{"list":"other","total":54,"rows":[{"id":"1910.10683","title":"Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer","created":"2019-10-23","cited_by_count":14599},{"id":"2009.03300","title":"Measuring Massive Multitask Language Understanding","created":"2020-09-07","cited_by_count":7963},{"id":"1803.05457","title":"Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge","created":"2018-03-14","cited_by_count":4886},{"id":"1606.05250","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","created":"2016-06-16","cited_by_count":4148},{"id":"1905.10044","title":"BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions","created":"2019-05-24","cited_by_count":2183},{"id":"1809.02789","title":"Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering","created":"2018-09-08","cited_by_count":2164},{"id":"1811.00937","title":"CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge","created":"2018-11-02","cited_by_count":1822},{"id":"1806.03822","title":"Know What You Don't Know: Unanswerable Questions for SQuAD","created":"2018-06-11","cited_by_count":1554},{"id":"1909.06146","title":"PubMedQA: A Dataset for Biomedical Research Question Answering","created":"2019-09-13","cited_by_count":1288},{"id":"2112.11446","title":"Scaling Language Models: Methods, Analysis & Insights from Training Gopher","created":"2021-12-08","cited_by_count":1202},{"id":"1903.00161","title":"DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphs","created":"2019-03-01","cited_by_count":903},{"id":"1704.04683","title":"RACE: Large-scale ReAding Comprehension Dataset From Examinations","created":"2017-04-15","cited_by_count":861},{"id":"2101.02235","title":"Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategies","created":"2021-01-06","cited_by_count":743},{"id":"2104.08773","title":"Cross-Task Generalization via Natural Language Crowdsourcing Instructions","created":"2021-04-18","cited_by_count":699},{"id":"1712.07040","title":"The NarrativeQA Reading Comprehension Challenge","created":"2017-12-19","cited_by_count":597},{"id":"2105.03011","title":"A Dataset of Information-Seeking Questions and Answers Anchored in Research Papers","created":"2021-05-07","cited_by_count":486},{"id":"2005.00700","title":"UnifiedQA: Crossing Format Boundaries With a Single QA System","created":"2020-05-02","cited_by_count":476},{"id":"1611.09830","title":"NewsQA: A Machine Comprehension Dataset","created":"2016-11-29","cited_by_count":331},{"id":"2010.01057","title":"LUKE: Deep Contextualized Entity Representations with Entity-aware Self-attention","created":"2020-10-02","cited_by_count":326},{"id":"1909.00277","title":"Cosmos QA: Machine Reading Comprehension with Contextual Commonsense Reasoning","created":"2019-08-31","cited_by_count":285},{"id":"1912.09713","title":"Measuring Compositional Generalization: A Comprehensive Method on Realistic Data","created":"2019-12-20","cited_by_count":284},{"id":"2107.02137","title":"ERNIE 3.0: Large-scale Knowledge Enhanced Pre-training for Language Understanding and Generation","created":"2021-07-05","cited_by_count":260},{"id":"1910.11473","title":"QASC: A Dataset for Question Answering via Sentence Composition","created":"2019-10-25","cited_by_count":252},{"id":"2002.04326","title":"ReClor: A Reading Comprehension Dataset Requiring Logical Reasoning","created":"2020-02-11","cited_by_count":217},{"id":"1907.10641","title":"WinoGrande: An Adversarial Winograd Schema Challenge at Scale","created":"2019-07-24","cited_by_count":204},{"id":"1810.12885","title":"ReCoRD: Bridging the Gap between Human and Machine Commonsense Reading Comprehension","created":"2018-10-30","cited_by_count":200},{"id":"2101.11038","title":"Muppet: Massive Multi-task Representations with Pre-Finetuning","created":"2021-01-26","cited_by_count":192},{"id":"2011.07743","title":"Beyond