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: Our model encodes the information from audio and text sequences using dual RNNs and then combines the information from these sources using a feed-forward neural model to predict the emotion class.
Output:
| [
"How do they combine audio and text sequences in their RNN?"
] | task461-d61d08566d954e3d89b16ae192b44239 |
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: Depechemood is a lexicon-based emotion detection method gathered from crowd-annotated news BIBREF24. Drawing on approximately 23.5K documents with average of 500 words per document from rappler.com, researchers asked subjects to report their emotions after reading each article. They then multiplied the document-emotion matrix and word-document matrix to derive emotion-word matrix for these words.
Output:
| [
"How id Depechemood trained?"
] | task461-3d24a0cbbb2e488ba137d8d71e7b17a8 |
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 competition is divided into five subtasks which involve standard classification, ordinal classification and distributional estimation. For a more detailed description see BIBREF0 .
Output:
| [
"What were the five English subtasks?"
] | task461-a312f3dc59454f6dab4bf2a6ece285fb |
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 characterize the evaluation of Emotionally-Aware Chatbot into two different parts, qualitative and quantitative assessment. Qualitative assessment will focus on assessing the functionality of the software, while quantitative more focus on measure the chatbots' performance with a number. Based on our investigation of several previous studies, we found that most of the works utilized ISO 9241 to assess chatbots' quality by focusing on the usability aspect. This aspect can be grouped into three focuses, including efficiency, effectiveness, and satisfaction, concerning systems' performance to achieve the specified goals. In automatic evaluation, some studies focus on evaluating the system at emotion level BIBREF15 , BIBREF28 . Therefore, some common metrics such as precision, recall, and accuracy are used to measure system performance, compared to the gold label. This evaluation is similar to emotion classification tasks such as previous SemEval 2018 BIBREF32 and SemEval 2019 . Other studies also proposed to use perplexity to evaluate the model at the content level (to determine whether the content is relevant and grammatical) BIBREF14 , BIBREF39 , BIBREF28 . This evaluation metric is widely used to evaluate dialogue-based systems which rely on probabilistic approach BIBREF61 . Another work by BIBREF14 used BLEU to evaluate the machine response and compare against the gold response (the actual response), although using BLEU to measure conversation generation task is not recommended by BIBREF62 due to its low correlation with human judgment. This evaluation involves human judgement to measure the chatbots' performance, based on several criteria. BIBREF15 used three annotators to rate chatbots' response in two criteria, content (scale 0,1,2) and emotion (scale 0,1). Content is focused on measuring whether the response is natural acceptable and could plausible produced by a human. This metric measurement is already adopted and recommended by researchers and conversation challenging tasks, as proposed in BIBREF38 .
Output:
| [
"How are EAC evaluated?"
] | task461-2182a14d5a3f4f3db0d12caa1351aaf6 |
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 dataset was collected through Mechanical Turk using 100 simulated environments with a corresponding topological map and, to the best of our knowledge, it is the first of its kind for behavioral navigation. We created a new dataset for the problem of following navigation instructions under the behavioral navigation framework of BIBREF5 . This dataset was created using Amazon Mechanical Turk and 100 maps of simulated indoor environments, each with 6 to 65 rooms. To the best of our knowledge, this is the first benchmark for comparing translation models in the context of behavioral robot navigation.
As shown in Table TABREF16 , the dataset consists of 8066 pairs of free-form natural language instructions and navigation plans for training. This training data was collected from 88 unique simulated environments, totaling 6064 distinct navigation plans (2002 plans have two different navigation instructions each; the rest has one). The dataset contains two test set variants:
While the dataset was collected with simulated environments, no structure was imposed on the navigation instructions while crowd-sourcing data. Thus, many instructions in our dataset are ambiguous. Moreover, the order of the behaviors in the instructions is not always the same. For instance, a person said “turn right and advance” to describe part of a route, while another person said “go straight after turning right” in a similar situation. The high variability present in the natural language descriptions of our dataset makes the problem of decoding instructions into behaviors not trivial. See Appendix A of the supplementary material for additional details on our data collection effort.
Output:
| [
"How were the navigation instructions collected?"
