{"url":"/task/reading-comprehension","name":"Reading Comprehension","slug":"reading-comprehension","description_markdown":"Most current question answering datasets frame the task as reading comprehension where the question is about a paragraph or document and the answer often is a span in the document. \r\n\r\nSome specific tasks of reading comprehension include multi-modal machine reading comprehension and textual machine reading comprehension, among others. In the literature, machine reading comprehension can be divide into four categories: **cloze style**, **multiple choice**, **span prediction**, and **free-form answer**.  Read more about each category [here](https://paperswithcode.com/paper/a-survey-on-machine-reading-comprehension-1).\r\n\r\nBenchmark datasets used for testing a model's reading comprehension abilities include [MovieQA](/dataset/movieqa), [ReCoRD](dataset/record), and [RACE](/dataset/race), among others.\r\n\r\nThe Machine Reading group at UCL also provides an [overview of reading comprehension tasks](https://uclnlp.github.io/ai4exams/data.html).\r\n\r\nFigure source: [A Survey on Machine Reading Comprehension: Tasks, Evaluation Metrics and Benchmark Datasets](https://arxiv.org/pdf/2006.11880.pdf)","categories":[{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":1760,"papers_with_code":634,"benchmarks":7,"benchmark_tables_in_archive":7,"benchmark_tables_shown":7,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":95,"subtasks":20,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/reading-comprehension-on-reclor","slug":"reading-comprehension-on-reclor","dataset":"ReClor","dataset_url":"/dataset/reclor","rows_in_archive":39,"metrics":["Test"],"first_row_in_archive_order":{"model":"Rational Reasoner / IDOL","paper_title":"IDOL: Indicator-oriented Logic Pre-training for Logical Reasoning","paper_url":"/paper/idol-indicator-oriented-logic-pre-training","paper_date":"2023-06-27","arxiv_id":"2306.15273","code_links":[{"title":"GeekDream-x/IDOL","url":"https://github.com/GeekDream-x/IDOL"}],"syntology":null}},{"leaderboard":"/sota/reading-comprehension-on-race","slug":"reading-comprehension-on-race","dataset":"RACE","dataset_url":"/dataset/race","rows_in_archive":24,"metrics":["Accuracy","Accuracy (Middle)","Accuracy (High)"],"first_row_in_archive_order":{"model":"ALBERT (Ensemble)","paper_title":"Improving Machine Reading Comprehension with Single-choice Decision and Transfer Learning","paper_url":"/paper/improving-machine-reading-comprehension-with-2","paper_date":"2020-11-06","arxiv_id":"2011.03292","code_links":[],"syntology":null}},{"leaderboard":"/sota/reading-comprehension-on-muserc","slug":"reading-comprehension-on-muserc","dataset":"MuSeRC","dataset_url":"/dataset/muserc","rows_in_archive":22,"metrics":["Average F1","EM "],"first_row_in_archive_order":{"model":"Golden Transformer","paper_title":null,"paper_url":null,"paper_date":"","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/reading-comprehension-on-adversarialqa","slug":"reading-comprehension-on-adversarialqa","dataset":"AdversarialQA","dataset_url":"/dataset/adversarialqa","rows_in_archive":3,"metrics":["Overall: F1","D(BiDAF): F1","D(BERT): F1","D(RoBERTa): F1"],"first_row_in_archive_order":{"model":"RoBERTa-Large","paper_title":"Beat the AI: Investigating Adversarial Human Annotation for Reading Comprehension","paper_url":"/paper/beat-the-ai-investigating-adversarial-human","paper_date":"2020-02-02","arxiv_id":"2002.00293","code_links":[{"title":"maxbartolo/adversarialQA","url":"https://github.com/maxbartolo/adversarialQA"}],"syntology":null}},{"leaderboard":"/sota/reading-comprehension-on-crowdsource-qa-1","slug":"reading-comprehension-on-crowdsource-qa-1","dataset":"CrowdSource