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: We evaluate our model on two benchmark treebanks, English Penn Treebank (PTB) and Chinese Penn Treebank (CTB5.1) following standard data splitting BIBREF30, BIBREF31. POS tags are predicted by the Stanford Tagger BIBREF32. For constituent parsing, we use the standard evalb tool to evaluate the F1 score. For dependency parsing, we apply Stanford basic dependencies (SD) representation BIBREF4 converted by the Stanford parser. Following previous work BIBREF27, BIBREF33, we report the results without punctuations for both treebanks. Tables TABREF17, TABREF18 and TABREF19 compare our model to existing state-of-the-art, in which indicator Separate with our model shows the results of our model learning constituent or dependency parsing separately, (Sum) and (Concat) respectively represent the results with the indicated input token representation setting. On PTB, our model achieves 93.90 F1 score of constituent parsing and 95.91 UAS and 93.86 LAS of dependency parsing. On CTB, our model achieves a new state-of-the-art result on both constituent and dependency parsing. At last, our model is evaluated on two benchmark treebanks for both constituent and dependency parsing. The empirical results show that our parser reaches new state-of-the-art for all parsing tasks.
Output:
| [
"How is dependency parsing empirically verified?"
] | task461-63f0ae34704e4a97872cd4c67980c8a2 |
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 paper, we propose an improved RNN-T model with language bias to alleviate the problem. The model is trained to predict language IDs as well as the subwords. To ensure the model can learn CS information, we add language IDs in the CS point of transcription, as illustrated in Fig. 1.
Output:
| [
"How do they obtain language identities?"
] | task461-01eb7b075bd64078be082fcca4b3024b |
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 leveraged an existing, annotated Twitter dataset that was constructed based on a hierarchical model of depression-related symptoms BIBREF12 , BIBREF13 . The dataset contains 9,473 annotations for 9,300 tweets.
Output:
| [
"What dataset is used for this study?"
] | task461-9fccabb754764dd0929ca9465f6d45c6 |
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 paper, we study verifiable robustness, i.e., providing a certificate that for a given network and test input, no attack or perturbation under the specification can change predictions, using the example of text classification tasks, Stanford Sentiment Treebank (SST) BIBREF15 and AG News BIBREF16.
Output:
| [
"Which dataset do they use?"
] | task461-309d5e5e7d4e452cb04c52c7e21c2a7e |
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 our HR-VAE model with three strong baselines using VAE for text modelling:
VAE-LSTM-base: A variational autoencoder model which uses LSTM for both encoder and decoder. KL annealing is used to tackled the latent variable collapse issue BIBREF0;
VAE-CNN: A variational autoencoder model with a LSTM encoder and a dilated CNN decoder BIBREF7;
vMF-VAE: A variational autoencoder model using LSTM for both encoder and decoder where the prior distribution is the von Mises-Fisher (vMF) distribution rather than a Gaussian distribution BIBREF5.
Output:
| [
"Do they compare against state of the art text generation?"
] | task461-46015377c26f443a8c0b442f78c06d36 |
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 used a dataset provided by Shortir, an Indonesian news aggregator and summarizer company. The dataset contains roughly 20K news articles. Each article has the title, category, source (e.g., CNN Indonesia, Kumparan), URL to the original article, and an abstractive summary which was created manually by a total of 2 native speakers of Indonesian
Output:
| [
"Did they use a crowdsourcing platform for the summaries?"
] | task461-911ae58d1b194f5d8114016c7bd583bc |
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 context, we propose a robust multilingual sentiment analysis method, tested in eight different languages: Spanish, English, Italian, Arabic, German, Portuguese, Russian and Swedish.
Output:
| [
"What eight language are reported on?"
] | task461-50fabb8fe0104d5eb6afe140ebf0dfae |
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 experiments that use parallel data to initialize foreign specific parameters, we use the same datasets in the work of BIBREF6. Specifically, we use United Nations Parallel Corpus BIBREF18 for en-ru, en-ar, en-zh, and en-fr. We collect en-hi parallel data from IIT Bombay corpus BIBREF19 and en-vi data from OpenSubtitles 2018.
Output:
| [
"What datasets are used for evaluation?"
] | task461-855b4d8e034e453d88065e07f4977def |
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 the GLUE tasks, these state-of-the-art systems make their greatest gains on the acceptability task with the Corpus of Linguistic Acceptability BIBREF0 . CoLA contains example sentences from linguistics publications labeled by experts for grammatical acceptability, and written to show subtle grammatical features. Because minimal syntactic differences can separate acceptable sentences from unacceptable ones (What did Bo write a book about? / *What was a book about written by Bo?), and acceptability classifiers are more reliable when trained on GPT and BERT than on recurrent models, it stands to reason that GPT and BERT have better implicit knowledge of syntactic features relevant to acceptability.
Output:
| [
"How is the CoLA grammatically annotated?"
] | task461-17649000a6f94c31b83a699fb4f5dd69 |
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, to be able to make use of multiple answer styles within a single system, our model introduces an artificial token corresponding to the target style at the beginning of the answer sentence ( $y_1$ ), like BIBREF14 . At test time, the user can specify the first token to control the answer styles.
Output:
| [
"Does their model also take the expected answer style as input?"
] | task461-058ef31a01dd4d42a35cce573d631eed |
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: Trinomials are likely to appear in exactly one order, and when they appear in more than one order the last word is almost always the same across all instances.
Output:
| [
"Are there any new finding in analasys of trinomials that was not present binomials?"
] | task461-c939d3f7559045b39de24694ee457941 |
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 first experiment, we compare the quality of fastText embeddings trained on (high-quality) curated data and (low-quality) massively extracted data for Twi and Yorùbá languages. The huge ambiguity in the written Twi language motivates the exploration of different approaches to word embedding estimations. In this work, we compare the standard fastText methodology to include sub-word information with the character-enhanced approach with position-based clustered embeddings (CWE-LP as introduced in Section SECREF17).