] | task461-a0cbc347a6b441b4b814b0f39bc0e37a |
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: FastTextBIBREF4: It uses bag of words and bag of n-grams as features for text classification, capturing partial information about the local word order efficiently. BiLSTM: Unlike feedforward neural networks, recurrent neural networks like BiLSTMs use memory based on history information to learn long-distance features and then predict the output. We use a two-layer BiLSTM architecture with GloVe word embeddings as a strong RNN baseline. BERT BIBREF5: It is a contextualized word representation model that uses bidirectional transformers, pretrained on a large $3.3B$ word corpus. We use the $BERT_{large}$ model finetuned on the training dataset.
Output:
| [
"What is the baseline for the experiments?"
] | task461-4d6c5b35f8bd467991243fdbc7a7d5f8 |
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 quality of the document embeddings learned by MPAD on 10 document classification datasets, covering the topic identification, coarse and fine sentiment analysis and opinion mining, and subjectivity detection tasks. We briefly introduce the datasets next. Their statistics are reported in Table TABREF21.
(1) Reuters. This dataset contains stories collected from the Reuters news agency in 1987. Following common practice, we used the ModApte split and considered only the 10 classes with the highest number of positive training examples. We also removed documents belonging to more than one class and then classes left with no document (2 classes).
(2) BBCSport BIBREF30 contains documents from the BBC Sport website corresponding to 2004-2005 sports news articles.
(3) Polarity BIBREF31 features positive and negative labeled snippets from Rotten Tomatoes.
(4) Subjectivity BIBREF32 contains movie review snippets from Rotten Tomatoes (subjective sentences), and Internet Movie Database plot summaries (objective sentences).
(5) MPQA BIBREF33 is made of positive and negative phrases, annotated as part of the summer 2002 NRRC Workshop on Multi-Perspective Question Answering.
(6) IMDB BIBREF34 is a collection of highly polarized movie reviews from IMDB (positive and negative). There are at most 30 reviews for each movie.
(7) TREC BIBREF35 consists of questions that are classified into 6 different categories.
(8) SST-1 BIBREF36 contains the same snippets as Polarity. The authors used the Stanford Parser to parse the snippets and split them into multiple sentences. They then used Amazon Mechanical Turk to annotate the resulting phrases according to their polarity (very negative, negative, neutral, positive, very positive).
(9) SST-2 BIBREF36 is the same as SST-1 but with neutral reviews removed and snippets classified as positive or negative.
(10) Yelp2013 BIBREF26 features reviews obtained from the 2013 Yelp Dataset Challenge.
Output:
| [
"Which datasets are used?"
] | task461-e82a33ce26f14a25a0befa67b82adda4 |
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 type and correctness of all the question answer pairs are verified by at least two annotators.
Output:
| [
"What was the inter-annotator agreement?"
] | task461-8049aee2c02044b2a797e29c559c7bec |
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 experiments are run using the English$\rightarrow $Italian/German portions of the MuST-C corpus BIBREF25, which is extracted from TED talks, using the same train/validation/test split as provided with the corpus (see Table TABREF18). As additional data, we use a mix of public and proprietary data for about 16 million sentence pairs for English-Italian (En-It) and $4.4$ million WMT14 sentence pairs for the English-German (En-De).
Output:
| [
"What dataset do they use?",
"What dataset do they use for experiments?"
] | task461-5ac5a884f93d4625840d54c9831fe923 |
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 represent each instance of image, question, and user choice as a triplet consisting of image feature, question feature, and the label vector for the user's answer. In addition, collecting multiple choices from identical users enables us to represent any two instances by the same user as a pair of triplets, assuming source-target relation. With these pairs of triplets, we can train the system to predict a user's choice on a new image and a new question, given the same user's choice on the previous image and its associated question. As discussed earlier, we attempt to reflect user's interest by asking questions that provide visual context. In other words, a question whose answer is so obvious that it can be answered in an identical way would not be valid as an interactive question. If the most likely candidate $c_i=\max p_{ans}$ , where $c_i \in C$ , has a probability of being answer over a certain threshold $\alpha $ , then the question is considered to have a single obvious answer, and is thus considered ineligible. In our experiments, we set $\alpha $ as 0.33. We also excluded the yes/no type of questions.
Output:
| [
"What are the features of used to customize target user interaction? "
] | task461-164f031f1a3846f2957e06425a416ea3 |
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 multi-task BERT models involve six different Arabic classification tasks. Author profiling and deception detection in Arabic (APDA). LAMA+DINA Emotion detection. Sentiment analysis in Arabic tweets.
Output:
| [
"What are the tasks used in the mulit-task learning setup?"
] | task461-1fc5545596e44a4bbf6b860fd8892970 |
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 word2vec BIBREF0 to train the word embeddings.
