve very high localization accuracy, significantly outperforming the baseline that does not include this mechanism.
Output:
| [
"What evaluation metrics did the authors look at?"
] | task461-c448ba7eb78241b6bcd545e931d658d4 |
Definition: In this task, you will be presented with a context from an academic paper and you have to write an answerable question based on the context. Your questions can be extractive, abstractive, or yes-no questions.
Positive Example 1 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: how was the dataset built?
Positive Example 2 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language are the tweets?
Negative Example 1 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language is tweets?
Negative Example 2 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: What is the size of the dataset?
Now complete the following example -
Input: For both POS tagging and dependency parsing, we run experiments on the Wall Street Journal (WSJ) portion of the Penn Treebank.
Output:
| [
"Do they evaluate only on English datasets?",
"What datasets do they evaluate on?"
] | task461-7fa5a053405244828e1a868e939401ce |
Definition: In this task, you will be presented with a context from an academic paper and you have to write an answerable question based on the context. Your questions can be extractive, abstractive, or yes-no questions.
Positive Example 1 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: how was the dataset built?
Positive Example 2 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language are the tweets?
Negative Example 1 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language is tweets?
Negative Example 2 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: What is the size of the dataset?
Now complete the following example -
Input: To assess the predictive capability of this and other models, we require some method by which we can compare the models. For that purpose, we use receiver operating characteristic (ROC) curves as a visual representation of predictive effectiveness. ROC curves compare the true positive rate (TPR) and false positive rate (FPR) of a model's predictions at different threshold levels. The area under the curve (AUC) (between 0 and 1) is a numerical measure, where the higher the AUC is, the better the model performs. We cross-validate our model by first randomly splitting the corpus into a training set (95% of the corpus) and test set (5% of the corpus). We then fit the model to the training set, and use it to predict the response of the documents in the test set. We repeat this process 100 times. The threshold-averaged ROC curve BIBREF13 is found from these predictions, and shown in Figure 3 . Table 1 shows the AUC for each model considered.
Output:
| [
"How is performance measured?"
] | task461-b57cca7dc4d24ba29f774d07faec27f8 |
Definition: In this task, you will be presented with a context from an academic paper and you have to write an answerable question based on the context. Your questions can be extractive, abstractive, or yes-no questions.
Positive Example 1 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: how was the dataset built?
Positive Example 2 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language are the tweets?
Negative Example 1 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language is tweets?
Negative Example 2 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: What is the size of the dataset?
Now complete the following example -
Input: Using an encoder-decoder backbone, our model may be regarded as an extension of the constituent parsing model of BIBREF18 as shown in Figure FIGREF4. The difference is that in our model both constituent and dependency parsing share the same token representation and shared self-attention layers and each has its own individual Self-Attention Layers and subsequent processing layers. Our model includes four modules: token representation, self-attention encoder, constituent and dependency parsing decoder. Constituent Parsing Decoder Dependency Parsing Decoder
Output:
| [
"What are the models used to perform constituency and dependency parsing?"
] | task461-8ba4217d28d640a5bfa9a685622faf3c |
Definition: In this task, you will be presented with a context from an academic paper and you have to write an answerable question based on the context. Your questions can be extractive, abstractive, or yes-no questions.
Positive Example 1 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: how was the dataset built?
Positive Example 2 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language are the tweets?
Negative Example 1 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language is tweets?
Negative Example 2 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: What is the size of the dataset?
Now complete the following example -
Input: Methods ::: Combining the two methods
We further propose to use the two methods together to combine their strengths. In fact, while the length token acts as a soft constraint to bias NMT to produce short or long translation with respect to the source, actually no length information is given to the network. On the other side, length encoding leverages information about the target length, but it is agnostic of the source length.
Output:
| [
"Do they experiment with combining both methods?"
] | task461-6e35539070d24a6ba2722b226143ce9d |
Definition: In this task, you will be presented with a context from an academic paper and you have to write an answerable question based on the context. Your questions can be extractive, abstractive, or yes-no questions.
Positive Example 1 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: how was the dataset built?
Positive Example 2 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language are the tweets?
Negative Example 1 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language is tweets?
Negative Example 2 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: What is the size of the dataset?
Now complete the following example -
Input: A simple, yet recurrent text model is the well-known word co-occurrence network. After optional textual pre-processing steps, in a co-occurrence network each different word becomes a node and edges are established via co-occurrence in a desired window. A common strategy connects only adjacent words in the so called word adjacency networks.
Output:
| [
"On what model architectures are previous co-occurence networks based?"
] | task461-f7fc57f8a8a94f7493b20355a88c10f7 |
Definition: In this task, you will be presented with a context from an academic paper and you have to write an answerable question based on the context. Your questions can be extractive, abstractive, or yes-no questions.
Positive Example 1 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: how was the dataset built?
Positive Example 2 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language are the tweets?
Negative Example 1 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language is tweets?
Negative Example 2 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: What is the size of the dataset?
Now complete the following example -
Input: We describe our rules for WikiSQL here. We first detect WHERE values, which exactly match to table cells. After that, if a cell appears at more than one column, we choose the column name with more overlapped words with the question, with a constraint that the number of co-occurred words is larger than 1. By default, a WHERE operator is INLINEFORM0 , except for the case that surrounding words of a value contain keywords for INLINEFORM1 and INLINEFORM2 . Then, we deal with the SELECT column, which has the largest number of co-occurred words and cannot be same with any WHERE column. By default, the SELECT AGG is NONE, except for matching to any keywords in Table TABREF8 . The coverage of our rule on training set is 78.4%, with execution accuracy of 77.9%. Our rule for KBQA is simple without using a curated mapping dictionary. The pipeline of rules in SequentialQA is similar to that of WikiSQL. Compared to the grammar of WikiSQL, the grammar of SequentialQA has additional actions including copying the previous-turn logical form, no greater than, no more than, and negation.
Output:
| [
"How many rules had to be defined?"
] | task461-86d5dd2da38d44f3b6be7116f018d9c2 |
Definition: In this task, you will be presented with a context from an academic paper and you have to write an answerable question based on the context. Your questions can be extractive, abstractive, or yes-no questions.
Positive Example 1 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: how was the dataset built?
Positive Example 2 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language are the tweets?
Negative Example 1 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language is tweets?
Negative Example 2 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: What is the size of the dataset?
Now complete the following example -
Input: At each training step, we train the model with a batch of original examples along with adversarial examples with balanced labels. The adversarial examples account for around 10% in a batch. During training, we generate adversarial examples with the current model as the target and update the model parameters with the hybrid batch iteratively.
Output:
| [
"What is discriminator in this generative adversarial setup?"
] | task461-5672331808b14179b248630ca4a11d62 |
Definition: In this task, you will be presented with a context from an academic paper and you have to write an answerable question based on the context. Your questions can be extractive, abstractive, or yes-no questions.
Positive Example 1 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: how was the dataset built?
Positive Example 2 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language are the tweets?
Negative Example 1 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language is tweets?
Negative Example 2 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: What is the size of the dataset?
Now complete the following example -
Input: Moreover, the add and add-gated variants of Bertram perform surprisingly well for more frequent words, improving the score for WNLaMPro-medium by 50% compared to BERT$_\text{base}$ and 31% compared to Attentive Mimicking.
Output:
| [
"How much is representaton improved for rare/medum frequency words compared to standalone BERT and previous work?"
] | task461-3fd1d3cdc1d743ddb0d1fc3dc72ab9de |
Definition: In this task, you will be presented with a context from an academic paper and you have to write an answerable question based on the context. Your questions can be extractive, abstractive, or yes-no questions.
Positive Example 1 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: how was the dataset built?
Positive Example 2 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language are the tweets?
Negative Example 1 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language is tweets?
Negative Example 2 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: What is the size of the dataset?
Now complete the following example -
Input: We evaluate our method on IWSLT16 German-English (DE-EN) translation in both directions, WMT15 English-German (EN-DE) translation in both directions, and NIST Chinese-to-English (ZH$\rightarrow $EN) translation.