QA","dataset_url":null,"rows_in_archive":1,"metrics":["MSE"],"first_row_in_archive_order":{"model":"BERT","paper_title":"Predicting Subjective Features of Questions of QA Websites using BERT","paper_url":"/paper/predicting-subjective-features-from-questions","paper_date":"2020-02-24","arxiv_id":"2002.10107","code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers"},{"title":"tensorflow/models","url":"https://github.com/tensorflow/models/tree/master/official/nlp"},{"title":"google-research/bert","url":"https://github.com/google-research/bert"},{"title":"graykode/nlp-tutorial","url":"https://github.com/graykode/nlp-tutorial"},{"title":"Moradnejad/Predicting-Subjective-Features-on-QA-Websites","url":"https://github.com/Moradnejad/Predicting-Subjective-Features-on-QA-Websites"}],"syntology":null}},{"leaderboard":"/sota/reading-comprehension-on-radqa","slug":"reading-comprehension-on-radqa","dataset":"RadQA","dataset_url":"/dataset/radqa","rows_in_archive":1,"metrics":["Answer F1"],"first_row_in_archive_order":{"model":"BERT pretrained on MIMIC-III","paper_title":"RadQA: A Question Answering Dataset to Improve Comprehension of Radiology Reports","paper_url":"/paper/radqa-a-question-answering-dataset-to-improve","paper_date":"","arxiv_id":null,"code_links":[],"syntology":null}},{"leaderboard":"/sota/reading-comprehension-on-recam","slug":"reading-comprehension-on-recam","dataset":"ReCAM","dataset_url":"/dataset/recam","rows_in_archive":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"NAL","paper_title":"ZJUKLAB at SemEval-2021 Task 4: Negative Augmentation with Language Model for Reading Comprehension of Abstract Meaning","paper_url":"/paper/zjuklab-at-semeval-2021-task-4-negative","paper_date":"2021-02-25","arxiv_id":"2102.12828","code_links":[{"title":"zjunlp/SemEval2021Task4","url":"https://github.com/zjunlp/SemEval2021Task4"}],"syntology":null}}],"datasets":[{"url":"/dataset/ms-marco","name":"MS MARCO","full_name":"Microsoft Machine Reading Comprehension Dataset","num_papers_in_archive":1036},{"url":"/dataset/triviaqa","name":"TriviaQA","full_name":"","num_papers_in_archive":953},{"url":"/dataset/hotpotqa","name":"HotpotQA","full_name":"","num_papers_in_archive":933},{"url":"/dataset/race","name":"RACE","full_name":"ReAding Comprehension dataset from Examinations","num_papers_in_archive":412},{"url":"/dataset/docvqa","name":"DocVQA","full_name":"","num_papers_in_archive":290},{"url":"/dataset/coqa","name":"CoQA","full_name":"Conversational Question Answering Challenge","num_papers_in_archive":281},{"url":"/dataset/newsqa","name":"NewsQA","full_name":"","num_papers_in_archive":272},{"url":"/dataset/narrativeqa","name":"NarrativeQA","full_name":"NarrativeQA","num_papers_in_archive":206},{"url":"/dataset/xquad","name":"XQuAD","full_name":"XQuAD","num_papers_in_archive":190},{"url":"/dataset/sciq","name":"SciQ","full_name":"SciQ","num_papers_in_archive":183},{"url":"/dataset/quac","name":"QuAC","full_name":"Question Answering in Context","num_papers_in_archive":178},{"url":"/dataset/multirc","name":"MultiRC","full_name":"Multi-Sentence Reading Comprehension","num_papers_in_archive":162},{"url":"/dataset/squad","name":"SQuAD","full_name":"Stanford Question Answering Dataset","num_papers_in_archive":151},{"url":"/dataset/tydi-qa","name":"TyDiQA","full_name":"Typologically Diverse Question Answering","num_papers_in_archive":148},{"url":"/dataset/pg-19","name":"PG-19","full_name":"","num_papers_in_archive":147},{"url":"/dataset/mrqa-2019","name":"MRQA","full_name":"","num_papers_in_archive":116},{"url":"/dataset/mctest","name":"MCTest","full_name":"","num_papers_in_archive":114},{"url":"/dataset/qasc","name":"QASC","full_name":"Question Answering via Sentence