Output:
| [
"What kind of model do they build to expand abbreviations?"
] | task461-cb0f2d7e6014422f813a383d1a23aac3 |
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 Amazon Mechanical Turk (AMT) for our annotations, restricting the task to workers in five English-speaking countries (USA, UK, Canada, New Zealand, and Australia), more than 1000 finished HITs and at least a 95% acceptance rate.
Output:
| [
"What crowdsourcing platform did they use?"
] | task461-ac5750311b7e465caf2d999814db6678 |
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 approach on the Chinese social media text summarization task, based on the sequence-to-sequence model. Large-Scale Chinese Short Text Summarization Dataset (LCSTS) is constructed by BIBREF1 . The dataset consists of more than 2.4 million text-summary pairs in total, constructed from a famous Chinese social media microblogging service Weibo.
Output:
| [
"Are results reported only for English data?"
] | task461-d5b9d4a95b9940b2b033df2f833f0d19 |
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 employ BIBREF73 's weighted lexicon of terms that uses the dataset of 75,394 Facebook users who shared their status, age and gender. Utilizing these two weighted lexicon of terms, we are predicting the demographic information (age or gender) of INLINEFORM0 (denoted by INLINEFORM1 ) using following equation: INLINEFORM2
where INLINEFORM0 is the lexicon weight of the term, and INLINEFORM1 represents the frequency of the term in the user generated INLINEFORM2 , and INLINEFORM3 measures total word count in INLINEFORM4 .
Output:
| [
"How do this framework facilitate demographic inference from social media?"
] | task461-c3208cc2583b4fea8fd9a0f0a246853c |
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 general, the model transforms the segments into object-pairs by the TC-CNN and passes sentence through bi-GRU to obtain the global representation. Then we integrate object-pairs with global representation and make a pair-wise inference to detect the relationship among the segments. Ablation studies show that the proposed SCRN at the segment level has the capacity for relational reasoning and promotes the result significantly.
Output:
| [
"How is Relation network used to infer causality at segment level?"
] | task461-fdb94d56ca8b4d3cac95e9dc70936a29 |
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 feed these representations into a clustering algorithm that produces exactly eleven clusters of five cities each and evaluate them against both Calvino's original labels and crowdsourced human judgments. While the overall correlation with Calvino's labels is low, both computers and humans can reliably identify some thematic groups associated with concrete objects.
Output:
| [
"How do they obtain human judgements?"
] | task461-d53421d4fce84ab78d16c5f502338661 |
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: On Twitter we can see results that are consistent with the RCV results for the left-to-center political spectrum. The exception, which clearly stands out, is the right-wing groups ENL and EFDD that seem to be the most cohesive ones. This is the direct opposite of what was observed in the RCV data. We speculate that this phenomenon can be attributed to the fact that European right-wing groups, on a European but also on a national level, rely to a large degree on social media to spread their narratives critical of European integration.
Output:
| [
"Do the authors mention any possible confounds in their study?"
] | task461-0e39f381586440ad9e3377924db25c7d |
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 HotpotQA, on average we can find 6 candidate chains (2-hop) in a instance, and the human labeled true reasoning chain is unique. A predicted chain is correct if the chain only contains all supporting passages (exact match of passages).
In MedHop, on average we can find 30 candidate chains (3-hop). For each candidate chain our human annotators labeled whether it is correct or not, and the correct reasoning chain is not unique. A predicted chain is correct if it is one of the chains that human labeled as correct.
The accuracy is defined as the ratio: The accuracy is defined as the ratio:
Output:
| [
"What benchmarks are created?"
] | task461-1b2c81c95e144815843c0368c1243850 |
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: Method ::: Passage Ranking Model
The key component of our framework is the Ranker model, which is provided with a question $q$ and $K$ passages $\mathcal {P} = \lbrace p_1, p_2 ... p_K\rbrace $ from a pool of candidates, and outputs a chain of selected passages. Method ::: Cooperative Reasoner
To alleviate the noise in the distant supervision signal $\mathcal {C}$, in addition to the conditional selection, we further propose a cooperative Reasoner model, also implemented with the MatchLSTM architecture (see Appendix SECREF6), to predict the linking entity from the selected passages.
Output:
| [
"What are two models' architectures in proposed solution?"