Output:
| [
"What corpora is used?"
] | task461-3f8c7fea02724f3bb6fe64eb273cb757 |
Definition: In this task, you will be presented with a context from an academic paper and you have to write an answerable question based on the context. Your questions can be extractive, abstractive, or yes-no questions.
Positive Example 1 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: how was the dataset built?
Positive Example 2 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language are the tweets?
Negative Example 1 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language is tweets?
Negative Example 2 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: What is the size of the dataset?
Now complete the following example -
Input: Ablation Study
To further investigate the efficacy of the key components in our framework, namely, THA and STN, we perform ablation study as shown in the second block of Table TABREF39 . The results show that each of THA and STN is helpful for improving the performance, and the contribution of STN is slightly larger than THA. “OURS w/o THA & STN” only keeps the basic bi-linear attention. Although it performs not bad, it is still less competitive compared with the strongest baseline (i.e., CMLA), suggesting that only using attention mechanism to distill opinion summary is not enough. After inserting the STN component before the bi-linear attention, i.e. “OURS w/o THA”, we get about 1% absolute gains on each dataset, and then the performance is comparable to CMLA. By adding THA, i.e. “OURS”, the performance is further improved, and all state-of-the-art methods are surpassed.
Output:
| [
"Do they explore how useful is the detection history and opinion summary?"
] | task461-376f4e5339f34e278b1663160ae0f368 |
Definition: In this task, you will be presented with a context from an academic paper and you have to write an answerable question based on the context. Your questions can be extractive, abstractive, or yes-no questions.
Positive Example 1 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: how was the dataset built?
Positive Example 2 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language are the tweets?
Negative Example 1 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language is tweets?
Negative Example 2 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: What is the size of the dataset?
Now complete the following example -
Input: In this work, we make use of the widely-recognized state of the art entailment technique – BERT BIBREF18, and train it on three mainstream entailment datasets: MNLI BIBREF19, GLUE RTE BIBREF20, BIBREF21 and FEVER BIBREF22, respectively. We convert all datasets into binary case: “entailment” vs. “non-entailment”, by changing the label “neutral” (if exist in some datasets) into “non-entailment”.
For our label-fully-unseen setup, we directly apply this pretrained entailment model on the test sets of all $\textsc {0shot-tc}$ aspects. For label-partially-unseen setup in which we intentionally provide annotated data, we first pretrain BERT on the MNLI/FEVER/RTE, then fine-tune on the provided training data.
Output:
| [
"Do they use pretrained models?"
] | task461-d9b26fd4453840c4bfd34ae18d397d24 |
Definition: In this task, you will be presented with a context from an academic paper and you have to write an answerable question based on the context. Your questions can be extractive, abstractive, or yes-no questions.
Positive Example 1 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: how was the dataset built?
Positive Example 2 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language are the tweets?
Negative Example 1 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language is tweets?
Negative Example 2 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: What is the size of the dataset?
Now complete the following example -
Input: We first use state-of-the-art PDTB taggers for our baseline BIBREF13 , BIBREF12 for the evaluation of the causality prediction of our models ( BIBREF12 requires sentences extracted from the text as its input, so we used our parser to extract sentences from the message).
Output:
| [
"What baselines did they consider?"
] | task461-8d6b22c1aff849299e237a7635517151 |
Definition: In this task, you will be presented with a context from an academic paper and you have to write an answerable question based on the context. Your questions can be extractive, abstractive, or yes-no questions.
Positive Example 1 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: how was the dataset built?
Positive Example 2 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language are the tweets?
Negative Example 1 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language is tweets?
Negative Example 2 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: What is the size of the dataset?
Now complete the following example -
Input: Note that the BoW/SVM model being a linear predictor relying directly on word frequency statistics, it lacks expressive power in comparison to the CNN model which additionally learns intermediate hidden layer representations and convolutional filters. Moreover the CNN model can take advantage of the semantic similarity encoded in the distributed word2vec representations, while for the BoW/SVM model all words are “equidistant” in the bag-of-words semantic space
Output:
| [
"According to the authors, why does the CNN model exhibit a higher level of explainability?"
] | task461-83cfa2f3a56c4a1d8446601d9dad8da4 |
Definition: In this task, you will be presented with a context from an academic paper and you have to write an answerable question based on the context. Your questions can be extractive, abstractive, or yes-no questions.
Positive Example 1 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: how was the dataset built?
Positive Example 2 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language are the tweets?
Negative Example 1 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language is tweets?
Negative Example 2 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: What is the size of the dataset?
Now complete the following example -
Input: FarsNet [20] [21] is the first WordNet for Persian, developed by the NLP Lab at Shahid Beheshti University and it follows the same structure as the original WordNet.
Output:
| [
"What is the WordNet counterpart for Persian?"
] | task461-4a910173e5f041efa53405b394ea3c03 |
Definition: In this task, you will be presented with a context from an academic paper and you have to write an answerable question based on the context. Your questions can be extractive, abstractive, or yes-no questions.
Positive Example 1 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: how was the dataset built?
Positive Example 2 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language are the tweets?
Negative Example 1 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language is tweets?
Negative Example 2 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: What is the size of the dataset?
Now complete the following example -
Input: Throughout this article, we use two different embedding spaces. The first is the widely used representation built on GoogleNews BIBREF8 . The second is taken from BIBREF2 , and was trained on a Reddit dataset BIBREF9 .
Output:
| [
"Which embeddings do they detect biases in?"
] | task461-fe6193dc84224719a651e6031e904805 |
Definition: In this task, you will be presented with a context from an academic paper and you have to write an answerable question based on the context. Your questions can be extractive, abstractive, or yes-no questions.
Positive Example 1 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: how was the dataset built?
Positive Example 2 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language are the tweets?
Negative Example 1 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language is tweets?
Negative Example 2 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: What is the size of the dataset?
Now complete the following example -
Input: We carried out experiments on four Chinese NLP tasks, including Emotion Classification (EC), Named Entity Recognition (NER), Sentence Pair Matching (SPM) and Natural Language Inference (NLI).
Output:
| [
"What benchmarks did they experiment on?"
] | task461-a854d8f113a74f3dbd96a4279bf192e6 |
Definition: In this task, you will be presented with a context from an academic paper and you have to write an answerable question based on the context. Your questions can be extractive, abstractive, or yes-no questions.
Positive Example 1 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: how was the dataset built?
Positive Example 2 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language are the tweets?
Negative Example 1 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language is tweets?
Negative Example 2 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: What is the size of the dataset?
Now complete the following example -
Input: We design the word-level refine decoder because this process is similar to the cloze task in BERT's pre-train process, therefore by using the ability of the contextual language model the decoder can generate more fluent and natural sequences.
Output:
| [
"Why masking words in the decoder is helpful?"
] | task461-6ed47bacfaac44b2a64019ed751ca208 |
Definition: In this task, you will be presented with a context from an academic paper and you have to write an answerable question based on the context. Your questions can be extractive, abstractive, or yes-no questions.
Positive Example 1 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: how was the dataset built?
Positive Example 2 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language are the tweets?
Negative Example 1 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language is tweets?
Negative Example 2 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: What is the size of the dataset?
Now complete the following example -
Input: To deal with this problem, BIBREF1 introduced a semantically conditioned generation model using Hierarchical Disentangled Self-Attention (HDSA) .
Output:
| [
"what semantically conditioned models did they compare with?"
] | task461-067b4e90d9dd4801b05bd6b6dd9095cf |
Definition: In this task, you will be presented with a context from an academic paper and you have to write an answerable question based on the context. Your questions can be extractive, abstractive, or yes-no questions.
Positive Example 1 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: how was the dataset built?
Positive Example 2 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language are the tweets?
Negative Example 1 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language is tweets?
Negative Example 2 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: What is the size of the dataset?
Now complete the following example -
Input: BIBREF17: The Lemming model is a log-linear model that performs joint morphological tagging and lemmatization.