Composition","num_papers_in_archive":114},{"url":"/dataset/cosmosqa","name":"CosmosQA","full_name":"","num_papers_in_archive":102},{"url":"/dataset/clue","name":"CLUE","full_name":"Chinese Language Understanding Evaluation Benchmark","num_papers_in_archive":99},{"url":"/dataset/cbt","name":"CBT","full_name":"Children’s Book Test","num_papers_in_archive":92},{"url":"/dataset/reclor","name":"ReClor","full_name":"","num_papers_in_archive":88},{"url":"/dataset/opus-100","name":"OPUS-100","full_name":"","num_papers_in_archive":78},{"url":"/dataset/cmrc","name":"CMRC","full_name":"Chinese Machine Reading Comprehension","num_papers_in_archive":69},{"url":"/dataset/belebele","name":"Belebele","full_name":"","num_papers_in_archive":68},{"url":"/dataset/dream","name":"DREAM","full_name":"","num_papers_in_archive":68},{"url":"/dataset/dureader","name":"DuReader","full_name":"","num_papers_in_archive":65},{"url":"/dataset/c3","name":"C3","full_name":"","num_papers_in_archive":54},{"url":"/dataset/drcd","name":"DRCD","full_name":"Delta Reading Comprehension Dataset","num_papers_in_archive":53},{"url":"/dataset/qrecc","name":"QReCC","full_name":"","num_papers_in_archive":51},{"url":"/dataset/emrqa","name":"emrQA","full_name":"","num_papers_in_archive":50},{"url":"/dataset/nombank","name":"NomBank","full_name":"NomBank","num_papers_in_archive":50},{"url":"/dataset/quoref","name":"Quoref","full_name":"Quoref","num_papers_in_archive":50},{"url":"/dataset/cmrc-2018","name":"CMRC 2018","full_name":"Chinese Machine Reading Comprehension 2018","num_papers_in_archive":49},{"url":"/dataset/tqa","name":"TQA","full_name":"Textbook Question Answering","num_papers_in_archive":48},{"url":"/dataset/quasar-1","name":"QUASAR","full_name":"QUestion Answering by Search And Reading","num_papers_in_archive":47},{"url":"/dataset/cos-e","name":"CoS-E","full_name":"Commonsense Explanations Dataset","num_papers_in_archive":46},{"url":"/dataset/sharc","name":"ShARC","full_name":"Shaping Answers with Rules through Conversation","num_papers_in_archive":43},{"url":"/dataset/duorc","name":"DuoRC","full_name":"DuoRC","num_papers_in_archive":42},{"url":"/dataset/wikimovies","name":"WikiMovies","full_name":"","num_papers_in_archive":39},{"url":"/dataset/chid","name":"ChID","full_name":"Chinese IDiom dataset","num_papers_in_archive":38},{"url":"/dataset/propara","name":"ProPara","full_name":"","num_papers_in_archive":34},{"url":"/dataset/worldtree","name":"Worldtree","full_name":"","num_papers_in_archive":32},{"url":"/dataset/holl-e","name":"Holl-E","full_name":"","num_papers_in_archive":30},{"url":"/dataset/molweni","name":"Molweni","full_name":"","num_papers_in_archive":29},{"url":"/dataset/adversarialqa","name":"AdversarialQA","full_name":"","num_papers_in_archive":26},{"url":"/dataset/iirc","name":"IIRC","full_name":"Incomplete Information Reading Comprehension","num_papers_in_archive":26},{"url":"/dataset/wikireading","name":"WikiReading","full_name":"","num_papers_in_archive":26},{"url":"/dataset/mcscript","name":"MCScript","full_name":"MCScript","num_papers_in_archive":24},{"url":"/dataset/ropes","name":"ROPES","full_name":"Reasoning Over Paragraph Effects in Situations","num_papers_in_archive":24},{"url":"/dataset/spoken-squad","name":"Spoken-SQuAD","full_name":null,"num_papers_in_archive":24},{"url":"/dataset/booktest","name":"BookTest","full_name":"","num_papers_in_archive":22},{"url":"/dataset/clicr","name":"CliCR","full_name":"CliCR","num_papers_in_archive":21},{"url":"/dataset/cloth","name":"CLOTH","full_name":"CLOze test by