] | task461-c70adbe8c8b14e8fb2aaa47d222744fe |
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, I introduce an interpretable word embedding model, and an associated topic model, which are designed to work well when trained on a small to medium-sized corpus of interest. I tested the performance of the representations as features for document categorization and regression tasks. The results are given in Table TABREF26 . For document categorization, I used three standard benchmark datasets: 20 Newsgroups (19,997 newsgroup posts), Reuters-150 newswire articles (15,500 articles and 150 classes), and Ohsumed medical abstracts on 23 cardiovascular diseases (20,000 articles). I I also analyzed the regression task of predicting the year of a state of the Union address based on its text information.
Output:
| [
"What supervised learning tasks are attempted with these representations?"
] | task461-245ffde0f5c34a34b9f594e39dc4b956 |
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 model an answer which is a collection of spans, the multi-span head uses the $\mathtt {BIO}$ tagging format BIBREF8: $\mathtt {B}$ is used to mark the beginning of a span, $\mathtt {I}$ is used to mark the inside of a span and $\mathtt {O}$ is used to mark tokens not included in a span. In this way, we get a sequence of chunks that can be decoded to a final answer - a collection of spans.
Output:
| [
"How they use sequence tagging to answer multi-span questions?"
] | task461-95afcc99452d49fdb8d1ed78373adf19 |
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 target data set consists of a corpus of discharge summaries, admission notes, individual encounter notes, and other clinical notes from 220 patients in the OnTrackTM program at McLean Hospital. OnTrackTM is an outpatient program, focusing on treating adults ages 18 to 30 who are experiencing their first episodes of psychosis. The length of time in the program varies depending on patient improvement and insurance coverage, with an average of two to three years. The program focuses primarily on early intervention via individual therapy, group therapy, medication evaluation, and medication management. See Table TABREF2 for a demographic breakdown of the 220 patients, for which we have so far extracted approximately 240,000 total EHR paragraphs spanning from 2011 to 2014 using Meditech, the software employed by McLean for storing and organizing EHR data.
These patients are part of a larger research cohort of approximately 1,800 psychosis patients, which will allow us to connect the results of this EHR study with other ongoing research studies incorporating genetic, cognitive, neurobiological, and functional outcome data from this cohort.
We also use an additional data set for training our vector space model, comprised of EHR texts queried from the Research Patient Data Registry (RPDR), a centralized regional data repository of clinical data from all institutions in the Partners HealthCare network. These records are highly comparable in style and vocabulary to our target data set. The corpus consists of discharge summaries, encounter notes, and visit notes from approximately 30,000 patients admitted to the system's hospitals with psychiatric diagnoses and symptoms. This breadth of data captures a wide range of clinical narratives, creating a comprehensive foundation for topic extraction.
Output:
| [
"What datasets did the authors use?"
] | task461-1e3daec1362e41c58bc76d00c8cafd4d |
Definition: In this task, you will be presented with a context from an academic paper and you have to write an answerable question based on the context. Your questions can be extractive, abstractive, or yes-no questions.
Positive Example 1 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: how was the dataset built?
Positive Example 2 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language are the tweets?
Negative Example 1 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language is tweets?
Negative Example 2 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: What is the size of the dataset?
Now complete the following example -
Input: We have also performed preliminary experiments on the Arabic portion of the SemEval-2016 cQA task.
Output:
| [
"Did they experimnet in other languages?"
] | task461-753a832e6e92410e81e390b38b284477 |
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 achieve this, a method is proposed that transforms the goal-labels of the used dataset (DSTC2) into labels whose behaviour can be replicated during deployment.
Output:
| [
"what corpus is used to learn behavior?"
] | task461-b705bc909ad24a27b9ddc05a6a8dedbb |
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: There are almost 1.1 million sentences in the collection. There are 119 different relation types (unique predicates), having from just a few relations to a few million relations.
Output:
| [
"How big is their dataset?"
] | task461-49cf5f9e8b8c447cbbc0efd86d366fc9 |
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 Universal Dependencies' Hindi-English codemixed data set BIBREF9 to test the model's ability to label code-mixed data. This dataset is based on code-switching tweets of Hindi and English multilingual speakers. We use the Devanagari script provided by the data set as input tokens.
Output:
| [
"What codemixed language pairs are evaluated?"
] | task461-5c7afb8d19724d8fb5159836c40fc83c |
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: Prior to the SAOKE data set, an annotated data set for OIE tasks with 3,200 sentences in 2 domains was released in BIBREF20 to evaluate OIE algorithms, in which the data set was said BIBREF20 “13 times larger than the previous largest annotated Open IE corpus”.