Output:
| [
"What were the non-neural baselines used for the task?"
] | task461-5db6608e98464775be5b046852d361ab |
Definition: In this task, you will be presented with a context from an academic paper and you have to write an answerable question based on the context. Your questions can be extractive, abstractive, or yes-no questions.
Positive Example 1 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: how was the dataset built?
Positive Example 2 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language are the tweets?
Negative Example 1 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language is tweets?
Negative Example 2 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: What is the size of the dataset?
Now complete the following example -
Input: To further demonstrate the effectiveness of the additional task-specific BiRNN layers in our architecture, we conducted an ablation study using the CoNLL04 dataset. We trained and evaluated in the same manner described above, using the same hyperparameters, with the following exceptions:
We used either (i) zero NER-specific BiRNN layers, (ii) zero RE-specific BiRNN layers, or (iii) zero task-specific BiRNN layers of any kind.
We increased the number of shared BiRNN layers to keep the total number of model parameters consistent with the number of parameters in the baseline model.
We average the results for each set of hyperparameter across three trials with random weight initializations.
Output:
| [
"What were the variables in the ablation study?"
] | task461-d07180915b484929946944ec68d7c35b |
Definition: In this task, you will be presented with a context from an academic paper and you have to write an answerable question based on the context. Your questions can be extractive, abstractive, or yes-no questions.
Positive Example 1 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: how was the dataset built?
Positive Example 2 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language are the tweets?
Negative Example 1 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language is tweets?
Negative Example 2 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: What is the size of the dataset?
Now complete the following example -
Input: It should also be noted that signals can be recognized even when the model misclassifies relations, since ${\Delta }_s$ does not rely on correct classification: it merely quantifies the contribution of a word in context toward the correct label's score. If we examine the influence of each word on the score of the correct relation, that impact should and does still correlate with human judgments based on what the system may tag as the second or third best class to choose.
Output:
| [
"Where does proposed metric overlap with juman judgement?"
] | task461-6f20c0c1211e49ed853f050001b27645 |
Definition: In this task, you will be presented with a context from an academic paper and you have to write an answerable question based on the context. Your questions can be extractive, abstractive, or yes-no questions.
Positive Example 1 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: how was the dataset built?
Positive Example 2 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language are the tweets?
Negative Example 1 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language is tweets?
Negative Example 2 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: What is the size of the dataset?
Now complete the following example -
Input: Four factual attributes pertaining to the 200 colleges are extracted from the U.S. News Statistics, which consists of Undergraduate Enrollment, Male/Female Ratio, Private/Public, and Region (Northeast, South, West, and Midwest).
Output:
| [
"Which major geographical regions are studied?"
] | task461-cbb905e70dbc412aaa3d8d5291e25772 |
Definition: In this task, you will be presented with a context from an academic paper and you have to write an answerable question based on the context. Your questions can be extractive, abstractive, or yes-no questions.
Positive Example 1 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: how was the dataset built?
Positive Example 2 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language are the tweets?
Negative Example 1 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language is tweets?
Negative Example 2 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: What is the size of the dataset?
Now complete the following example -
Input: VQA research began in earnest in late 2014 when the DAQUAR dataset was released BIBREF0
Output:
| [
"From when are many VQA datasets collected?"
] | task461-5847e7a548f147f8a7428d5fd8ec8b4e |
Definition: In this task, you will be presented with a context from an academic paper and you have to write an answerable question based on the context. Your questions can be extractive, abstractive, or yes-no questions.
Positive Example 1 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: how was the dataset built?
Positive Example 2 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language are the tweets?
Negative Example 1 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language is tweets?
Negative Example 2 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: What is the size of the dataset?
Now complete the following example -
Input: For the NER task, we consider both Chinese datasets, i.e., OntoNotes4.0 BIBREF34 and MSRA BIBREF35, and English datasets, i.e., CoNLL2003 BIBREF36 and OntoNotes5.0 BIBREF37. Table shows experimental results on NER datasets. For English datasets including CoNLL2003 and OntoNotes5.0, our proposed method outperforms BERT-MRCBIBREF38 by +0.29 and +0.96 respectively. We observe huge performance boosts on Chinese datasets, achieving F1 improvements by +0.97 and +2.36 on MSRA and OntoNotes4.0, respectively. As far as we are concerned, we are setting new SOTA performances on all of the four NER datasets.
Output:
| [
"What are method's improvements of F1 for NER task for English and Chinese datasets?"
] | task461-3ec10ddbbc024ef8aef0db901693bb94 |
Definition: In this task, you will be presented with a context from an academic paper and you have to write an answerable question based on the context. Your questions can be extractive, abstractive, or yes-no questions.
Positive Example 1 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: how was the dataset built?
Positive Example 2 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language are the tweets?
Negative Example 1 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language is tweets?
Negative Example 2 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: What is the size of the dataset?
Now complete the following example -
Input: We decided to explore the remaining space for improvement on the CBT by testing humans on a random subset of 50 named entity and 50 common noun validation questions that the psr ensemble could not answer correctly.
Output:
| [
"How do they show there is space for further improvement?"
] | task461-e32288ee05374c04b78f9eec4ccebe9c |
Definition: In this task, you will be presented with a context from an academic paper and you have to write an answerable question based on the context. Your questions can be extractive, abstractive, or yes-no questions.
Positive Example 1 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: how was the dataset built?
Positive Example 2 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language are the tweets?
Negative Example 1 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language is tweets?
Negative Example 2 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: What is the size of the dataset?
Now complete the following example -
Input: Datasets: We experimented on four standard datasets: WN18 and FB15k are extracted by BIBREF5 from Wordnet BIBREF32 Freebase BIBREF33 .
Output:
| [
"What datasets are used to evaluate the model?"
] | task461-7dcc0cf3bf6c425e8d11a05cbec70911 |
Definition: In this task, you will be presented with a context from an academic paper and you have to write an answerable question based on the context. Your questions can be extractive, abstractive, or yes-no questions.
Positive Example 1 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: how was the dataset built?
Positive Example 2 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language are the tweets?
Negative Example 1 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language is tweets?
Negative Example 2 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: What is the size of the dataset?
Now complete the following example -
Input: Given a statement and articles, workers are asked to judge whether the statement can be derived from the articles at three grades: True, Likely (i.e. Answerable), or Unsure (i.e. Unanswerable). If a worker selects Unsure, we ask workers to tell us why they are unsure from two choices (“Not stated in the article” or “Other”). If a worker selects True or Likely in the judgement task, we first ask which sentences in the given articles are justification explanations for a given statement, similarly to HotpotQA BIBREF2. The “summary” text boxes (i.e. NLDs) are then initialized with these selected sentences.
Output:
| [
"How was the dataset annotated?"
] | task461-9492e3672f494eebac47e3e694af25d9 |
Definition: In this task, you will be presented with a context from an academic paper and you have to write an answerable question based on the context. Your questions can be extractive, abstractive, or yes-no questions.
Positive Example 1 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: how was the dataset built?
Positive Example 2 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language are the tweets?
Negative Example 1 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language is tweets?
Negative Example 2 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: What is the size of the dataset?
Now complete the following example -
Input: The annotation scheme was developed to capture three aspects of classroom talk that are theorized in the literature as important to discussion quality and learning opportunities: argumentation (the process of systematically reasoning in support of an idea), specificity (the quality of belonging or relating uniquely to a particular subject), and knowledge domain (area of expertise represented in the content of the talk).
Output:
| [
"how do they measure discussion quality?"
] | task461-18a2f62291a643e084dfaaeefff19749 |
Definition: In this task, you will be presented with a context from an academic paper and you have to write an answerable question based on the context. Your questions can be extractive, abstractive, or yes-no questions.
Positive Example 1 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: how was the dataset built?
Positive Example 2 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language are the tweets?
Negative Example 1 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language is tweets?
Negative Example 2 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: What is the size of the dataset?
