The Natural Questions corpus is a question answering dataset containing 307,373 training examples, 7,830 development examples, and 7,842 test examples. Each example is comprised of a google.com query and a corresponding Wikipedia page. Each Wikipedia page has a passage (or long answer) annotated on the page that answers the question and one or more short spans from the annotated passage containing the actual answer. The long and the short answer annotations can however be empty. If they are both empty, then there is no answer on the page at all. If the long answer annotation is non-empty, but the short answer annotation is empty, then the annotated passage answers the question but no explicit short answer could be found. Finally 1% of the documents have a passage annotated with a short answer that is “yes” or “no”, instead of a list of short spans.
1,025 PAPERS • 8 BENCHMARKS
The MS MARCO (Microsoft MAchine Reading Comprehension) is a collection of datasets focused on deep learning in search. The first dataset was a question answering dataset featuring 100,000 real Bing questions and a human generated answer. Over time the collection was extended with a 1,000,000 question dataset, a natural language generation dataset, a passage ranking dataset, keyphrase extraction dataset, crawling dataset, and a conversational search.
834 PAPERS • 7 BENCHMARKS
TriviaQA is a realistic text-based question answering dataset which includes 950K question-answer pairs from 662K documents collected from Wikipedia and the web. This dataset is more challenging than standard QA benchmark datasets such as Stanford Question Answering Dataset (SQuAD), as the answers for a question may not be directly obtained by span prediction and the context is very long. TriviaQA dataset consists of both human-verified and machine-generated QA subsets.
643 PAPERS • 4 BENCHMARKS
HotpotQA is a question answering dataset collected on the English Wikipedia, containing about 113K crowd-sourced questions that are constructed to require the introduction paragraphs of two Wikipedia articles to answer. Each question in the dataset comes with the two gold paragraphs, as well as a list of sentences in these paragraphs that crowdworkers identify as supporting facts necessary to answer the question.
571 PAPERS • 1 BENCHMARK
CNN/Daily Mail is a dataset for text summarization. Human generated abstractive summary bullets were generated from news stories in CNN and Daily Mail websites as questions (with one of the entities hidden), and stories as the corresponding passages from which the system is expected to answer the fill-in the-blank question. The authors released the scripts that crawl, extract and generate pairs of passages and questions from these websites.
469 PAPERS • 10 BENCHMARKS
BoolQ is a question answering dataset for yes/no questions containing 15942 examples. These questions are naturally occurring – they are generated in unprompted and unconstrained settings. Each example is a triplet of (question, passage, answer), with the title of the page as optional additional context.
412 PAPERS • 1 BENCHMARK
The ReAding Comprehension dataset from Examinations (RACE) dataset is a machine reading comprehension dataset consisting of 27,933 passages and 97,867 questions from English exams, targeting Chinese students aged 12-18. RACE consists of two subsets, RACE-M and RACE-H, from middle school and high school exams, respectively. RACE-M has 28,293 questions and RACE-H has 69,574. Each question is associated with 4 candidate answers, one of which is correct. The data generation process of RACE differs from most machine reading comprehension datasets - instead of generating questions and answers by heuristics or crowd-sourcing, questions in RACE are specifically designed for testing human reading skills, and are created by domain experts.
355 PAPERS • 3 BENCHMARKS
OpenBookQA is a new kind of question-answering dataset modeled after open book exams for assessing human understanding of a subject. It consists of 5,957 multiple-choice elementary-level science questions (4,957 train, 500 dev, 500 test), which probe the understanding of a small “book” of 1,326 core science facts and the application of these facts to novel situations. For training, the dataset includes a mapping from each question to the core science fact it was designed to probe. Answering OpenBookQA questions requires additional broad common knowledge, not contained in the book. The questions, by design, are answered incorrectly by both a retrieval-based algorithm and a word co-occurrence algorithm. Additionally, the dataset includes a collection of 5,167 crowd-sourced common knowledge facts, and an expanded version of the train/dev/test questions where each question is associated with its originating core fact, a human accuracy score, a clarity score, and an anonymized crowd-worker
353 PAPERS • 2 BENCHMARKS
Automatic image captioning is the task of producing a natural-language utterance (usually a sentence) that correctly reflects the visual content of an image. Up to this point, the resource most used for this task was the MS-COCO dataset, containing around 120,000 images and 5-way image-caption annotations (produced by paid annotators).