TeacHers","num_papers_in_archive":20},{"url":"/dataset/wikisection","name":"WikiSection","full_name":"","num_papers_in_archive":17},{"url":"/dataset/uit-viquad","name":"UIT-ViQuAD","full_name":"","num_papers_in_archive":15},{"url":"/dataset/medhop","name":"MedHop","full_name":"MedHop","num_papers_in_archive":14},{"url":"/dataset/biomrc","name":"BIOMRC","full_name":"","num_papers_in_archive":13},{"url":"/dataset/inquisitive","name":"INQUISITIVE","full_name":"","num_papers_in_archive":13},{"url":"/dataset/jec-qa","name":"JEC-QA","full_name":"","num_papers_in_archive":13},{"url":"/dataset/sara","name":"SARA","full_name":"StAtutory Reasoning Assessment","num_papers_in_archive":13},{"url":"/dataset/who-did-what","name":"Who-did-What","full_name":"Who did What","num_papers_in_archive":13},{"url":"/dataset/policyqa","name":"PolicyQA","full_name":"","num_papers_in_archive":12},{"url":"/dataset/cmrc-2017","name":"CMRC 2017","full_name":"Chinese Machine Reading Comprehension 2017","num_papers_in_archive":11},{"url":"/dataset/recam","name":"ReCAM","full_name":"SemEval-2021 Task 4: Reading Comprehension of Abstract Meaning","num_papers_in_archive":11},{"url":"/dataset/sberquad","name":"SberQuAD","full_name":"Sberbank Question Answering Dataset","num_papers_in_archive":10},{"url":"/dataset/radqa","name":"RadQA","full_name":"A Question Answering Dataset to Improve Comprehension of Radiology Reports","num_papers_in_archive":9},{"url":"/dataset/cmrc-2019","name":"CMRC 2019","full_name":"Chinese Machine Reading Comprehension 2019","num_papers_in_archive":8},{"url":"/dataset/quasar-s","name":"QUASAR-S","full_name":"QUestion Answering by Search And Reading – Stack Overflow","num_papers_in_archive":8},{"url":"/dataset/russe","name":"RUSSE","full_name":"Russian Words in Context (based on RUSSE)","num_papers_in_archive":8},{"url":"/dataset/vmsmo","name":"VMSMO","full_name":null,"num_papers_in_archive":8},{"url":"/dataset/vnhsge","name":"VNHSGE","full_name":"VietNamese High School Graduation Examination Dataset for Large Language Models","num_papers_in_archive":7},{"url":"/dataset/bipar","name":"BiPaR","full_name":"BiPaR","num_papers_in_archive":6},{"url":"/dataset/muserc","name":"MuSeRC","full_name":"Russian Multi-Sentence Reading Comprehension","num_papers_in_archive":6},{"url":"/dataset/xqa","name":"XQA","full_name":"XQA","num_papers_in_archive":6},{"url":"/dataset/mocha","name":"MOCHA","full_name":"","num_papers_in_archive":5},{"url":"/dataset/onestopqa","name":"OneStopQA","full_name":"","num_papers_in_archive":5},{"url":"/dataset/taiga-corpus","name":"Taiga Corpus","full_name":"An open-source corpus for machine learning.","num_papers_in_archive":5},{"url":"/dataset/uit-vinewsqa","name":"UIT-ViNewsQA","full_name":"","num_papers_in_archive":5},{"url":"/dataset/simran-arora","name":"ConcurrentQA Benchmark","full_name":"","num_papers_in_archive":3},{"url":"/dataset/cs","name":"CS","full_name":"Chinese Simile","num_papers_in_archive":3},{"url":"/dataset/dmqa","name":"DMQA","full_name":"DeepMind Q&A","num_papers_in_archive":3},{"url":"/dataset/shmoop-corpus","name":"Shmoop Corpus","full_name":"","num_papers_in_archive":3},{"url":"/dataset/bulgarian-reading-comprehension-dataset","name":"Bulgarian Reading Comprehension Dataset","full_name":"","num_papers_in_archive":2},{"url":"/dataset/codequeries","name":"CodeQueries","full_name":"","num_papers_in_archive":2},{"url":"/dataset/mc-afp","name":"MC-AFP","full_name":"","num_papers_in_archive":2},{"url":"/dataset/wikireading-recycled","name":"WikiReading Recycled","full_name":"","num_papers_in_archive":2},{"url":"/dataset/x-wikire","name":"X-WikiRE","full_name":"X-WikiRE","num_papers_in_archive":2},{"url":"/dataset/idk-mrc","name":"IDK-MRC","full_name":"","num_papers_in_archive":1},{"url":"/dataset/jecc","name":"JECC","full_name":"Jericho Environment Commonsense Comprehension","num_papers_in_archive":1},{"url":"/dataset/mcic-coco","name":"MCIC-COCO","full_name":"","num_papers_in_archive":1},{"url":"/dataset/nerel-bio","name":"NEREL-BIO","full_name":"","num_papers_in_archive":1},{"url":"/dataset/persianqa","name":"PersianQA","full_name":"Persian