Now complete the following example -
Input: The current release of Katecheo uses a Bi-Directional Attention Flow, or BiDAF, model for reading comprehension BIBREF6 . Future releases of Katecheo will include the ability to swap out the reading comprehension model for newer architectures based on, e.g., BERT BIBREF8 or XLNet BIBREF9 or custom trained models.
Architecture and Configuration
Output:
| [
"what pretrained models were used?"
] | task461-861701949fe249e6b92b39a50bb1e314 |
Definition: In this task, you will be presented with a context from an academic paper and you have to write an answerable question based on the context. Your questions can be extractive, abstractive, or yes-no questions.
Positive Example 1 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: how was the dataset built?
Positive Example 2 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language are the tweets?
Negative Example 1 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language is tweets?
Negative Example 2 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: What is the size of the dataset?
Now complete the following example -
Input: To identify new keywords in the selected microposts, we again leverage crowdsourcing, as humans are typically better than machines at providing specific explanations BIBREF18, BIBREF19. In the crowdsourcing task, workers are first asked to find those microposts where the model predictions are deemed correct. Then, from those microposts, workers are asked to find the keyword that best indicates the class of the microposts as predicted by the model.
Output:
| [
"How is the keyword specific expectation elicited from the crowd?"
] | task461-282a4d00240f4a8195004f292a07bcf7 |
Definition: In this task, you will be presented with a context from an academic paper and you have to write an answerable question based on the context. Your questions can be extractive, abstractive, or yes-no questions.
Positive Example 1 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: how was the dataset built?
Positive Example 2 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language are the tweets?
Negative Example 1 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language is tweets?
Negative Example 2 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: What is the size of the dataset?
Now complete the following example -
Input: TOEFL listening comprehension test is for human English learners whose native language is not English. This paper reports how today's machine can perform with such a test.
The listening comprehension task considered here is highly related to Spoken Question Answering (SQA) BIBREF0 , BIBREF1 .
Output:
| [
"What is the new task proposed in this work?"
] | task461-482a1231cf8348d493dc3a196fc401aa |
Definition: In this task, you will be presented with a context from an academic paper and you have to write an answerable question based on the context. Your questions can be extractive, abstractive, or yes-no questions.
Positive Example 1 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: how was the dataset built?
Positive Example 2 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language are the tweets?
Negative Example 1 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language is tweets?
Negative Example 2 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: What is the size of the dataset?
Now complete the following example -
Input: Four datasets are used in our work, including CoNLL 2003 German BIBREF9 , CoNLL 2002 Spanish BIBREF10 , OntoNotes 4 BIBREF11 and Weibo NER BIBREF12 . Table TABREF22 shows the results on Chinese OntoNotes 4.0.
Output:
| [
"Which languages do they work with?"
] | task461-e4b48760ccc14872a170c11e9a7a6194 |
Definition: In this task, you will be presented with a context from an academic paper and you have to write an answerable question based on the context. Your questions can be extractive, abstractive, or yes-no questions.
Positive Example 1 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: how was the dataset built?
Positive Example 2 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language are the tweets?
Negative Example 1 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language is tweets?
Negative Example 2 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: What is the size of the dataset?
Now complete the following example -
Input: The second, Continuous Bag-of-Words (CBOW), the model is given the sequence of words without the middle one and attempts to predict this omitted word.
Output:
| [
"Which word embeddings are analysed?"
] | task461-7d62917052fd419f8c263daf6a544ea1 |
Definition: In this task, you will be presented with a context from an academic paper and you have to write an answerable question based on the context. Your questions can be extractive, abstractive, or yes-no questions.
Positive Example 1 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: how was the dataset built?
Positive Example 2 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language are the tweets?
Negative Example 1 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language is tweets?
Negative Example 2 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: What is the size of the dataset?
Now complete the following example -
Input: The Bi-LSTM model consists of a Bi-LSTM layer followed by a linear layer to extract input features. The Bi-LSTM layer has a 300-dimensional hidden state for each direction. For the final classification, an additional linear layer is added to output predicted class distributions. The BERT model is obtained by fine-tuning the pre-trained BERT embeddings on NER data with an additional untrained CRF classifier. We fine-tuned all the parameters of BERT including that of the CRF end-to-end.
Output:
| [
"What classifiers were used in experiments?"
] | task461-30d5ce3466c74dddb0c62f75983c2964 |
Definition: In this task, you will be presented with a context from an academic paper and you have to write an answerable question based on the context. Your questions can be extractive, abstractive, or yes-no questions.
Positive Example 1 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: how was the dataset built?
Positive Example 2 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language are the tweets?
Negative Example 1 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language is tweets?
Negative Example 2 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: What is the size of the dataset?
Now complete the following example -
Input: We have also included the unlabelled set of 2472 telephone calls from both minor (Cebuano and Mandarin) and major (Tagalog and Cantonese) languages provided by NIST in the system training.
Output:
| [
"Which are the novel languages on which SRE placed emphasis on?"
] | task461-8a9cd324fb4341189728905fb99fd2d7 |
Definition: In this task, you will be presented with a context from an academic paper and you have to write an answerable question based on the context. Your questions can be extractive, abstractive, or yes-no questions.
Positive Example 1 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: how was the dataset built?
Positive Example 2 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language are the tweets?
Negative Example 1 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language is tweets?
Negative Example 2 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: What is the size of the dataset?
Now complete the following example -
Input: However, we also showed difference in produced errors for each method and different impact at word-level depending of the approach or units. Thus, future work will focus on analysing the orthographic output of these systems in two ways: 1) investigate errors produced by the end-to-end methods and explore several approaches to correct common errors done in French and 2) compare the end-to-end methods in a SLU context and evaluate the semantic value of the partially correct produced words.
Output:
| [
"What will be in focus for future work?"
] | task461-96a185229c7b4b3ea58d4560a111bd44 |
Definition: In this task, you will be presented with a context from an academic paper and you have to write an answerable question based on the context. Your questions can be extractive, abstractive, or yes-no questions.
Positive Example 1 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: how was the dataset built?
Positive Example 2 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language are the tweets?
Negative Example 1 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language is tweets?
Negative Example 2 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: What is the size of the dataset?
Now complete the following example -
Input: We address the robustness problem on top of GE-FL BIBREF0 , a GE method which leverages labeled features as prior knowledge.
Output:
| [
"What background knowledge do they leverage?"
] | task461-f9a590084c9a49d4b71c4342d449774f |
Definition: In this task, you will be presented with a context from an academic paper and you have to write an answerable question based on the context. Your questions can be extractive, abstractive, or yes-no questions.
Positive Example 1 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: how was the dataset built?
Positive Example 2 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language are the tweets?
Negative Example 1 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language is tweets?
Negative Example 2 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: What is the size of the dataset?
Now complete the following example -
Input: to answer how offensive they thought the tweet was on a 6-point Likert scale from 1 (Not offensive at all) to 6 (Very offensive). If they answered 4 or higher, the participants had the option to state which particular words they found offensive.
Output:
| [
"Was the degree of offensiveness taken as how generally offensive the text was, or how personally offensive it was to the annotator?"
] | task461-ee34bbcff914452e9c545de117abd4f8 |
Definition: In this task, you will be presented with a context from an academic paper and you have to write an answerable question based on the context. Your questions can be extractive, abstractive, or yes-no questions.
Positive Example 1 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: how was the dataset built?
Positive Example 2 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language are the tweets?
Negative Example 1 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language is tweets?
Negative Example 2 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: What is the size of the dataset?
Now complete the following example -
Input: The results show that NCEL consistently outperforms various baselines with a favorable generalization ability.
Output:
| [
"How effective is their NCEL approach overall?"
] | task461-7572cfc075a14f2c909ce3df4773e90e |
Definition: In this task, you will be presented with a context from an academic paper and you have to write an answerable question based on the context. Your questions can be extractive, abstractive, or yes-no questions.
Positive Example 1 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: how was the dataset built?
Positive Example 2 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language are the tweets?
Negative Example 1 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language is tweets?