314 PAPERS • 2 BENCHMARKS
Discrete Reasoning Over Paragraphs DROP is a crowdsourced, adversarially-created, 96k-question benchmark, in which a system must resolve references in a question, perhaps to multiple input positions, and perform discrete operations over them (such as addition, counting, or sorting). These operations require a much more comprehensive understanding of the content of paragraphs than what was necessary for prior datasets. The questions consist of passages extracted from Wikipedia articles. The dataset is split into a training set of about 77,000 questions, a development set of around 9,500 questions and a hidden test set similar in size to the development set.
297 PAPERS • 2 BENCHMARKS
The Choice Of Plausible Alternatives (COPA) evaluation provides researchers with a tool for assessing progress in open-domain commonsense causal reasoning. COPA consists of 1000 questions, split equally into development and test sets of 500 questions each. Each question is composed of a premise and two alternatives, where the task is to select the alternative that more plausibly has a causal relation with the premise. The correct alternative is randomized so that the expected performance of randomly guessing is 50%.
287 PAPERS • 1 BENCHMARK
Outside Knowledge Visual Question Answering (OK-VQA) includes more than 14,000 questions that require external knowledge to answer.
261 PAPERS • 2 BENCHMARKS
The NewsQA dataset is a crowd-sourced machine reading comprehension dataset of 120,000 question-answer pairs.
250 PAPERS • 1 BENCHMARK
CoQA is a large-scale dataset for building Conversational Question Answering systems. The goal of the CoQA challenge is to measure the ability of machines to understand a text passage and answer a series of interconnected questions that appear in a conversation.
229 PAPERS • 2 BENCHMARKS
BEIR (Benchmarking IR) is a heterogeneous benchmark containing different information retrieval (IR) tasks. Through BEIR, it is possible to systematically study the zero-shot generalization capabilities of multiple neural retrieval approaches.
206 PAPERS • 19 BENCHMARKS
The WebQuestions dataset is a question answering dataset using Freebase as the knowledge base and contains 6,642 question-answer pairs. It was created by crawling questions through the Google Suggest API, and then obtaining answers using Amazon Mechanical Turk. The original split uses 3,778 examples for training and 2,032 for testing. All answers are defined as Freebase entities.
202 PAPERS • 3 BENCHMARKS
The WikiQA corpus is a publicly available set of question and sentence pairs, collected and annotated for research on open-domain question answering. In order to reflect the true information need of general users, Bing query logs were used as the question source. Each question is linked to a Wikipedia page that potentially has the answer. Because the summary section of a Wikipedia page provides the basic and usually most important information about the topic, sentences in this section were used as the candidate answers. The corpus includes 3,047 questions and 29,258 sentences, where 1,473 sentences were labeled as answer sentences to their corresponding questions.
190 PAPERS • 2 BENCHMARKS
StrategyQA is a question answering benchmark where the required reasoning steps are implicit in the question, and should be inferred using a strategy. It includes 2,780 examples, each consisting of a strategy question, its decomposition, and evidence paragraphs. Questions in StrategyQA are short, topic-diverse, and cover a wide range of strategies.
179 PAPERS • 1 BENCHMARK
Question Answering in Context is a large-scale dataset that consists of around 14K crowdsourced Question Answering dialogs with 98K question-answer pairs in total. Data instances consist of an interactive dialog between two crowd workers: (1) a student who poses a sequence of freeform questions to learn as much as possible about a hidden Wikipedia text, and (2) a teacher who answers the questions by providing short excerpts (spans) from the text.
165 PAPERS • 1 BENCHMARK
ATOMIC is an atlas of everyday commonsense reasoning, organized through 877k textual descriptions of inferential knowledge. Compared to existing resources that center around taxonomic knowledge, ATOMIC focuses on inferential knowledge organized as typed if-then relations with variables (e.g., "if X pays Y a compliment, then Y will likely return the compliment").
162 PAPERS • NO BENCHMARKS YET
MLQA (MultiLingual Question Answering) is a benchmark dataset for evaluating cross-lingual question answering performance. MLQA consists of over 5K extractive QA instances (12K in English) in SQuAD format in seven languages - English, Arabic, German, Spanish, Hindi, Vietnamese and Simplified Chinese. MLQA is highly parallel, with QA instances parallel between 4 different languages on average.
153 PAPERS • 1 BENCHMARK
The NarrativeQA dataset includes a list of documents with Wikipedia summaries, links to full stories, and questions and answers.