Output:
| [
"What two architectures are used?"
] | task461-aa011e11da70424da518fcaac68d1d64 |
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 comparison, we also report the performance of the error detection system by Rei2016, trained using the same FCE dataset.
Output:
| [
"What was the baseline used?"
] | task461-e348c2263b2143128c760a8ac25ffa18 |
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 the moment defender can draw on methods from image area to text for improving the robustness of DNNs, e.g. adversarial training BIBREF107 , adding extra layer BIBREF113 , optimizing cross-entropy function BIBREF114 , BIBREF115 or weakening the transferability of adversarial examples.
Output:
| [
"Which strategies show the most promise in deterring these attacks?"
] | task461-b92c6a3eb91d41d6b7da23ba7eaa2507 |
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 hypothesized that question answering can benefit from synergistic interaction between the two tasks through parameter sharing and joint training under this multitask setting.
Output:
| [
"Which components of QA and QG models are shared during training?"
] | task461-873fa212ecb542ba8209f30e28dfba12 |
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: Since our methodology does not use a seed list of offensive words, it is not biased by topic, target, or dialect. Using our methodology, we tagged 10,000 Arabic tweet dataset for offensiveness, where offensive tweets account for roughly 19% of the tweets. Further, we labeled tweets as vulgar or hate speech. To date, this is the largest available dataset, which we plan to make publicly available along with annotation guidelines. We use this dataset to characterize Arabic offensive language to ascertain the topics, dialects, and users' gender that are most associated with the use of offensive language.
Output:
| [
"In what way is the offensive dataset not biased by topic, dialect or target?"
] | task461-1ca7224246214b16b5fe912c01150985 |
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 bossa-nova and jovem-guarda genres, which have few instances in the dataset, are among the most difficult ones to classify using the model.
Output:
| [
"what genre was the most difficult to classify?"
] | task461-6e802776319c4317b7fd1c6a888af356 |
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 1 shows a simple linear model with rank constraint.
Output:
| [
"What are their baseline methods?"
] | task461-f95dff54b2fa42fba0333b1f6cf0035b |
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 model yields the best results on both UAS and LAS metrics of all languages except the Japanese. As for Japanese, our model gives unsatisfactory results because the original treebank was written in Roman phonetic characters instead of hiragana, which is used by both common Japanese writing and our pre-trained embeddings. Despite this, our model overall still gives 1.0% higher average UAS and LAS than the previous best parser, BIAF. Although both BIAF and STACKPTR parsers have achieved relatively high parsing accuracies on the 12 languages and have all UAS higher than 90%, our model achieves state-of-the-art results in all languages for both UAS and LAS. Overall, our model reports more than 1.0% higher average UAS than STACKPTR and 0.3% higher than BIAF.
Output:
| [
"What are performance compared to former models?"
] | task461-c5aad0478c7a46e2a055f975e59a7c6c |
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 the full text of a scientific publication, we want to rank its citations according to the author's judgments. We collected recent publications from the open-access PLoS journals and asked the authors to rank by closeness five citations we selected from their paper.
Output:
| [
"what crowdsourcing platform is used?"
] | task461-0ab7d66f64fe4f9f9901dff7c17a877b |
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 TABREF19 displays the performance of the 4 baselines on the ReviewQA's test set. These results are the performance achieved by our own implementation of these 4 models.
Output:
| [
"What tasks were evaluated?"
] | task461-9c57f3c25dfc4d8ca96837e642974244 |
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 baseline for the RNN models, we apply a uni-directional RNN which predicts the relation after processing the whole sentence.
Output:
| [
"Which variant of the recurrent neural network do they use?"
] | task461-d83412e85593452f84bcacf603c770a4 |
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 behavior model was implemented using an RNN with LSTM units and trained with the Couples Therapy Corpus. Out of the 33 behavioral codes included in the corpus we applied the behaviors Acceptance, Blame, Negativity, Positivity, and Sadness to train our models. This is motivated from previous works which showed good separability in these behaviors as well as being easy to interpret. The behavior model is pre-trained to identify the presence of each behavior from a sequence of words using a multi-label classification scheme. The pre-trained portion of the behavior model was implemented using a single layer RNN with LSTM units with dimension size 50.
Output:
| [
"How is module that analyzes behavioral state trained?"
] | task461-e97fdabbb697451799ed0d6d552dd122 |
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 Wikipedia revision dumps that were previously introduced by Leskovec et al. leskovec2010governance contain eight GB (compressed size) revision edits with meta data.
Output:
| [
"How large is the Wikipedia revision dump dataset?"
] | task461-207f561fe7224fa28906704b64f4c826 |
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 result, transfer training with only 1000 hours data can match equivalent performance for full training with 7300 hours data.
Output:
| [
"how small of a dataset did they train on?"
] | task461-51683d9948404fa8945634b0dd769aa0 |
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 paper, we analyze the task of automatically correcting run-on sentences. We develop two methods: a conditional random field model (roCRF) and a Seq2Seq attention model (roS2S) and show that they outperform models from the sister tasks of punctuation restoration and whole-sentence grammatical error correction.
Output:
| [
"Which machine learning models do they use to correct run-on sentences?"
] | task461-7c8de99f11b449d7b1d9243c39324ad6 |
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 section, we empirically compare automatic differentiation (AD, our implementation based on Clad) and numerical differentiation (ND, based on finite difference method) in ROOT. We show that AD can drastically improve accuracy and performance of derivative evaluation, compared to ND.
Output:
| [
"How is correctness of automatic derivation proved?"
] | task461-335682df8e12483aa08248a95f9b2da4 |
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: Topology only embeddings: MMB BIBREF45 , DeepWalk BIBREF1 , LINE BIBREF33 , Node2vec BIBREF46 . ( INLINEFORM1 ) Joint embedding of topology & text: Naive combination, TADW BIBREF5 , CENE BIBREF6 , CANE BIBREF9 , WANE BIBREF10 , DMTE BIBREF34 .