Negative Example 2 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: What is the size of the dataset?
Now complete the following example -
Input: For the intitial data collection using the CRWIZ platform, 145 unique dialogues were collected (each dialogue consists of a conversation between two participants). The average time per assignment was 10 minutes 47 seconds, very close to our initial estimate of 10 minutes, and the task was available for 5 days in AMT. Out of the 145 dialogues, 14 (9.66%) obtained the bonus of $0.2 for resolving the emergency. We predicted that only a small portion of the participants would be able to resolve the emergency in less than 6 minutes, thus it was framed as a bonus challenge rather than a requirement to get paid. The fastest time recorded to resolve the emergency was 4 minutes 13 seconds with a mean of 5 minutes 8 seconds. Table TABREF28 shows several interaction statistics for the data collected compared to the single lab-based WoZ study BIBREF4.
Data Analysis ::: Subjective Data
Table TABREF33 gives the results from the post-task survey. We observe, that subjective and objective task success are similar in that the dialogues that resolved the emergency were rated consistently higher than the rest.
Mann-Whitney-U one-tailed tests show that the scores of the Emergency Resolved Dialogues for Q1 and Q2 were significantly higher than the scores of the Emergency Not Resolved Dialogues at the 95% confidence level (Q1: $U = 1654.5$, $p < 0.0001$; Q2: $U = 2195$, $p = 0.009$, both $p < 0.05$). This indicates that effective collaboration and information ease are key to task completion in this setting.
Regarding the qualitative data, one of the objectives of the Wizard-of-Oz technique was to make the participant believe that they are interacting with an automated agent and the qualitative feedback seemed to reflect this: “The AI in the game was not helpful at all [...]” or “I was talking to Fred a bot assistant, I had no other partner in the game“.
Data Analysis ::: Single vs Multiple Wizards
In Table TABREF28, we compare various metrics from the dialogues collected with crowdsourcing with the dialogues previously collected in a lab environment for a similar task. Most figures are comparable, except the number of emergency assistant turns (and consequently the total number of turns). To further understand these differences, we have first grouped the dialogue acts in four different broader types: Updates, Actions, Interactions and Requests, and computed the relative frequency of each of these types in both data collections. In addition, Figures FIGREF29 and FIGREF30 show the distribution of the most frequent dialogue acts in the different settings. It is visible that in the lab setting where the interaction was face-to-face with a robot, the Wizard used more Interaction dialogue acts (Table TABREF32). These were often used in context where the Wizard needed to hold the turn while looking for the appropriate prompt or waiting for the robot to arrive at the specified goal in the environment. On the other hand, in the crowdsourced data collection utterances, the situation updates were a more common choice while the assistant was waiting for the robot to travel to the specified goal in the environment.
Perhaps not surprisingly, the data shows a medium strong positive correlation between task success and the number of Action type dialogue acts the Wizard performs, triggering events in the world leading to success ($R=0.475$). There is also a positive correlation between task success and the number of Request dialogue acts requesting confirmation before actions ($R=0.421$), e.g., “Which robot do you want to send?”. As Table 3 shows, these are relatively rare but perhaps reflect a level of collaboration needed to further the task to completion. Table TABREF40 shows one of the dialogues collected where the Emergency Assistant continuously engaged with the Operator through these types of dialogue acts.
The task success rate was also very different between the two set-ups. In experiments reported in BIBREF4, 96% of the dialogues led to the extinction of the fire whereas in the crowdsourcing setting only 9.66% achieved the same goal. In the crowdsourced setting, the robots were slower moving at realistic speeds unlike the lab setting. A higher bonus and more time for the task might lead to a higher task success rate.
Data Analysis ::: Limitations
It is important to consider the number of available participants ready and willing to perform the task at any one time. This type of crowdsourcing requires two participants to connect within a few minutes of each other to be partnered together. As mentioned above, there were some issues with participants not collaborating and these dialogues had to be discarded as they were not of use.
Output:
| [
"Is CRWIZ already used for data collection, what are the results?"
] | task461-043ddf104b434bfbafed2bb824b52c26 |
Definition: In this task, you will be presented with a context from an academic paper and you have to write an answerable question based on the context. Your questions can be extractive, abstractive, or yes-no questions.
Positive Example 1 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: how was the dataset built?
Positive Example 2 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language are the tweets?
Negative Example 1 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language is tweets?
Negative Example 2 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: What is the size of the dataset?
Now complete the following example -
Input: Table TABREF18 shows the Spearman correlation values of GM$\_$KL model evaluated on the benchmark word similarity datasets: SL BIBREF20, WS, WS-R, WS-S BIBREF21, MEN BIBREF22, MC BIBREF23, RG BIBREF24, YP BIBREF25, MTurk-287 and MTurk-771 BIBREF26, BIBREF27, and RW BIBREF28. Table TABREF19 shows the evaluation results of GM$\_$KL model on the entailment datasets such as entailment pairs dataset BIBREF29 created from WordNet with both positive and negative labels, a crowdsourced dataset BIBREF30 of 79 semantic relations labelled as entailed or not and annotated distributionally similar nouns dataset BIBREF31
Output:
| [
"What are the qualitative experiments performed on benchmark datasets?"
] | task461-7c466d0b9c244ba8aaad774c75ec3ce1 |
Definition: In this task, you will be presented with a context from an academic paper and you have to write an answerable question based on the context. Your questions can be extractive, abstractive, or yes-no questions.
Positive Example 1 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: how was the dataset built?
Positive Example 2 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language are the tweets?
Negative Example 1 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language is tweets?
Negative Example 2 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: What is the size of the dataset?
Now complete the following example -
Input: Our goal is to compare the efectiviness of the proposed approach against the baseline system described in BIBREF13 . We evaluate the false-reject (FR) and false-accept (FA) tradeoff across several end-to-end models of distinct sizes and computational complexities. As can be seen in the Receiver Operating Characteristic (ROC) curves in Figure FIGREF14 , the 2 largest end-to-end models, with 2-stage training, significantly outperform the recognition quality of the much larger and complex Baseline_1850K system. More specifically, E2E_318K_2stage and E2E_700K_2stage show up to 60% relative FR rate reduction over Baseline_1850K in most test conditions.
Output:
| [
"How do they measure the quality of detection?"
] | task461-8c91c87d2c3448938c03ec541a224872 |
Definition: In this task, you will be presented with a context from an academic paper and you have to write an answerable question based on the context. Your questions can be extractive, abstractive, or yes-no questions.
Positive Example 1 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: how was the dataset built?
Positive Example 2 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language are the tweets?
Negative Example 1 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language is tweets?
Negative Example 2 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: What is the size of the dataset?
Now complete the following example -
Input: The task of attribute embedding lays is embedding every value in attribute triples into a continuous vector space while preserving the semantic information. To capture both high-order structural information of KGs, we used an attention-based embedding propagation method. The final embedding of entities, relations and values are feed into two different deep neural network for two different tasks including link predication and entity classification.
Output:
| [
"How does KANE capture both high-order structural and attribute information of KGs in an efficient, explicit and unified manner?"
] | task461-76c559f1157248ea924ed8c038b80673 |
Definition: In this task, you will be presented with a context from an academic paper and you have to write an answerable question based on the context. Your questions can be extractive, abstractive, or yes-no questions.
Positive Example 1 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: how was the dataset built?
Positive Example 2 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language are the tweets?
Negative Example 1 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language is tweets?
Negative Example 2 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: What is the size of the dataset?
Now complete the following example -
Input: This layer consists of two submodules: the Multi-Head Attention (MHA) and the Point-wise Convolution Transformation (PCT).
Output:
| [
"Do they use multi-attention heads?"
] | task461-ea3233274e524a82b8fefe6e97f02e66 |
Definition: In this task, you will be presented with a context from an academic paper and you have to write an answerable question based on the context. Your questions can be extractive, abstractive, or yes-no questions.
Positive Example 1 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: how was the dataset built?