Output:
| [
"What's the size of the previous largest OpenIE dataset?"
] | task461-0b018e7bd2d64a00b5c0ab5f25654f40 |
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: EmotionLines BIBREF6 is a dialogue dataset composed of two subsets, Friends and EmotionPush, according to the source of the dialogues.
Output:
| [
"what datasets were used?"
] | task461-ccf000947d6c49f6a2536a46f929b5b0 |
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: Each passage was labelled by 3 unique annotators.
Output:
| [
"How many annotators were there?"
] | task461-6f53595f6e914e4fa9efd43cde6d69fd |
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 test this hypothesis we first trained UG-WGAN in English, Chinese and German following the procedure described in Section "UG-WGAN" . For this experiment we trained UG-WGAN on the English and Russian language following the procedure described in Section "UG-WGAN" . To do so we trained 6 UG-WGAN models on the following languages: English, Russian, Arabic, Chinese, German, Spanish, French.
Output:
| [
"What are the languages they consider in this paper?"
] | task461-a62a385fbef84abeae4bc510184b611a |
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: Observe that in only about 12% (7 of the top 59) of the most cited areas of research, women received higher average citations than men. These include: sentiment analysis, information extraction, document summarization, spoken dialogue, cross lingual (research), dialogue, systems, language generation. (Of course, note that some of the 59 areas, as estimated using title term bigrams, are overlapping. Also, we did not include large scale in the list above because the difference in averages is very small and it is not really an area of research.) Thus, the citation gap is common across a majority of the high-citations areas within NLP.
Output:
| [
"Which NLP area have the highest average citation for woman author?"
] | task461-b4768156d85f4828982139704bc113e2 |
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: WN18RR dataset consists of two kinds of relations: the symmetric relations such as $\_similar\_to$, which link entities in the category (b); other relations such as $\_hypernym$ and $\_member\_meronym$, which link entities in the category (a). Actually, RotatE can model entities in the category (b) very well BIBREF7. However, HAKE gains a 0.021 higher MRR, a 2.4% higher H@1, and a 2.4% higher H@3 against RotatE, respectively. FB15k-237 dataset has more complex relation types and fewer entities, compared with WN18RR and YAGO3-10. Although there are relations that reflect hierarchy in FB15k-237, there are also lots of relations, such as “/location/location/time_zones” and “/film/film/prequel”, that do not lead to hierarchy. The characteristic of this dataset accounts for why our proposed models doesn't outperform the previous state-of-the-art as much as that of WN18RR and YAGO3-10 datasets. AGO3-10 datasets contains entities with high relation-specific indegree BIBREF18. For example, the link prediction task $(?, hasGender, male)$ has over 1000 true answers, which makes the task challenging. Fortunately, we can regard “male” as an entity at higher level of the hierarchy and the predicted head entities as entities at lower level. In this way, YAGO3-10 is a dataset that clearly has semantic hierarchy property, and we can expect that our proposed models is capable of working well on this dataset. Table TABREF19 validates our expectation. Both ModE and HAKE significantly outperform the previous state-of-the-art. Notably, HAKE gains a 0.050 higher MRR, 6.0% higher H@1 and 4.6% higher H@3 than RotatE, respectively.
Output:
| [
"How better does HAKE model peform than state-of-the-art methods?"
] | task461-67906f68b0624c408d20ced86108951d |
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 prediction of outcomes of debates is very interesting in our case. Most of the results seem to match with the views of some experts such as the political pundits of the Washington Post. This implies that certain rules that were used to score the candidates in the debates by said-experts were in fact reflected by reading peoples' sentiments expressed over social media. This opens up a wide variety of learning possibilities from users' sentiments on social media, which is sometimes referred to as the wisdom of crowd.
Output:
| [
"Who is the crowd in these experiments?"
] | task461-6a180bea2cd24835afceae1abeeb3eec |
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: Davidson et al. BIBREF2 showed that there were systematic and substantial racial biases in five benchmark Twitter datasets annotated for offensive language detection. By examining more samples and with respect to recently studies BIBREF2, BIBREF24, BIBREF19, it is clear that many errors are due to biases from data collection BIBREF19 and rules of annotation BIBREF24 and not the classifier itself.
Output:
| [
"What are the existing biases?"