Output:
| [
"Which other embeddings do they compare against?"
] | task461-3fadfe499cc34325bfea2bae343d7ec5 |
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 seed lexicon consists of positive and negative predicates. If the predicate of an extracted event is in the seed lexicon and does not involve complex phenomena like negation, we assign the corresponding polarity score ($+1$ for positive events and $-1$ for negative events) to the event. It is a
Output:
| [
"What is the seed lexicon?"
] | task461-cedb2fc1fa0d4016b968163490073880 |
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 Garimella et al. BIBREF23 have made their code public , we reproduced their best method Randomwalk on our datasets and measured the AUC ROC, obtaining a score of 0.935. An interesting finding was that their method had a poor performance over their own datasets. This was due to the fact (already explained in Section SECREF4) that it was not possible to retrieve the complete discussions, moreover, in no case could we restore more than 50% of the tweets. So we decided to remove these discussions and measure again the AUC ROC of this method, obtaining a 0.99 value. Our hypothesis is that the performance of that method was seriously hurt by the incompleteness of the data. We also tested our method on these datasets, obtaining a 0.99 AUC ROC with Walktrap and 0.989 with Louvain clustering.
Output:
| [
"What are the state of the art measures?"
] | task461-53cc0f7c4756446094d1c1ebe9a961fc |
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: Following the previous works, we report the precision ($P.$), recall ($R.$) and $F_1$ scores for target recognition and targeted sentiment.
Output:
| [
"How is the effectiveness of the model evaluated?"
] | task461-8c9c48aab22c4fdbaf0b7dc94141d6d2 |
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: Experiments ::: Evaluation Metrics ::: Setup of Automatic Evaluation ::: Language Fluency
We fine-tuned the GPT-2 medium model BIBREF51 on our collected headlines and then used it to measure the perplexity (PPL) on the generated outputs.
Output:
| [
"How is fluency automatically evaluated?"
] | task461-e7405d2a1e6642178f5b848ce7f69f03 |
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 addition to the majority baseline, we also compare our results with a lexicon-based approach. For experimental results, we report majority baseline for each language where the majority baseline corresponds to a model's accuracy if it always predicts the majority class in the dataset.
Output:
| [
"what are the baselines?"
] | task461-d2cfedd25a294e7c9bfb7391557835e0 |
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 used the Levenshtein distance metric BIBREF8 implemented in Apache Lucene library BIBREF9 . Another simple approach is the aforementioned diacritical swapping, which is a term that we introduce here for referring to a solution inspired by the work of BIBREF4 . A promising method, adapted from work on correcting texts by English language learners BIBREF11 , expands on the concept of selecting a correction nearest to the spelling error according to some notion of distance. Here, the Levenshtein distance is used in a weighted sum to cosine distance between word vectors. Our ELMo-augmented LSTM is bidirectional.
Output:
| [
"What methods are tested in PIEWi?"
] | task461-a5679fe60cee4e3e93435acf5081f183 |
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: Results and Analysis
Output:
| [
"what quantitative analysis is done?"
] | task461-ac797b9129c44e09a45de2b1c821831a |
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: Both beat the non-attention baseline by a significant margin. For the attention baseline, we use the standard parametrized attention BIBREF2 .
Output:
| [
"Which baseline methods are used?"
] | task461-68ff4b3babfc4969965dbff2d6378273 |
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, this work also handles the cases of singular/plural, subject pronoun/object pronoun, etc. For instance, the pronoun “he" is used for the subject as “he" but is used for the object as “him".
Output:
| [
"What else is tried to be solved other than 12 tenses, model verbs and negative form?"
] | task461-dbe806cf42704113b7c074dbb9afb182 |
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 performed the annotation with freely available tools for the Portuguese language.
Output:
| [
"Are the annotations automatic or manually created?"
] | task461-edc15fefb01d425db825eec3971c3428 |
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: his reduces significantly the needed training time: SBERT can be tuned in less than 20 minutes, while yielding better results than comparable sentence embedding methods.
Output:
| [
"How much time takes its training?"
] | task461-8594437797c9447597df80bd3ec30923 |
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 do not restrict ourselves to a test set of sequences of fixed lengths during testing. Rather, we exhaustively enumerate all the sequences in a language by their lengths and then go through the sequences in the test set one by one until our network errs $k$ times, thereby providing a more fine-grained evaluation criterion of its generalization capabilities. To study the effect of various length distributions on the learning capability and speed of LSTM models, we experimented with four discrete probability distributions supported on bounded intervals (Figure 2 ) to sample the lengths of sequences for the languages.
Output:
| [
"Are the unobserved samples from the same distribution as the training data?"
] | task461-bb1b988496bd4b7aa789c36a75ee4aed |
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 paper, we propose the first large-scale dataset for QA over social media data. Table TABREF3 gives an example from our TweetQA dataset. The dataset now includes 10,898 articles, 17,794 tweets, and 13,757 crowdsourced question-answer pairs
Output:
| [
"What is the size of this dataset?"
] | task461-29f78b72d73941d4afe54badfe254899 |
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 focus of this section is on recently published datasets and LID research applicable to the South African context. An in depth survey of algorithms, features, datasets, shared tasks and evaluation methods may be found in BIBREF0.
The datasets for the DSL 2015 & DSL 2017 shared tasks BIBREF1 are often used in LID benchmarks and also available on Kaggle . The recently published JW300 parallel corpus BIBREF2 covers over 300 languages with around 100 thousand parallel sentences per language pair on average. The WiLI-2018 benchmark dataset BIBREF4 for monolingual written natural language identification includes around 1000 paragraphs of 235 languages. The NCHLT text corpora BIBREF7 is likely a good starting point for a shared LID task dataset for the South African languages BIBREF8.