147 PAPERS • 1 BENCHMARK
Science Question Answering (ScienceQA) is a new benchmark that consists of 21,208 multimodal multiple choice questions with diverse science topics and annotations of their answers with corresponding lectures and explanations. Out of the questions in ScienceQA, 10,332 (48.7%) have an image context, 10,220 (48.2%) have a text context, and 6,532 (30.8%) have both. Most questions are annotated with grounded lectures (83.9%) and detailed explanations (90.5%). The lecture and explanation provide general external knowledge and specific reasons, respectively, for arriving at the correct answer. To the best of our knowledge, ScienceQA is the first large-scale multimodal dataset that annotates lectures and explanations for the answers.
Visual Dialog (VisDial) dataset contains human annotated questions based on images of MS COCO dataset. This dataset was developed by pairing two subjects on Amazon Mechanical Turk to chat about an image. One person was assigned the job of a ‘questioner’ and the other person acted as an ‘answerer’. The questioner sees only the text description of an image (i.e., an image caption from MS COCO dataset) and the original image remains hidden to the questioner. Their task is to ask questions about this hidden image to “imagine the scene better”. The answerer sees the image, caption and answers the questions asked by the questioner. The two of them can continue the conversation by asking and answering questions for 10 rounds at max.
144 PAPERS • 6 BENCHMARKS
MultiRC (Multi-Sentence Reading Comprehension) is a dataset of short paragraphs and multi-sentence questions, i.e., questions that can be answered by combining information from multiple sentences of the paragraph. The dataset was designed with three key challenges in mind: * The number of correct answer-options for each question is not pre-specified. This removes the over-reliance on answer-options and forces them to decide on the correctness of each candidate answer independently of others. In other words, the task is not to simply identify the best answer-option, but to evaluate the correctness of each answer-option individually. * The correct answer(s) is not required to be a span in the text. * The paragraphs in the dataset have diverse provenance by being extracted from 7 different domains such as news, fiction, historical text etc., and hence are expected to be more diverse in their contents as compared to single-domain datasets. The entire corpus consists of around 10K questions
143 PAPERS • 1 BENCHMARK
Given a partial description like "she opened the hood of the car," humans can reason about the situation and anticipate what might come next ("then, she examined the engine"). SWAG (Situations With Adversarial Generations) is a large-scale dataset for this task of grounded commonsense inference, unifying natural language inference and physically grounded reasoning.
143 PAPERS • 2 BENCHMARKS
e-SNLI is used for various goals, such as obtaining full sentence justifications of a model's decisions, improving universal sentence representations and transferring to out-of-domain NLI datasets.
126 PAPERS • 1 BENCHMARK
MCTest is a freely available set of stories and associated questions intended for research on the machine comprehension of text.
113 PAPERS • 2 BENCHMARKS
The MRQA (Machine Reading for Question Answering) dataset is a dataset for evaluating the generalization capabilities of reading comprehension systems.
113 PAPERS • 1 BENCHMARK
SimpleQuestions is a large-scale factoid question answering dataset. It consists of 108,442 natural language questions, each paired with a corresponding fact from Freebase knowledge base. Each fact is a triple (subject, relation, object) and the answer to the question is always the object. The dataset is divided into training, validation, and test sets with 75,910, 10,845 and 21,687 questions respectively.
SHAPES is a dataset of synthetic images designed to benchmark systems for understanding of spatial and logical relations among multiple objects. The dataset consists of complex questions about arrangements of colored shapes. The questions are built around compositions of concepts and relations, e.g. Is there a red shape above a circle? or Is a red shape blue?. Questions contain between two and four attributes, object types, or relationships. There are 244 questions and 15,616 images in total, with all questions having a yes and no answer (and corresponding supporting image). This eliminates the risk of learning biases.
112 PAPERS • 1 BENCHMARK
The ActivityNet-QA dataset contains 58,000 human-annotated QA pairs on 5,800 videos derived from the popular ActivityNet dataset. The dataset provides a benchmark for testing the performance of VideoQA models on long-term spatio-temporal reasoning.
91 PAPERS • 2 BENCHMARKS
Children’s Book Test (CBT) is designed to measure directly how well language models can exploit wider linguistic context. The CBT is built from books that are freely available thanks to Project Gutenberg.
90 PAPERS • 2 BENCHMARKS
CosmosQA is a large-scale dataset of 35.6K problems that require commonsense-based reading comprehension, formulated as multiple-choice questions. It focuses on reading between the lines over a diverse collection of people’s everyday narratives, asking questions concerning on the likely causes or effects of events that require reasoning beyond the exact text spans in the context.
89 PAPERS • NO BENCHMARKS YET
NExT-QA is a VideoQA benchmark targeting the explanation of video contents. It challenges QA models to reason about the causal and temporal actions and understand the rich object interactions in daily activities. It supports both multi-choice and open-ended QA tasks. The videos are untrimmed and the questions usually invoke local video contents for answers.