Positive Example 2 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language are the tweets?
Negative Example 1 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language is tweets?
Negative Example 2 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: What is the size of the dataset?
Now complete the following example -
Input: Sememes are minimum semantic units of word meanings, and the meaning of each word sense is typically composed of several sememes, as is illustrated in Figure 1 .
Output:
| [
"What is a sememe?"
] | task461-64731f9065aa415c91d0c48e195f1cdd |
Definition: In this task, you will be presented with a context from an academic paper and you have to write an answerable question based on the context. Your questions can be extractive, abstractive, or yes-no questions.
Positive Example 1 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: how was the dataset built?
Positive Example 2 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language are the tweets?
Negative Example 1 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language is tweets?
Negative Example 2 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: What is the size of the dataset?
Now complete the following example -
Input: The dataset consists of a set of polysemous words: 20 nouns, 20 verbs, and 10 adjectives and specifies 20 to 100 contexts per word, with the total of 4,664 contexts, drawn from the Open American National Corpus. Given a set of contexts of a polysemous word, the participants of the competition had to divide them into clusters by sense of the word. The contexts are manually labelled with WordNet senses of the target words, the gold standard clustering is generated from this labelling.
The task allows two setups: graded WSI where participants can submit multiple senses per word and provide the probability of each sense in a particular context, and non-graded WSI where a model determines a single sense for a word in context. In our experiments we performed non-graded WSI. We considered the most suitable sense as the one with the highest cosine similarity with embeddings of the context, as described in Section SECREF9.
Output:
| [
"How are the different senses annotated/labeled? "
] | task461-034984dce30d4a08a7a1ed89d5793d49 |
Definition: In this task, you will be presented with a context from an academic paper and you have to write an answerable question based on the context. Your questions can be extractive, abstractive, or yes-no questions.
Positive Example 1 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: how was the dataset built?
Positive Example 2 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language are the tweets?
Negative Example 1 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language is tweets?
Negative Example 2 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: What is the size of the dataset?
Now complete the following example -
Input: An attention-based sequence-to-sequence model with the emoji vector as additional input as discribed in MojiTalk BIBREF16. CVAE.
An RNN-based conditional variational autoencoder for dialogue response generation BIBREF16, which uses a multivariate Gaussian latent variable to model the response and concatenate it with the last hidden state of the encoder as the initial state of the decoder. KL annealing, early stopping strategy and bag-of-word auxiliary loss are applied during the training. We use the implementation released by BIBREF16
Output:
| [
"What baselines other than standard transformers are used in experiments?"
] | task461-5243b5e6400144c18ee9ed576966676b |
Definition: In this task, you will be presented with a context from an academic paper and you have to write an answerable question based on the context. Your questions can be extractive, abstractive, or yes-no questions.
Positive Example 1 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: how was the dataset built?
Positive Example 2 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language are the tweets?
Negative Example 1 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language is tweets?
Negative Example 2 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: What is the size of the dataset?
Now complete the following example -
Input: In our setup, our starting point is a base model, trained on NLI data. Rather than employing automated adversarial methods, here the model's “adversary” is a human annotator. Given a context (also often called a “premise” in NLI), and a desired target label, we ask the human writer to provide a hypothesis that fools the model into misclassifying the label. One can think of the writer as a “white hat” hacker, trying to identify vulnerabilities in the system. For each human-generated example that is misclassified, we also ask the writer to provide a reason why they believe it was misclassified.
Output:
| [
"Do they use active learning to create their dataset?"
] | task461-51c127ccbd2f4f51b0afa2cfe1d3bb8a |
Definition: In this task, you will be presented with a context from an academic paper and you have to write an answerable question based on the context. Your questions can be extractive, abstractive, or yes-no questions.
Positive Example 1 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: how was the dataset built?
Positive Example 2 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language are the tweets?
Negative Example 1 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language is tweets?
Negative Example 2 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: What is the size of the dataset?
Now complete the following example -
Input: The memory mechanism is adopted in order to enable the model to look beyond localized features and have access to the entire sequence.
Output:
| [
"Which features do they use?"
] | task461-ecb9b05b73a34ef79df2b627fce00edd |
Definition: In this task, you will be presented with a context from an academic paper and you have to write an answerable question based on the context. Your questions can be extractive, abstractive, or yes-no questions.
Positive Example 1 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: how was the dataset built?
Positive Example 2 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language are the tweets?
Negative Example 1 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language is tweets?
Negative Example 2 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: What is the size of the dataset?
Now complete the following example -
Input: The observed performance of both the BasicDCGAN and MultitaskDCGAN using 3-classes is comparable to the state-of-the-art, with 49.80% compared to 49.99% reported in BIBREF16
Output:
| [
"What model achieves state of the art performance on this task?"
] | task461-7b0cd21882f144e28019e128949b6cd2 |
Definition: In this task, you will be presented with a context from an academic paper and you have to write an answerable question based on the context. Your questions can be extractive, abstractive, or yes-no questions.
Positive Example 1 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: how was the dataset built?
Positive Example 2 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language are the tweets?
Negative Example 1 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language is tweets?
Negative Example 2 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: What is the size of the dataset?
Now complete the following example -
Input: We focus primarily on the smaller data set of 645 hand-labeled articles provided to task participants, both for training and for validation. We pre-trained BERT-base on the 600,000 articles without labels by using the same Cloze task BIBREF5 that BERT had originally used for pre-training.
Output:
| [
"How long is the dataset?"
] | task461-444505679a80499795205c33e707239f |
Definition: In this task, you will be presented with a context from an academic paper and you have to write an answerable question based on the context. Your questions can be extractive, abstractive, or yes-no questions.
Positive Example 1 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: how was the dataset built?
Positive Example 2 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language are the tweets?
Negative Example 1 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language is tweets?
Negative Example 2 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: What is the size of the dataset?
Now complete the following example -
Input: We compare Blse (Sections UID23 – UID30 ) to VecMap, Muse, and Barista (Section "Previous Work" ) as baselines, which have similar data requirements and to machine translation (MT) and monolingual (Mono) upper bounds which request more resources.
Output:
| [
"what baseline do they compare to?"
] | task461-53bad1b04cef4f4c88fed715d4055e0d |
Definition: In this task, you will be presented with a context from an academic paper and you have to write an answerable question based on the context. Your questions can be extractive, abstractive, or yes-no questions.
Positive Example 1 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: how was the dataset built?
Positive Example 2 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language are the tweets?
Negative Example 1 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language is tweets?
Negative Example 2 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: What is the size of the dataset?
Now complete the following example -
Input: We propose extended middle context, a new context representation for CNNs for relation classification. The contexts are split into three disjoint regions based on the two relation arguments: the left context, the middle context and the right context. Hence, we propose to use two contexts: (1) a combination of the left context, the left entity and the middle context; and (2) a combination of the middle context, the right entity and the right context. The two contexts are processed by two independent convolutional and max-pooling layers. After pooling, the results are concatenated to form the sentence representation.
Output:
| [
"How do they obtain the new context represetation?"
] | task461-ccb24ad4737643b898718fd47916586f |
Definition: In this task, you will be presented with a context from an academic paper and you have to write an answerable question based on the context. Your questions can be extractive, abstractive, or yes-no questions.
Positive Example 1 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: how was the dataset built?
Positive Example 2 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language are the tweets?
Negative Example 1 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language is tweets?
Negative Example 2 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: What is the size of the dataset?
Now complete the following example -
Input: We use the pre-trained uncased BERT$_\mathrm {BASE}$ model for fine-tuning, because we find that BERT$_\mathrm {LARGE}$ model performs slightly worse than BERT$_\mathrm {BASE}$ in this task.
Output:
| [
"Do they use large or small BERT?"
] | task461-bbe93b3f9ccd459f8e8cb548ae84690e |
Definition: In this task, you will be presented with a context from an academic paper and you have to write an answerable question based on the context. Your questions can be extractive, abstractive, or yes-no questions.
Positive Example 1 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: how was the dataset built?