Output:
| [
"Which datasets are employed for South African languages LID?"
] | task461-d4e79087e392459f89dc39a307d546a4 |
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 plotted the distribution of harassment incidents in each categorization dimension (Figure FIGREF19). It displays statistics that provide important evidence as to the scale of harassment and that can serve as the basis for more effective interventions to be developed by authorities ranging from advocacy organizations to policy makers. It provides evidence to support some commonly assumed factors about harassment: First, we demonstrate that harassment occurred more frequently during the night time than the day time. Second, it shows that besides unspecified strangers (not shown in the figure), conductors and drivers are top the list of identified types of harassers, followed by friends and relatives. Furthermore, we uncovered that there exist strong correlations between the age of perpetrators and the location of harassment, between the single/multiple harasser(s) and location, and between age and single/multiple harasser(s) (Figure FIGREF20). We also found that the majority of young perpetrators engaged in harassment behaviors on the streets. These findings suggest that interventions with young men and boys, who are readily influenced by peers, might be most effective when education is done peer-to-peer. It also points to the locations where such efforts could be made, including both in schools and on the streets. In contrast, we found that adult perpetrators of sexual harassment are more likely to act alone. Most of the adult harassers engaged in harassment on public transportation. These differences in adult harassment activities and locations, mean that interventions should be responsive to these factors. For example, increasing the security measures on transit at key times and locations. In addition, we also found that the correlations between the forms of harassment with the age, single/multiple harasser, type of harasser, and location (Figure FIGREF21). For example, young harassers are more likely to engage in behaviors of verbal harassment, rather than physical harassment as compared to adults. It was a single perpetrator that engaged in touching or groping more often, rather than groups of perpetrators. In contrast, commenting happened more frequently when harassers were in groups. Last but not least, public transportation is where people got indecently touched most frequently both by fellow passengers and by conductors and drivers. The nature and location of the harassment are particularly significant in developing strategies for those who are harassed or who witness the harassment to respond and manage the everyday threat of harassment. For example, some strategies will work best on public transport, a particular closed, shared space setting, while other strategies might be more effective on the open space of the street.
Output:
| [
"What patterns were discovered from the stories?"
] | task461-3fef45c5bc5844bb9ed2cd5833d9cdb2 |
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: pretrained word embeddings (WE): For the PDT experiments, we generate the word embeddings with word2vec on a concatenation of large raw Czech corpora available from the LINDAT/CLARIN repository. For UD Czech, we use FastText word embeddings BIBREF27 of dimension 300, which we pretrain on Czech Wikipedia using segmentation and tokenization trained from the UD data.
BERT BIBREF1: Pretrained contextual word embeddings of dimension 768 from the Base model. We average the last four layers of the BERT model to produce the embeddings. Because BERT utilizes word pieces, we decompose UD words into appropriate subwords and then average the generated embeddings over subwords belonging to the same word.
Flair BIBREF2: Pretrained contextual word embeddings of dimension 4096.
Output:
| [
"What data is used to build the embeddings?"
] | task461-743988ba4da64857b72df51301482160 |
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: One of the solutions that has been proposed for mitigating gender bias on the word embedding level is Counterfactual Data Augmentation (CDA) BIBREF25. We apply this method by augmenting our dataset with a copy of every dialogue with gendered words swapped using the gendered word pair list provided by BIBREF21.
Output:
| [
"How does counterfactual data augmentation aim to tackle bias?"
] | task461-7bc71338bf6b49e6a410a77734567331 |
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: News Articles
Our dataset source of news articles is described in BIBREF2. This dataset was built from two different sources, for the trusted news (real news) they sampled news articles from the English Gigaword corpus. For the false news, they collected articles from seven different unreliable news sites. Twitter
For this dataset, we rely on a list of several Twitter accounts for each type of false information from BIBREF6. This list was created based on public resources that annotated suspicious Twitter accounts. The authors in BIBREF6 have built a dataset by collecting tweets from these accounts and they made it available.
Output:
| [
"What datasets did they use?"
] | task461-25dbd166bf894b0f8e606610673a1caa |
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: So, we can impose the constraint that our model's representation of the input's syntax cannot contain this context-invariant information. This regularization is strictly preferable to allowing all aspects of word meaning to propagate into the input's syntax representation. Without such a constraint, all inputs could, in principle, be given their own syntactic categories.
Output:
| [
"Does having constrained neural units imply word meanings are fixed across different context?"
] | task461-291102e55b304c36b39f19ad73b92fb9 |
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: Ethnicity/race
One interesting pattern is that the ethnicity/race of babies doesn't seem to be mentioned unless the baby is black or asian. In other words: white seems to be the default, and others seem to be marked. How can we tell whether or not the data is actually biased?
The numbers in Table TABREF22 are striking: there seems to be a real, systematic difference in ethnicity marking between the groups. We can take one step further and look at all the 697 pictures with the word `baby' in it. If there turn out to be disproportionately many white babies, this strengthens the conclusion that the dataset is biased.
Output:
| [
"What biases are found in the dataset?"
] | task461-f177626ede384ca8969452881c92f546 |
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 experiment and compare with the following models.
Pointer-Gen is the baseline model trained by optimizing $L_\text{MLE}$ in Equation DISPLAY_FORM13.
Pointer-Gen+Pos is the baseline model by training Pointer-Gen only on positive examples whose sensationalism score is larger than 0.5
Pointer-Gen+Same-FT is the model which fine-tunes Pointer-Gen on the training samples whose sensationalism score is larger than 0.1
Pointer-Gen+Pos-FT is the model which fine-tunes Pointer-Gen on the training samples whose sensationalism score is larger than 0.5
Pointer-Gen+RL-ROUGE is the baseline model trained by optimizing $L_\text{RL-ROUGE}$ in Equation DISPLAY_FORM17, with ROUGE-L BIBREF9 as the reward.