] | task461-21a637bbd4734ba8bb85c0d28151abae |
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 AV in-cabin data-set includes 30 hours of multimodal data collected from 30 passengers (15 female, 15 male) in 20 rides/sessions. 10 types of passenger intents are identified and annotated as: Set/Change Destination, Set/Change Route (including turn-by-turn instructions), Go Faster, Go Slower, Stop, Park, Pull Over, Drop Off, Open Door, and Other (turn music/radio on/off, open/close window/trunk, change AC/temp, show map, etc.). Relevant slots are identified and annotated as: Location, Position/Direction, Object, Time-Guidance, Person, Gesture/Gaze (this, that, over there, etc.), and None. In addition to utterance-level intent types and their slots, word-level intent keywords are annotated as Intent as well.
Output:
| [
"What intents does the paper explore?"
] | task461-c0a999829b9a41f2844c6318b1d59265 |
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 graphs in figure 1 show the distances between duplicate and non-duplicate questions using different embedding systems. Large achieved a F1 score of 0.71 for this task without any specific training, simply by choosing a threshold below which all sentence pairs are considered duplicates. In order to test whether these results generalised to our domain, we devised a test that would make use of what little data we had to evaluate.
Output:
| [
"How is the accuracy of the system measured?"
] | task461-3bbe12a416ca4d7fbab4982a0e5b4591 |
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 decoder is the second LSTM network that uses the information obtained from the encoder to generate the sequence's story. The first input $x_0$ to the decoder is the image for which the text is being generated. The last hidden state from the encoder $h_e^{(t)}$ is used to initialize the first hidden state of the decoder $h_d^{(0)}$ . With this strategy, we provide the decoder with the context of the whole sequence and the content of the current image (i.e. global and local information) to generate the corresponding text that will contribute to the overall story.
Output:
| [
"How is the sequential nature of the story captured?"
] | task461-71bacd424e8741cbac0ba2673f4847db |
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 tackle this issue, we present a new evaluation dataset that covers a wide range of monotonicity reasoning that was created by crowdsourcing and collected from linguistics publications (Section "Dataset" ).
Output:
| [
"Do they release MED?"
] | task461-e06265b4797e429faa1643bd9f86c52c |
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: Each dataset consists of a collection of records with one QA problem per record. For each record, we include some question text, a context document relevant to the question, a set of candidate solutions, and the correct solution. The context document for each record consists of a list of ranked and scored pseudodocuments relevant to the question. Several baselines rely on the retrieved context to extract the answer to a question. For these, we refer to the fraction of instances for which the correct answer is present in the context as Search Accuracy. Naturally, the search accuracy increases as the context size increases, however at the same time reading performance decreases since the task of extracting the answer becomes harder for longer documents.
Output:
| [
"Which retrieval system was used for baselines?"
] | task461-4d7ca357f75a4399a149ae8f9f938324 |
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 that non-content words are distinctive enough for a classifier to determine style, we propose a suite of low-level linguistic feature counts (henceforth, controls) as our formal, content-blind definition of style. The style of a sentence is represented as a vector of counts of closed word classes (like personal pronouns) as well as counts of syntactic features like the number of SBAR non-terminals in its constituency parse, since clause structure has been shown to be indicative of style BIBREF20. Controls are extracted heuristically, and almost all rely on counts of pre-defined word lists. For constituency parses we use the Stanford Parser BIBREF21. table:controlexamples lists all the controls along with examples.
Output:
| [
"How they model style as a suite of low-level linguistic controls, such as frequency of pronouns, prepositions, and subordinate clause constructions?"
] | task461-ba4202ccd84d4f48be2d419ff5f80a40 |
Definition: In this task, you will be presented with a context from an academic paper and you have to write an answerable question based on the context. Your questions can be extractive, abstractive, or yes-no questions.
Positive Example 1 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: how was the dataset built?
Positive Example 2 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language are the tweets?
Negative Example 1 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language is tweets?
Negative Example 2 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: What is the size of the dataset?
Now complete the following example -
Input: While the performances of a purely content-based model naturally stays stable, the performance of the other systems decrease notably – they perform worse than the content-based model.
Output:
| [
"How do they demonstrate the robustness of their results?"
] | task461-be6e99f3386e4129b095b85d67721610 |
Definition: In this task, you will be presented with a context from an academic paper and you have to write an answerable question based on the context. Your questions can be extractive, abstractive, or yes-no questions.
Positive Example 1 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: how was the dataset built?
Positive Example 2 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language are the tweets?