Positive Example 2 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language are the tweets?
Negative Example 1 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language is tweets?
Negative Example 2 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: What is the size of the dataset?
Now complete the following example -
Input: he immediate impact of the explicit constraint is avoiding the collapse issue ($D_{KL}=0$) by setting a non-zero positive constraint ($C\ge 0$) on the KL term ($|D_{KL}\big (q_\phi ({z}|{x}) || p({z})\big )-C|$).
Output:
| [
"Why does proposed term help to avoid posterior collapse?"
] | task461-855772c4106d4f0f8d2b3c8bf4152e9a |
Definition: In this task, you will be presented with a context from an academic paper and you have to write an answerable question based on the context. Your questions can be extractive, abstractive, or yes-no questions.
Positive Example 1 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: how was the dataset built?
Positive Example 2 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language are the tweets?
Negative Example 1 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language is tweets?
Negative Example 2 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: What is the size of the dataset?
Now complete the following example -
Input: To further improve the performance of our models, we introduce in-house labeled data that we use to fine-tune BERT. For the gender classification task, we manually label an in-house dataset of 1,100 users with gender tags, including 550 female users, 550 male users. We obtain 162,829 tweets by crawling the 1,100 users' timelines. For the dialect identification task, we randomly sample 20,000 tweets for each class from an in-house dataset gold labeled with the same 15 classes as the shared task.
Output:
| [
"What are the in-house data employed?"
] | task461-a1f71c5b29f041debcbe945687fe042d |
Definition: In this task, you will be presented with a context from an academic paper and you have to write an answerable question based on the context. Your questions can be extractive, abstractive, or yes-no questions.
Positive Example 1 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: how was the dataset built?
Positive Example 2 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language are the tweets?
Negative Example 1 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language is tweets?
Negative Example 2 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: What is the size of the dataset?
Now complete the following example -
Input: This step was followed by a pre-processing stage where the texts were normalized by replacing zero-width-non-joiner (ZWNJ) BIBREF2 and manually verifying the orthography based on the reference orthography of the Kurdistan Region of Iraq.
Output:
| [
"How is the corpus normalized?"
] | task461-060211e6421942ccad5e61d7eeacb7ca |
Definition: In this task, you will be presented with a context from an academic paper and you have to write an answerable question based on the context. Your questions can be extractive, abstractive, or yes-no questions.
Positive Example 1 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: how was the dataset built?
Positive Example 2 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language are the tweets?
Negative Example 1 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language is tweets?
Negative Example 2 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: What is the size of the dataset?
Now complete the following example -
Input: Spelling correction tests described in literature have tended to focus on one approach applied to a specific corpus. Limited examples include works on spellchecking mammography reports and tweets BIBREF7 , BIBREF4 . These works emphasized the importance of tailoring correction systems to specific problems of corpora they are applied to. For example, mammography reports suffer from poor typing, which in this case is a repetitive work done in relative hurry. Tweets, on the other hand, tend to contain emoticons and neologisms that can trick solutions based on rules and dictionaries, such as LanguageTool. The latter is, by itself, fairly well suited for Polish texts, since a number of extensions to the structure of this application was inspired by problems with morphology of Polish language BIBREF3 .
Output:
| [
"Which specific error correction solutions have been proposed for specialized corpora in the past?"
] | task461-dcd829bcc77c4d58800106f83e49ee1b |
Definition: In this task, you will be presented with a context from an academic paper and you have to write an answerable question based on the context. Your questions can be extractive, abstractive, or yes-no questions.
Positive Example 1 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: how was the dataset built?
Positive Example 2 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language are the tweets?
Negative Example 1 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language is tweets?
Negative Example 2 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: What is the size of the dataset?
Now complete the following example -
Input: 300 test queries are randomly selected out, and annotators are asked to independently score the results of these queries with different points in terms of their quality: (1) Good (3 points): The response is grammatical, semantically relevant to the query, and more importantly informative and interesting; (2) Acceptable (2 points): The response is grammatical, semantically relevant to the query, but too trivial or generic (e.g.,“我不知道(I don't know)", “我也是(Me too)”, “我喜欢(I like it)" etc.); (3) Failed (1 point): The response has grammar mistakes or irrelevant to the query.
Output:
| [
"How is human evaluation performed, what were the criteria?"
] | task461-6cda6019eb724846a897d5f9f772d51b |
Definition: In this task, you will be presented with a context from an academic paper and you have to write an answerable question based on the context. Your questions can be extractive, abstractive, or yes-no questions.
Positive Example 1 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: how was the dataset built?
Positive Example 2 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language are the tweets?
Negative Example 1 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language is tweets?
Negative Example 2 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: What is the size of the dataset?
Now complete the following example -
Input: A representation that is more in line with observed user behavior is a concept map BIBREF5 , a labeled graph showing concepts as nodes and relationships between them as edges (Figure FIGREF2 ).
Output:
| [
"How do the authors define a concept map?"
] | task461-eb0b509c771b4217869a644c5876b241 |
Definition: In this task, you will be presented with a context from an academic paper and you have to write an answerable question based on the context. Your questions can be extractive, abstractive, or yes-no questions.
Positive Example 1 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: how was the dataset built?
Positive Example 2 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language are the tweets?
Negative Example 1 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language is tweets?
Negative Example 2 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: What is the size of the dataset?
Now complete the following example -
Input: The gated mechanism learn the domain agnostic representations. They together control the information that has to flow through further fully connected output layer after max pooling. The effectiveness of gated architectures rely on the idea of training a gate with sole purpose of identifying a weightage. In the task of sentiment analysis this weightage corresponds to what weights will lead to a decrement in final loss or in other words, most accurate prediction of sentiment. In doing so, the gate architecture learns which words or n-grams contribute to the sentiment the most, these words or n-grams often co-relate with domain independent words. On the other hand the gate gives less weightage to n-grams which are largely either specific to domain or function word chunks which contribute negligible to the overall sentiment. This is what makes gated architectures effective at Domain Adaptation. We see that gated architectures almost always outperform recurrent, attention and linear models BoW, TFIDF, PV. This is largely because while training and testing on same domains, these models especially recurrent and attention based may perform better. However, for Domain Adaptation, as they lack gated structure which is trained in parallel to learn importance, their performance on target domain is poor as compared to gated architectures. As gated architectures are based on convolutions, they exploit parallelization to give significant boost in time complexity as compared to other models.
Output:
| [
"Are there conceptual benefits to using GCNs over more complex architectures like attention?"
] | task461-a57cda728b9549018734840dd3643cbc |
Definition: In this task, you will be presented with a context from an academic paper and you have to write an answerable question based on the context. Your questions can be extractive, abstractive, or yes-no questions.
Positive Example 1 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: how was the dataset built?
Positive Example 2 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language are the tweets?
Negative Example 1 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language is tweets?
Negative Example 2 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: What is the size of the dataset?
Now complete the following example -
Input: To ensure the universality and general applicability of the curriculum, we perform an in-depth investigation on three publicly available conversation corpora, PersonaChat BIBREF12, DailyDialog BIBREF13 and OpenSubtitles BIBREF7, consisting of 140 248, 66 594 and 358 668 real-life conversation samples, respectively.
Output:
| [
"What three publicly available coropora are used?"
] | task461-e02c38c4165849318cc720617458be13 |
Definition: In this task, you will be presented with a context from an academic paper and you have to write an answerable question based on the context. Your questions can be extractive, abstractive, or yes-no questions.
Positive Example 1 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: how was the dataset built?
Positive Example 2 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language are the tweets?
Negative Example 1 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language is tweets?
Negative Example 2 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: What is the size of the dataset?
Now complete the following example -
Input: We use datasets from the NIST DUC-05, DUC-06 and DUC-07 shared tasks BIBREF7, BIBREF19, BIBREF20. Given a question and a cluster of newswire documents, the contestants were asked to generate a 250-word summary answering the question. DUC-05 contains 1,600 summaries (50 questions x 32 systems); in DUC-06, 1,750 summaries are included (50 questions x 35 systems); and DUC-07 has 1,440 summaries (45 questions x 32 systems).