Pointer-Gen+RL-SEN is the baseline model trained by optimizing $L_\text{RL-SEN}$ in Equation DISPLAY_FORM17, with $\alpha _\text{sen}$ as the reward.
Output:
| [
"Which baselines are used for evaluation?"
] | task461-e10eff1e39264025885d541d49664b86 |
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: Both the audio and the transcript are de-identified (by removing the identifying information) with digital zeros and [de-identified] tags, respectively.
Output:
| [
"Is the data de-identified?"
] | task461-de9a0629ad4643cf955955b1e2658101 |
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 phase 1 (also referred to as the “exploration” phase) the algorithm explores the state space through keeping track of previously visited states by maintaining an archive. During this phase, instead of resuming the exploration from scratch, the algorithm starts exploring from promising states in the archive to find high performing trajectories.
Output:
| [
"How is trajectory with how rewards extracted?"
] | task461-8f0581b96afc4f399f606effb18929b1 |
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: Experimental Setup
Output:
| [
"which chinese datasets were used?",
"what english datasets were used?",
"What domains are detected in this paper?"
] | task461-635d69761e804b5f8b3d41e7cbe431be |
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: RC-QED$^{\rm E}$ can be naturally solved by path ranking-based KGC (PRKGC), where the query triplet and the sampled paths correspond to a question and derivation steps, respectively.
Output:
| [
"What is the baseline?"
] | task461-d44d9c38b63641d282ae6c8f850c0ab5 |
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 performances of the NER experiments are reported separately for three different parts of the system proposed. Results shown that, in the first case, in the training set the F1 score is always greater than 97%, with a maximum of 99.65%. With both test sets performances decrease, varying between 94-97%. In the case of UGC, comparing the F1 score we can observe how performances significantly decrease.
Output:
| [
"What are their results on the entity recognition task?"
] | task461-101c8fda33b84965b7bc6c81fe8815ef |
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 main results are presented in Table TABREF6 on the test set of the regulatory filings and in Table TABREF7 on the test set of the property lease agreements; F$_1$, precision, and recall are computed in the manner described above.
Output:
| [
"What evaluation metric were used for presenting results? "
] | task461-9c5394fc5b904633bb3b9a89829c3f6f |
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 investigate the following six idiom resources:
Wiktionary;
the Oxford Dictionary of English Idioms (ODEI, BIBREF31);
UsingEnglish.com (UE);
the Sporleder corpus BIBREF10;
the VNC dataset BIBREF9;
and the SemEval-2013 Task 5 dataset BIBREF15.
Output:
| [
"What dictionaries are used for automatic extraction of PIEs?"
] | task461-5e8e9cdd0be442d298bf941933312d92 |
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 conducted the human evaluation using Amazon Mechanical Turk to assess subjective quality. We recruit master level workers (who have good prior approval rates) to perform a human comparison between generated responses from two systems (which are randomly sampled from comparison systems). The workers are required to judge each utterance from 1 (bad) to 3 (good) in terms of informativeness and naturalness. Informativeness indicates the extent to which generated utterance contains all the information specified in the dialog act. Naturalness denotes whether the utterance is as natural as a human does. To reduce judgement bias, we distribute each question to three different workers. Finally, we collected in total of 5800 judges.
Output:
| [
"What was the criteria for human evaluation?"
] | task461-66f5347fb8064d9caca21f0088e1c7f7 |
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 instance, a message can be regarded as harmless on its own, but when taking previous threads into account it may be seen as abusive, and vice versa. This aspect makes detecting abusive language extremely laborious even for human annotators; therefore it is difficult to build a large and reliable dataset BIBREF10 .
Output:
| [
"What examples of the difficulties presented by the context-dependent nature of online aggression do they authors give?"
] | task461-21c32996d22e4650a69f45b00ad064da |
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 achieve significant gains over our strong baseline by leveraging decompositions from our best decomposition model, trained with USeq2Seq on FastText pseudo-decompositions; we find a 3.1 F1 gain on the original dev set, 11 F1 gain on the multi-hop dev set, and 10 F1 gain on the out-of-domain dev set.
Output:
| [
"How large is the improvement over the baseline?"
] | task461-f2c173fe180e40d78c77c97877a10e68 |
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 further analysis the embeddings learned by our method, we use t-SNE tool BIBREF27 to visualize the learned embedding.
Output:
| [
"What further analysis is done?"
] | task461-216d0c74526e44098eb280835396a40a |
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 operationalized the question by submitting the chosen test data to the same vendor-based transcription pipeline that is used at Microsoft for production data (for model training and internal evaluation purposes), and then comparing the results to ASR system output under the NIST scoring protocol.
Output:
| [
"what standard speech transcription pipeline was used?"
] | task461-eb8397cff9264c1bae9f374a6f840825 |
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: Traditional text-to-speech (TTS) systems are composed of complex pipelines BIBREF0 , these often include accoustic frontends, duration model, acoustic prediction model and vocoder models. Neural text-to-speech systems have garnered large research interest in the past 2 years. The first to fully explore this avenue of research was Google's tacotron BIBREF1 system The architecture of our model utilizes RNN-based Seq2Seq model for generating mel spectrogram from text. The architecture is similar to that of Tacotron 2 BIBREF4 . Direct comparison of model parameters between ours and the open-source tacotron 2, our model contains 4.5 million parameters, whereas the Tacotron 2 contains around 13 million parameters with default setting
Output:
| [
"How do they measure the size of models?"
] | task461-1501ddf7367e411395b241cf4892af1d |
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 SVMhmm BIBREF111 implementation of Structural Support Vector Machines for sequence labeling. SVM implementation of
Output:
| [
"Which machine learning methods are used in experiments?"