Negative Example 1 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language is tweets?
Negative Example 2 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: What is the size of the dataset?
Now complete the following example -
Input: As shown in Equation ( EQREF6 ), tone prediction sub-network ( INLINEFORM0 ) takes video and pinyin sequence as inputs and predict corresponding tone sequence. Video context vectors INLINEFORM0 and pinyin context vectors INLINEFORM1 are fused when predicting a tone character at each decoder step. The video encoder is the same as in Section SECREF7 and the pinyin encoder is: DISPLAYFORM0 The input video sequence is first fed into the VGG model BIBREF9 to extract visual feature. The output of conv5 of VGG is appended with global average pooling BIBREF10 to get the 512-dim feature vector. Then the 512-dim feature vector is fed into video encoder.
Output:
| [
"What visual information characterizes tones?"
] | task461-82cdab0252c94ee3a515385a4ff7f16b |
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: Understanding a user's intent and sentiment is of utmost importance for current intelligent chatbots to respond appropriately to human requests. However, current systems are not able to perform to their best capacity when presented with incomplete data, meaning sentences with missing or incorrect words. This scenario is likely to happen when one considers human error done in writing. In fact, it is rather naive to assume that users will always type fully grammatically correct sentences.
Output:
| [
"How do the authors define or exemplify 'incorrect words'?"
] | task461-8380121337b240b18f465e4a3684c0e5 |
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 analyze the Hamming distance between the projections of the sentences from the enwik9 dataset and the corresponding projections of the same sentences after applying character level perturbations. We experiment with three types of character level perturbation BIBREF11 and two types of word level perturbation operations.
Perturbation Study ::: Character Level Perturbation Operations
insert(word, n) : We randomly choose n characters from the character vocabulary and insert them at random locations into the input word. We however retain the first and last characters of the word as is. Ex. transformation: $sample \rightarrow samnple$.
swap(word, n): We randomly swap the location of two characters in the word n times. As with the insert operation, we retain the first and last characters of the word as is and only apply the swap operation to the remaining characters. Ex. transformation: $sample \rightarrow sapmle$.
duplicate(word, n): We randomly duplicate a character in the word by n times. Ex. transformation: $sample \rightarrow saample$.
Perturbation Study ::: Character Level Perturbation Operations ::: Word Level Perturbation Operations
drop(sentence, n): We randomly drop n words from the sentence. Ex. transformation: This is a big cat. $\rightarrow $ This is a cat.
duplicate(sentence, n): Similar to duplicate(word, n) above, we randomly duplicate a word in the sentence n times. Ex. transformation: This is a big cat. $\rightarrow $ This is a big big cat.
swap(sentence, n): Similar to swap(word, n), we randomly swap the location of two words in the sentence n times. Ex. transformation: This is a big cat. $\rightarrow $ This cat is big.
Output:
| [
"How does their perturbation algorihm work?"
] | task461-1b97fe1586334a56a2bc1bef86199443 |
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: Methodology ::: Corpus-based Approach
Contextual information is informative in the sense that, in general, similar words tend to appear in the same contexts. In the corpus-based approach, we capture both of these characteristics and generate word embeddings specific to a domain. Methodology ::: Dictionary-based Approach
In Turkish, there do not exist well-established sentiment lexicons as in English. In this approach, we made use of the TDK (Türk Dil Kurumu - “Turkish Language Institution”) dictionary to obtain word polarities.
Output:
| [
"What word-based and dictionary-based feature are used?"
] | task461-0aac4e7c37574a53b8fd6a5ebc280980 |
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: There are several caveats in our work: first, tweet sentiment is rarely binary (this work could be extended to a multinomial or continuous model). Second, our results are constrained to Twitter users, who are known to be more negative than the general U.S. population BIBREF9 . Third, we do not take into account the aggregate effects of continued natural disasters over time. Going forward, there is clear demand in discovering whether social networks can indicate environmental metrics in a “nowcasting" fashion. As climate change becomes more extreme, it remains to be seen what degree of predictive power exists in our current model regarding climate change sentiments with regards to natural disasters.
Output:
| [
"Do the authors mention any confounds to their study?"
] | task461-6e5f95fdd93e4090aa180f7e8f9babef |
Definition: In this task, you will be presented with a context from an academic paper and you have to write an answerable question based on the context. Your questions can be extractive, abstractive, or yes-no questions.
Positive Example 1 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: how was the dataset built?
Positive Example 2 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language are the tweets?