84 PAPERS • 5 BENCHMARKS
ST-VQA aims to highlight the importance of exploiting high-level semantic information present in images as textual cues in the VQA process.
74 PAPERS • NO BENCHMARKS YET
GuessWhat?! is a large-scale dataset consisting of 150K human-played games with a total of 800K visual question-answer pairs on 66K images.
73 PAPERS • NO BENCHMARKS YET
WikiHop is a multi-hop question-answering dataset. The query of WikiHop is constructed with entities and relations from WikiData, while supporting documents are from WikiReading. A bipartite graph connecting entities and documents is first built and the answer for each query is located by traversal on this graph. Candidates that are type-consistent with the answer and share the same relation in query with the answer are included, resulting in a set of candidates. Thus, WikiHop is a multi-choice style reading comprehension data set. There are totally about 43K samples in training set, 5K samples in development set and 2.5K samples in test set. The test set is not provided. The task is to predict the correct answer given a query and multiple supporting documents.
67 PAPERS • 2 BENCHMARKS
CANARD is a dataset for question-in-context rewriting that consists of questions each given in a dialog context together with a context-independent rewriting of the question. The context of each question is the dialog utterences that precede the question. CANARD can be used to evaluate question rewriting models that handle important linguistic phenomena such as coreference and ellipsis resolution.
56 PAPERS • 1 BENCHMARK
ComplexWebQuestions is a dataset for answering complex questions that require reasoning over multiple web snippets. It contains a large set of complex questions in natural language, and can be used in multiple ways:
55 PAPERS • 2 BENCHMARKS
QASPER is a dataset for question answering on scientific research papers. It consists of 5,049 questions over 1,585 Natural Language Processing papers. Each question is written by an NLP practitioner who read only the title and abstract of the corresponding paper, and the question seeks information present in the full text. The questions are then answered by a separate set of NLP practitioners who also provide supporting evidence to answers.
53 PAPERS • 2 BENCHMARKS
QUASAR-T is a large-scale dataset aimed at evaluating systems designed to comprehend a natural language query and extract its answer from a large corpus of text. It consists of 43,013 open-domain trivia questions and their answers obtained from various internet sources. ClueWeb09 serves as the background corpus for extracting these answers. The answers to these questions are free-form spans of text, though most are noun phrases.
Quora Question Pairs (QQP) dataset consists of over 400,000 question pairs, and each question pair is annotated with a binary value indicating whether the two questions are paraphrase of each other.
53 PAPERS • 8 BENCHMARKS
TAT-QA (Tabular And Textual dataset for Question Answering) is a large-scale QA dataset, aiming to stimulate progress of QA research over more complex and realistic tabular and textual data, especially those requiring numerical reasoning.
53 PAPERS • 1 BENCHMARK
Delta Reading Comprehension Dataset (DRCD) is an open domain traditional Chinese machine reading comprehension (MRC) dataset. This dataset aimed to be a standard Chinese machine reading comprehension dataset, which can be a source dataset in transfer learning. The dataset contains 10,014 paragraphs from 2,108 Wikipedia articles and 30,000+ questions generated by annotators.
52 PAPERS • 5 BENCHMARKS
CoS-E consists of human explanations for commonsense reasoning in the form of natural language sequences and highlighted annotations
45 PAPERS • NO BENCHMARKS YET
The Question Answering by Search And Reading (QUASAR) is a large-scale dataset consisting of QUASAR-S and QUASAR-T. Each of these datasets is built to focus on evaluating systems devised to understand a natural language query, a large corpus of texts and to extract an answer to the question from the corpus. Specifically, QUASAR-S comprises 37,012 fill-in-the-gaps questions that are collected from the popular website Stack Overflow using entity tags. The QUASAR-T dataset contains 43,012 open-domain questions collected from various internet sources. The candidate documents for each question in this dataset are retrieved from an Apache Lucene based search engine built on top of the ClueWeb09 dataset.
45 PAPERS • 1 BENCHMARK
QReCC contains 14K conversations with 81K question-answer pairs. QReCC is built on questions from TREC CAsT, QuAC and Google Natural Questions. While TREC CAsT and QuAC datasets contain multi-turn conversations, Natural Questions is not a conversational dataset. Questions in NQ dataset were used as prompts to create conversations explicitly balancing types of context-dependent questions, such as anaphora (co-references) and ellipsis.
44 PAPERS • NO BENCHMARKS YET