] | task461-a7b1c87c13784367a29cef6494a5312d |
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: Proposed Fusion Techniques ::: Step-Wise Decoder Fusion
Our first proposed technique is the step-wise decoder fusion of visual features during every prediction step i.e. we concatenate the visual encoding as context at each step of the decoding process. Proposed Fusion Techniques ::: Multimodal Attention Modulation
Similar to general attention BIBREF8, wherein a variable-length alignment vector $a_{th}(s)$, whose size equals the number of time steps on the source side, is derived by comparing the current target hidden state $h_{t}$ with each source hidden state $\overline{h_{s}}$; we consider a variant wherein the visual encoding $v_{t}$ is used to calculate an attention distribution $a_{tv}(s)$ over the source encodings as well. Proposed Fusion Techniques ::: Visual-Semantic (VS) Regularizer
In terms of leveraging the visual modality for supervision, BIBREF1 use multi-task learning to learn grounded representations through image representation prediction.
Output:
| [
"What are 3 novel fusion techniques that are proposed?"
] | task461-4b10cd1d4b0a465f92b41e0cdab5006d |
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 VisDial v1.0 BIBREF0 dataset to train our models, where one example has an image with its caption, 9 question-answer pairs, and follow-up questions and candidate answers for each round. At round $r$, the caption and the previous question-answer pairs become conversational context. The whole dataset is split into 123,287/2,000/8,000 images for train/validation/test, respectively. Unlike the images in the train and validation sets, the images in the test set have only one follow-up question and candidate answers and their corresponding conversational context.
Output:
| [
"How big is dataset for this challenge?"
] | task461-8bd9fa9dfad6433f901c8a82c26e4bfb |
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 micro-averaged F1 score on all labels as the evaluation metric.
Output:
| [
"What metris are used for evaluation?"
] | task461-54212b4e7ce64b5eab2cffe6d7af7813 |
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: Three datasets annotated with emotions are commonly used for the development and evaluation of emotion detection systems, namely the Affective Text dataset, the Fairy Tales dataset, and the ISEAR dataset. A summary is provided in Table TABREF8 , which also shows, in the bottom row, what role each dataset has in our experiments: apart from the development portion of the Affective Text, which we used to develop our models (Section SECREF4 ), all three have been used as benchmarks for our evaluation.
Output:
| [
"Which existing benchmarks did they compare to?"
] | task461-220ba4bab1e04f3a8b25763233a761fd |
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: Similar to BIBREF9, we experiment with SVM with RBF kernel, with features that represent (1) the simple characteristics of the argument tree and (2) the linguistic characteristics of the claim.
Output:
| [
"What models that rely only on claim-specific linguistic features are used as baselines?"
] | task461-0ed7e044ba22430f95f01cff8910736a |
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: Overall, we observe a positive correlation between retweeting and co-voting, which is significantly different from zero. The strongest positive correlations are in the areas Area of freedom, security and justice, External relations of the Union, and Internal markets. Weaker, but still positive, correlations are observed in the areas Economic, social and territorial cohesion, European citizenship, and State and evolution of the Union. The only exception, with a significantly negative coefficient, is the area Economic and monetary system. This implies that in the area Economic and monetary system we observe a significant deviation from the usual co-voting patterns.
Output:
| [
"What is the relationship between the co-voting and retweeting patterns?"
] | task461-3a58643627c24a699d90c744a71828e9 |
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 data presented in this paper was collected and validated via Mozilla's Common Voice initiative. Using either the Common Voice website or iPhone app, contributors record their voice by reading sentences displayed on the screen (see Figure (FIGREF5)). The recordings are later verified by other contributors using a simple voting system. Shown in Figure (FIGREF6), this validation interface has contributors mark $<$audio,transcript$>$ pairs as being either correct (up-vote) or incorrect (down-vote).
Output:
| [
"What crowdsourcing platform is used for data collection and data validation?"
] | task461-cd83c8efe52a4251848bb4ce998d0ea9 |
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: Considering the improvements over the majority baseline achieved by the RNN model for both non-English (on the average 22.76% relative improvement; 15.82% relative improvement on Spanish, 72.71% vs. 84.21%, 30.53% relative improvement on Turkish, 56.97% vs. 74.36%, 37.13% relative improvement on Dutch, 59.63% vs. 81.77%, and 7.55% relative improvement on Russian, 79.60% vs. 85.62%) and English test sets (27.34% relative improvement), we can draw the conclusion that our model is robust to handle multiple languages.
Output:
| [
"which non-english language had the best performance?",
"which non-english language was the had the worst results?"
] | task461-cf20de288c28467dab4534d984748467 |
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: Specifically, we design three tasks for seq2seq model pre-training, namely Sentence Reordering (SR), Next Sentence Generation (NSG), and Masked Document Generation (MDG).
Output:
| [
"What is masked document generation?"
] | task461-fa5e686f006246e58f103d0ea57860ad |
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: Accordingly, marcheggiani2017 presented a neural model putting syntax aside for dependency-based SRL and obtain favorable results, which overturns the inherent belief that syntax is indispensable in SRL task BIBREF11 .
Output:
| [
"Are there syntax-agnostic SRL models before?"
] | task461-052a693560c047f2b2feb63896fc5091 |
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 formalize this intuition in a model called NextSum, which selects the next summary sentence based not only on properties of the source text, but also on the previously selected sentences in the summary.
Output:
| [
"How does nextsum work?"
] | task461-9d05a60fd5744cf88dc674cd112c5a43 |
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 PolyResponse restaurant search is currently available in 8 languages and for 8 cities around the world: English (Edinburgh), German (Berlin), Spanish (Madrid), Mandarin (Taipei), Polish (Warsaw), Russian (Moscow), Korean (Seoul), and Serbian (Belgrade).
Output:
| [
"In what 8 languages is PolyResponse engine used for restourant search and booking system?"