Output:
| [
"What dataset do they use?"
] | task461-37e1572baef64146bb6a7625d5ec22d8 |
Definition: In this task, you will be presented with a context from an academic paper and you have to write an answerable question based on the context. Your questions can be extractive, abstractive, or yes-no questions.
Positive Example 1 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: how was the dataset built?
Positive Example 2 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language are the tweets?
Negative Example 1 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language is tweets?
Negative Example 2 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: What is the size of the dataset?
Now complete the following example -
Input: While BERT-QC achieves large gains over existing methods on the ARC dataset, here we demonstrate that BERT-QC also matches state-of-the-art performance on TREC BIBREF6 , while surpassing state-of-the-art performance on the GARD corpus of consumer health questions BIBREF3 and MLBioMedLAT corpus of biomedical questions BIBREF4 .
Output:
| [
"Which datasets are used for evaluation?"
] | task461-b722230b316143c88abf55874fb1b24a |
Definition: In this task, you will be presented with a context from an academic paper and you have to write an answerable question based on the context. Your questions can be extractive, abstractive, or yes-no questions.
Positive Example 1 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: how was the dataset built?
Positive Example 2 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language are the tweets?
Negative Example 1 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language is tweets?
Negative Example 2 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: What is the size of the dataset?
Now complete the following example -
Input: To simulate the scenario, we split the Microsoft COCO dataset into food and non-food domain datasets. the food dataset has 3,806 images for training and 1,775 for validation. The non-food dataset has 78,976 images for training and 38,749 for validation. Adaptation to food domain captioning
Output:
| [
"How many examples are there in the source domain?"
] | task461-18853558fd1b48299b649631eafdc28f |
Definition: In this task, you will be presented with a context from an academic paper and you have to write an answerable question based on the context. Your questions can be extractive, abstractive, or yes-no questions.
Positive Example 1 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: how was the dataset built?
Positive Example 2 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language are the tweets?
Negative Example 1 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language is tweets?
Negative Example 2 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: What is the size of the dataset?
Now complete the following example -
Input: Spoken-SQuAD is chosen as the target domain data for training and testing. Spoken-SQuAD BIBREF5 is an automatically generated corpus in which the document is in spoken form and the question is in text form. The reference transcriptions are from SQuAD BIBREF1 . There are 37,111 and 5,351 question answer pairs in the training and testing sets respectively, and the word error rate (WER) of both sets is around 22.7%.
The original SQuAD, Text-SQuAD, is chosen as the source domain data, where only question answering pairs appearing in Spoken-SQuAD are utilized. In our task setting, during training we train the proposed QA model on both Text-SQuAD and Spoken-SQuAD training sets. While in the testing stage, we evaluate the performance on Spoken-SQuAD testing set.
Output:
| [
"Which datasets did they use for evaluation?"
] | task461-efcbcb4db5a64c73ab003d2a7fc0c3a1 |
Definition: In this task, you will be presented with a context from an academic paper and you have to write an answerable question based on the context. Your questions can be extractive, abstractive, or yes-no questions.
Positive Example 1 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: how was the dataset built?
Positive Example 2 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language are the tweets?
Negative Example 1 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language is tweets?
Negative Example 2 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: What is the size of the dataset?
Now complete the following example -
Input: The proposed system consists of a Bi-directional Long Short-Term Memory (BiLSTM) BIBREF16, a two-level attention mechanism BIBREF29, BIBREF30 and a shared representation for emotion and sentiment analysis tasks. The BiLSTM encodes the word representation of each word. This representation is shared between the subsystems of sentiment and emotion analysis. Each of the shared representations is then fed to the primary attention mechanism of both the subsystems. The primary attention mechanism finds the best representation for each word for each task. The secondary attention mechanism acts on top of the primary attention to extract the best sentence representation by focusing on the suitable context for each task. Finally, the representations of both the tasks are fed to two different feed-forward neural networks to produce two outputs - one for sentiment analysis and one for emotion analysis. Each component is explained in the subsequent subsections.
Output:
| [
"How is multi-tasking performed?"
] | task461-5998396a8add4650a76a36a615ecce73 |
Definition: In this task, you will be presented with a context from an academic paper and you have to write an answerable question based on the context. Your questions can be extractive, abstractive, or yes-no questions.
Positive Example 1 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: how was the dataset built?
Positive Example 2 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language are the tweets?
Negative Example 1 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language is tweets?
Negative Example 2 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: What is the size of the dataset?
Now complete the following example -
Input: We conduct our annotation study on Amazon Mechanical Turk, presenting Turkers with Human Intelligence Tasks (henceforth, HITs) consisting of a single conversation between a customer and an agent. In each HIT, we present Turkers with a definition of each dialogue act, as well as a sample annotated dialogue for reference. For each turn in the conversation, we allow Turkers to select as many labels from our taxonomy as required to fully characterize the intent of the turn. Additionally, annotators are asked three questions at the end of each conversation HIT, to which they could respond that they agreed, disagreed, or could not tell:
Output:
| [
"How are customer satisfaction, customer frustration and overall problem resolution data collected?"
] | task461-a68e1b2e959547d4a6512b0fe2c29bed |
Definition: In this task, you will be presented with a context from an academic paper and you have to write an answerable question based on the context. Your questions can be extractive, abstractive, or yes-no questions.
Positive Example 1 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: how was the dataset built?
Positive Example 2 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language are the tweets?
Negative Example 1 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language is tweets?
Negative Example 2 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: What is the size of the dataset?
Now complete the following example -
Input: Last but not least, ethics and fairness are important considerations, that deserve to be studied. In that sense, detection of individual and global bias should be prioritized in order to give useful feedbacks to practitioners. Furthermore we are considering using adversarial learning as in BIBREF33 in order to ensure fairness during the training process.
Output:
| [
"Is there any ethical consideration in the research?",
"Do they analyze if their system has any bias?"
] | task461-fe94d260f0be489693bf6d993b44cf97 |
Definition: In this task, you will be presented with a context from an academic paper and you have to write an answerable question based on the context. Your questions can be extractive, abstractive, or yes-no questions.
Positive Example 1 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: how was the dataset built?
Positive Example 2 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language are the tweets?
Negative Example 1 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language is tweets?
Negative Example 2 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: What is the size of the dataset?
Now complete the following example -
Input: To study how the multimodal context can boost the performance compared to an unimodal context we evaluate different models: a Feature Concatenation Model (FCM), a Spatial Concatenation Model (SCM) and a Textual Kernels Model (TKM).
Output:
| [
"What different models for multimodal detection were proposed?"
] | task461-9d68f12590e6415fbf2b75bad271995f |
Definition: In this task, you will be presented with a context from an academic paper and you have to write an answerable question based on the context. Your questions can be extractive, abstractive, or yes-no questions.
Positive Example 1 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: how was the dataset built?
Positive Example 2 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language are the tweets?
Negative Example 1 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language is tweets?
Negative Example 2 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: What is the size of the dataset?
Now complete the following example -
Input: As detailed before, we adapted the cluster-linking dataset from rupnik2016news to evaluate our online crosslingual clustering approach.
Output:
| [
"What are the sources of the datasets?"
] | task461-c39cee4d84ec48da91306dcc6dd3cdab |
Definition: In this task, you will be presented with a context from an academic paper and you have to write an answerable question based on the context. Your questions can be extractive, abstractive, or yes-no questions.
Positive Example 1 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: how was the dataset built?
Positive Example 2 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language are the tweets?
Negative Example 1 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language is tweets?
Negative Example 2 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: What is the size of the dataset?
Now complete the following example -
Input: As shown in Table TABREF12, the T-T model significantly outperforms the LSTM-based RNN-T baseline.
Output:
| [
"What was previous state of the art model?"
] | task461-6acaffd9ddd943a7a3338f9c7cfb5230 |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.