Negative Example 1 -
Input: Using this annotation model, we create a new large publicly available dataset of English tweets.
Output: In what language is tweets?
Negative Example 2 -
Input: Questions are gathered from anonymized, aggregated queries to the Google search engine. Queries that are likely to be yes/no questions are heuristically identified: we found selecting queries where the first word is in a manually constructed set of indicator words and are of sufficient length, to be effective.
Questions are only kept if a Wikipedia page is returned as one of the first five results, in which case the question and Wikipedia page are given to a human annotator for further processing.
Annotators label question/article pairs in a three-step process. First, they decide if the question is good, meaning it is comprehensible, unambiguous, and requesting factual information. This judgment is made before the annotator sees the Wikipedia page. Next, for good questions, annotators find a passage within the document that contains enough information to answer the question. Annotators can mark questions as “not answerable" if the Wikipedia article does not contain the requested information. Finally, annotators mark whether the question's answer is “yes" or “no". Annotating data in this manner is quite expensive since annotators need to search entire Wikipedia documents for relevant evidence and read the text carefully.
Output: What is the size of the dataset?
Now complete the following example -
Input: We evaluated the phrase compositionality models on the adjective–noun and noun–noun phrase similarity tasks compiled by Mitchell2010, using the same evaluation scheme as in the original work. Spearman's INLINEFORM0 between phrasal similarities derived from our compositional functions and the human annotators (computed individually per annotator and then averaged across all annotators) was the evaluation measure.
Output:
| [
"How do they score phrasal compositionality?"
] | task461-cabc759167d5490d85e5cd1a52c4aa4f |
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 TABREF16 shows the recognition performance of naive multilingual approach using BLSTMP and VGG model against a monolingual model trained with BLSTMP. The results clearly indicate that having a better architecture such as VGG-BLSTM helps in improving multilingual performance. We used a character-level RNNLM, which was trained with 2-layer LSTM on character sequences.
Output:
| [
"What architectures are explored to improve the seq2seq model?"
] | task461-f747bc5a1e5d44a0b99fd32b47ee50ca |
End of preview. Expand
in Dataset Viewer.
Dataset Card for Natural Instructions (https://github.com/allenai/natural-instructions) Task: task461_qasper_question_generation
Additional Information
Citation Information
The following paper introduces the corpus in detail. If you use the corpus in published work, please cite it:
@misc{wang2022supernaturalinstructionsgeneralizationdeclarativeinstructions,
title={Super-NaturalInstructions: Generalization via Declarative Instructions on 1600+ NLP Tasks},
author={Yizhong Wang and Swaroop Mishra and Pegah Alipoormolabashi and Yeganeh Kordi and Amirreza Mirzaei and Anjana Arunkumar and Arjun Ashok and Arut Selvan Dhanasekaran and Atharva Naik and David Stap and Eshaan Pathak and Giannis Karamanolakis and Haizhi Gary Lai and Ishan Purohit and Ishani Mondal and Jacob Anderson and Kirby Kuznia and Krima Doshi and Maitreya Patel and Kuntal Kumar Pal and Mehrad Moradshahi and Mihir Parmar and Mirali Purohit and Neeraj Varshney and Phani Rohitha Kaza and Pulkit Verma and Ravsehaj Singh Puri and Rushang Karia and Shailaja Keyur Sampat and Savan Doshi and Siddhartha Mishra and Sujan Reddy and Sumanta Patro and Tanay Dixit and Xudong Shen and Chitta Baral and Yejin Choi and Noah A. Smith and Hannaneh Hajishirzi and Daniel Khashabi},
year={2022},
eprint={2204.07705},
archivePrefix={arXiv},
primaryClass={cs.CL},
url={https://arxiv.org/abs/2204.07705},
}
More details can also be found in the following paper:
@misc{brüelgabrielsson2024compressserveservingthousands,
title={Compress then Serve: Serving Thousands of LoRA Adapters with Little Overhead},
author={Rickard Brüel-Gabrielsson and Jiacheng Zhu and Onkar Bhardwaj and Leshem Choshen and Kristjan Greenewald and Mikhail Yurochkin and Justin Solomon},
year={2024},
eprint={2407.00066},
archivePrefix={arXiv},
primaryClass={cs.DC},
url={https://arxiv.org/abs/2407.00066},
}
Contact Information
For any comments or questions, please email Rickard Brüel Gabrielsson
- Downloads last month
- 54