] | task461-5636054f6b1b49aaba7698fa2fe0b758 |
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 learning model for retrieval is trained by an oracle constructed using distant supervision. Using the answer labels in the training set, we can find appropriate articles that include the information requested in the question. First, the question and article are embedded into vector sequences, using the same method as the comprehension model. We do not use anonymization here, to retain simplicity. Otherwise, the anonymization procedure would have to be repeated several times for a potentially large collection of documents. These vector sequences are next fed to a Bi-GRU, to produce the outputs $v$ (for the question) and $H_c$ (for the document) similar to the previous section.
Output:
| [
"How can a neural model be used for a retrieval if the input is the entire Wikipedia?"
] | task461-cc573bff34884b848de5719c751febc3 |
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: Information Gathering: At step $t$ of the information gathering phase, the agent can issue one of the following four actions to interact with the paragraph $p$, where $p$ consists of $n$ sentences and where the current observation corresponds to sentence $s_k,~1 \le k \le n$:
previous: jump to $ \small {\left\lbrace \begin{array}{ll} s_n & \text{if $k = 1$,}\\ s_{k-1} & \text{otherwise;} \end{array}\right.} $
next: jump to $ \small {\left\lbrace \begin{array}{ll} s_1 & \text{if $k = n$,}\\ s_{k+1} & \text{otherwise;} \end{array}\right.} $
Ctrl+F $<$query$>$: jump to the sentence that contains the next occurrence of “query”;
stop: terminate information gathering phase.
Output:
| [
"What commands does their setup provide to models seeking information?"
] | task461-5308f96c0a634eef9aec82f1c6ce1ab6 |
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 paper explores the potential of predicting a user's industry –the aggregate of enterprises in a particular field– by identifying industry indicative text in social media.
Output:
| [
"What do they mean by a person's industry?"
] | task461-138d35e4f30347e89365b08763b1c410 |
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: jiant provides support for cutting-edge sentence encoder models, including support for Huggingface's Transformers. Supported models include: BERT BIBREF17, RoBERTa BIBREF27, XLNet BIBREF28, XLM BIBREF29, GPT BIBREF30, GPT-2 BIBREF31, ALBERT BIBREF32 and ELMo BIBREF33. jiant also supports the from-scratch training of (bidirectional) LSTMs BIBREF34 and deep bag of words models BIBREF35, as well as syntax-aware models such as PRPN BIBREF36 and ON-LSTM BIBREF37. jiant also supports word embeddings such as GloVe BIBREF38.
Output:
| [
"Is jiant compatible with models in any programming language?"
] | task461-7b98e07fda544aeb9dd75baa36026669 |
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: Adding word alignments in parallel sentences results in small, non significant improvements, even if there is some labeled data available in the source language. This difficulty in showing the usefulness of parallel corpora for SRI may be due to the current assumptions about role alignments, which mean that only a small percentage of roles are aligned. Further analyses reveals that annotating small amounts of data can easily outperform the performance gains obtained by adding large unlabeled dataset as well as adding parallel corpora.
Output:
| [
"Overall, does having parallel data improve semantic role induction across multiple languages?"
] | task461-c8c65da42182465586e69b819610da25 |
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 the proposed architecture on two publicly available datasets: the Adverse Drug Events (ADE) dataset BIBREF6 and the CoNLL04 dataset BIBREF7. We show that our architecture is able to outperform the current state-of-the-art (SOTA) results on both the NER and RE tasks in the case of ADE. In the case of CoNLL04, our proposed architecture achieves SOTA performance on the NER task and achieves near SOTA performance on the RE task. On both datasets, our results are SOTA when averaging performance across both tasks.
Output:
| [
"Do they repot results only on English data?"
] | task461-3ab6846db2ad4c8c8fe40a3a104a1569 |
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 used state-of-the-art features that have shown to be useful in ID: some of them are language-independent (e.g., punctuation marks, positive and negative emoticons, quotations, personal pronouns, tweet's length, named entities) while others are language-dependent relying on dedicated lexicons (e.g., negation, opinion lexicons, opposition words).
Output:
| [
"What text-based features are used?"
] | task461-5c53da9a4846446f98f105e344f12068 |
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: Instead, our analysis reveals that this behavior is caused by subtle artifacts arising from the translation process itself. In particular, we show that translating different parts of each instance separately (e.g. the premise and the hypothesis in NLI) can alter superficial patterns in the data (e.g. the degree of lexical overlap between them), which severely affects the generalization ability of current models. Based on the gained insights, we improve the state-of-the-art in XNLI, and show that some previous findings need to be reconsidered in the light of this phenomenon. The benchmark consists of a competence test, which evaluates the ability to understand antonymy relation and perform numerical reasoning, a distraction test, which evaluates the robustness to shallow patterns like lexical overlap and the presence of negation words, and a noise test, which evaluates robustness to spelling errors. Just as with previous experiments, we report results for the best epoch checkpoint in each test set.
Output:
| [
"What are examples of these artificats?"
] | task461-6f349c65c69548529bc32d79ef8b71f8 |
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 retrieved pairs are compared to the gold standard and evaluated using precision at $k$ (P@$k$, evaluating how often the correct translation is within the $k$ retrieved nearest neighbours of the query). Throughout this work we report P@1, which is equivalent to accuracy, but we also provide results with P@5 and P@10 in the Appendix.
Output:
| [
"What evaluation metrics did they use?"
] | task461-0404d7ffebbb4b2f829e81fa7d4d23a2 |
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 used the Twitter API to gather real-time tweets from September 2018 until February 2019, selecting the ones containing any of the 51 Hatebase terms that are more common in hate speech tweets, as studied in BIBREF9.
Output:
| [
"How is data collected, manual collection or Twitter api?"
] | task461-d6e76573269b4c009914133877a98a8c |
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: Through experiments on two large complex cross-domain datasets, SParC BIBREF2 and CoSQL BIBREF6, we carefully compare and analyze the performance of different context modeling methods.