I.I.D.: Three Levels of Generalization for Question Answering on Knowledge Bases","created":"2020-11-16","cited_by_count":171},{"id":"2110.07814","title":"Meta-learning via Language Model In-context Tuning","created":"2021-10-15","cited_by_count":164},{"id":"2111.10952","title":"ExT5: Towards Extreme Multi-Task Scaling for Transfer Learning","created":"2021-11-22","cited_by_count":161},{"id":"1902.00164","title":"DREAM: A Challenge Dataset and Models for Dialogue-Based Reading Comprehension","created":"2019-02-01","cited_by_count":156},{"id":"2002.00293","title":"Beat the AI: Investigating Adversarial Human Annotation for Reading Comprehension","created":"2020-02-02","cited_by_count":131},{"id":"2104.04670","title":"Adapting Language Models for Zero-shot Learning by Meta-tuning on Dataset and Prompt Collections","created":"2021-04-10","cited_by_count":128},{"id":"1906.04701","title":"HEAD-QA: A Healthcare Dataset for Complex Reasoning","created":"2019-06-11","cited_by_count":101},{"id":"1908.05803","title":"Quoref: A Reading Comprehension Dataset with Questions Requiring Coreferential Reasoning","created":"2019-08-16","cited_by_count":100},{"id":"2103.13009","title":"UNICORN on RAINBOW: A Universal Commonsense Reasoning Model on a New Multitask Benchmark","created":"2021-03-24","cited_by_count":98},{"id":"2001.09694","title":"Retrospective Reader for Machine Reading Comprehension","created":"2020-01-27","cited_by_count":86},{"id":"1908.05852","title":"Reasoning Over Paragraph Effects in Situations","created":"2019-08-16","cited_by_count":79},{"id":"2107.07170","title":"FLEX: Unifying Evaluation for Few-Shot NLP","created":"2021-07-15","cited_by_count":67},{"id":"1907.06292","title":"TWEETQA: A Social Media Focused Question Answering Dataset","created":"2019-07-14","cited_by_count":55},{"id":"2104.08727","title":"GooAQ: Open Question Answering with Diverse Answer Types","created":"2021-04-18","cited_by_count":53},{"id":"2106.03634","title":"PROST: Physical Reasoning of Objects through Space and Time","created":"2021-06-07","cited_by_count":48},{"id":"2104.00743","title":"Towards General Purpose Vision Systems","created":"2021-04-01","cited_by_count":46},{"id":"2109.02593","title":"General-Purpose Question-Answering with Macaw","created":"2021-09-06","cited_by_count":40},{"id":"1803.05223","title":"MCScript: A Novel Dataset for Assessing Machine Comprehension Using Script Knowledge","created":"2018-03-14","cited_by_count":30},{"id":"2201.05899","title":"Unobserved Local Structures Make Compositional Generalization Hard","created":"2022-01-15","cited_by_count":29},{"id":"1905.09531","title":"MCScript2.0: A Machine Comprehension Corpus Focused on Script Events and Participants","created":"2019-05-23","cited_by_count":20},{"id":"2004.14797","title":"STARC: Structured Annotations for Reading Comprehension","created":"2020-04-30","cited_by_count":17},{"id":"2105.06912","title":"QAConv: Question Answering on Informative Conversations","created":"2021-05-14","cited_by_count":17},{"id":"1902.00993","title":"Improving Question Answering with External Knowledge","created":"2019-02-03","cited_by_count":16},{"id":"2109.13880","title":"Single-dataset Experts for Multi-dataset Question Answering","created":"2021-09-28","cited_by_count":15},{"id":"1901.02262","title":"Multi-style Generative Reading Comprehension","created":"2019-01-08","cited_by_count":14},{"id":"2008.02434","title":"Interpretable Multi-Step Reasoning with Knowledge Extraction on Complex Healthcare Question Answering","created":"2020-08-06","cited_by_count":7},{"id":"2011.03292","title":"Improving Machine Reading Comprehension with Single-choice Decision and Transfer Learning","created":"2020-11-06","cited_by_count":7}],"next_cursor":null}