Output:
| [
"What are two datasets models are tested on?"
] | task461-b62ff356dd54448890452b3589fe74f9 |
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 calculate the probability of a sentence with a long-short term memory (LSTM, hochreiter1997long) LM, i.e., a special type of RNN LM, which has been trained on a large corpus. We train our LSTM LMs on the English Gigaword corpus BIBREF15 , which consists of news data.
Output:
| [
"what language models do they use?"
] | task461-407d547d3bae4266a309f40d7c933041 |
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: Based on Euclidean distance between vector representations of visits we applied and compared two clustering algorithms: k-means and hierarchical clustering with Ward's method for merging clusters BIBREF23 .
Output:
| [
"Which clustering technique do they use on partients' visits texts?"
] | task461-147d1823fbbd4229aa31c0417acaf5f3 |
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 attention heads in the proposed adaptively sparse Transformer can specialize more and with higher confidence In particular, we analyzed how the attention heads in the proposed adaptively sparse Transformer can specialize more and with higher confidence.
Output:
| [
"How does their model improve interpretability compared to softmax transformers?"
] | task461-234d57a5b08b4d189a87a4575e8aec4e |
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 process gives a total of INLINEFORM0 10700 training examples with roughly 2000 to 3000 examples per class, with each speaker having an average of 185 examples.
Output:
| [
"How many instances does their dataset have?"
] | task461-340c39ddbe5244e78cb28c548b3c10df |
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 evaluate the usefulness of our corpus for SMT purposes, we used it to train an automatic translator with Moses BIBREF8 .
Output:
| [
"What SMT models did they look at?"
] | task461-f8538f71680c4502bbd718643b7dab38 |
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 final collection of Facebook pages for the experiments described in this paper is as follows: FoxNews, CNN, ESPN, New York Times, Time magazine, Huffington Post Weird News, The Guardian, Cartoon Network, Cooking Light, Home Cooking Adventure, Justin Bieber, Nickelodeon, Spongebob, Disney.
Output:
| [
"Which Facebook pages did they look at?"
] | task461-b469386262b24116b90d9c796eefb568 |
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 resource is composed of data from two different surveys. In both surveys subjects were asked to draw on a map (displayed under a Mercator projection) a polygon representing a given geographical descriptor, in the context of the geography of Galicia in Northwestern Spain (see Fig. FIGREF1 ). The first survey was run in order to obtain a high number of responses to be used as an evaluation testbed for modeling algorithms. It was answered by 15/16 year old students in a high school in Pontevedra (located in Western Galicia). 99 students provided answers for a list of 7 descriptors (including cardinal points, coast, inland, and a proper name). The second survey was addressed to meteorologists in the Galician Weather Agency BIBREF12 .
Output:
| [
"Which two datasets does the resource come from?"
] | task461-9517f889680f4e8cbe04a7afe87310e0 |
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 both of the systems on the WMT15 German-to-English training data, see Table TABREF18 for some statistics. For this purpose, we use manual alignments provided by RWTH German-English dataset as the hard alignments.
Output:
| [
"What datasets are used?"
] | task461-a0b8eeeff9ba4bdd9e138326b21869d2 |
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 training data consists of 2.09M sentence pairs extracted from LDC corpus.
Output:
| [
"Where does the vocabulary come from?"
] | task461-7e976ca9181b44ab9b9a4a6bec6097f3 |
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: After having sentence representation, we use some classification models to classify input sentences. Those models will be described in detail in the section SECREF13. The first model is TextCNN (figure FIGREF2) proposed in BIBREF11. It only contains CNN blocks following by some Dense layers. The output of multiple CNN blocks with different kernel sizes is connected to each other.
The second model is VDCNN (figure FIGREF5) inspired by the research in BIBREF12. Like the TextCNN model, it contains multiple CNN blocks. The addition in this model is its residual connection.
The third model is a simple LSTM bidirectional model (figure FIGREF15). It contains multiple LSTM bidirectional blocks stacked to each other.
The fourth model is LSTMCNN (figure FIGREF24). Before going through CNN blocks, series of word embedding will be transformed by LSTM bidirectional block. The final model is the system named SARNN (figure FIGREF25). It adds an attention block between LTSM blocks. In this system, we use the Stacking method. In this method, the output of each model is not only class id but also the probability of each class in the set of three classes. This probability will become a feature for the ensemble model. The stacking ensemble model here is a simple full-connection model with input is all of probability that output from sub-model. The output is the probability of each class.
Output:
| [
"What classifier do they use?"
] | task461-927dc3da286d40a1bbc113cc3fcbb36b |
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: Causal documents were chosen to contain one occurrence only of the exact unigrams: `caused', `causing', or `causes'.
Output:
| [
"What are the selection criteria for \"causal statements\"?",
"How do they extract causality from text?"
] | task461-9a4da1b9d99c4685a7a3588e01c48874 |
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 opted for an automatic approach instead, that can be scaled arbitrarily and at little cost: we generate synthetic sentence pairs $(, \tilde{})$ by randomly perturbing 1.8 million segments $$ from Wikipedia. We use three techniques: mask-filling with BERT, backtranslation, and randomly dropping out words.
Output:
| [
"How are the synthetic examples generated?"
] | task461-a312a3cab93d485c967dfffdebf66b90 |
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 semi-parametric models were trained on 32 GPUs with each replica split over 2 GPUs, one to train the translation model and the other for computing the CSTM.
Output:
| [
"Does their combination of a non-parametric retrieval and neural network get trained end-to-end?"
] | task461-c1e101e679214e1482c4af66f1c7032d |
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, we evaluate our approaches in 9 commonly used text classification datasets. We evaluate our methods on several commonly used datasets whose themes range from sentiment, web-page, science to medical and healthcare.
Output:
| [
"What NLP tasks do they consider?"
] | task461-60c7d1b0773648d7b88df3ed9bc511cc |