Question Answering Dataset","num_papers_in_archive":1},{"url":"/dataset/qbsum","name":"QBSUM","full_name":"","num_papers_in_archive":1},{"url":"/dataset/wikisuggest","name":"WikiSuggest","full_name":"","num_papers_in_archive":1}],"subtasks":[{"url":"/task/belebele","name":"Belebele"},{"url":"/task/english-proverbs","name":"English Proverbs"},{"url":"/task/fantasy-reasoning","name":"Fantasy Reasoning"},{"url":"/task/figure-of-speech-detection","name":"Figure Of Speech Detection"},{"url":"/task/formal-fallacies-syllogisms-negation","name":"Formal Fallacies Syllogisms Negation"},{"url":"/task/gre-reading-comprehension","name":"GRE Reading Comprehension"},{"url":"/task/hyperbaton","name":"Hyperbaton"},{"url":"/task/implicatures","name":"Implicatures"},{"url":"/task/implicit-relations","name":"Implicit Relations"},{"url":"/task/intent-recognition","name":"Intent Recognition"},{"url":"/task/lambada","name":"LAMBADA"},{"url":"/task/logical-reasoning-reading-comprehension","name":"Logical Reasoning Reading Comprehension"},{"url":"/task/machine-reading-comprehension","name":"Machine Reading Comprehension"},{"url":"/task/movie-dialog-same-or-different","name":"Movie Dialog Same Or Different"},{"url":"/task/multi-hop-reading-comprehension","name":"Multi-Hop Reading Comprehension"},{"url":"/task/nonsense-words-grammar","name":"Nonsense Words Grammar"},{"url":"/task/phrase-relatedness","name":"Phrase Relatedness"},{"url":"/task/question-selection","name":"Question Selection"},{"url":"/task/race-h","name":"RACE-h"},{"url":"/task/race-m","name":"RACE-m"}],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":634,"tagged_in_all":1760,"items":[{"url":"/paper/language-models-are-few-shot-learners","title":"Language Models are Few-Shot Learners","date":"2020-05-28","arxiv_id":"2005.14165","repositories_listed":67,"syntology":{"n":65,"n_ran":15,"n_unverified":50,"n_pointer_only":4}},{"url":"/paper/roberta-a-robustly-optimized-bert-pretraining","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","date":"2019-07-26","arxiv_id":"1907.11692","repositories_listed":67,"syntology":{"n":48,"n_ran":22,"n_unverified":26,"n_pointer_only":23}},{"url":"/paper/listen-attend-and-spell","title":"Listen, Attend and Spell","date":"2015-08-05","arxiv_id":"1508.01211","repositories_listed":40,"syntology":{"n":51,"n_ran":12,"n_unverified":39,"n_pointer_only":9}},{"url":"/paper/xlnet-generalized-autoregressive-pretraining","title":"XLNet: Generalized Autoregressive Pretraining for Language Understanding","date":"2019-06-19","arxiv_id":"1906.08237","repositories_listed":27,"syntology":{"n":24,"n_ran":10,"n_unverified":14,"n_pointer_only":3}},{"url":"/paper/bidirectional-attention-flow-for-machine","title":"Bidirectional Attention Flow for Machine Comprehension","date":"2016-11-05","arxiv_id":"1611.01603","repositories_listed":27,"syntology":{"n":11,"n_ran":8,"n_unverified":3,"n_pointer_only":7}},{"url":"/paper/language-models-are-unsupervised-multitask","title":"Language Models are Unsupervised Multitask Learners","date":"2019-02-14","arxiv_id":null,"repositories_listed":21,"syntology":null},{"url":"/paper/squad-100000-questions-for-machine","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","date":"2016-06-16","arxiv_id":"1606.05250","repositories_listed":21,"syntology":{"n":6,"n_ran":4,"n_unverified":2,"n_pointer_only":6}},{"url":"/paper/towards-ai-complete-question-answering-a-set","title":"Towards AI-Complete Question Answering: A Set of Prerequisite Toy Tasks","date":"2015-02-19","arxiv_id":"1502.05698","repositories_listed":20,"syntology":{"n":3,"n_ran":1,"n_unverified":2,"n_pointer_only":2}},{"url":"/paper/qanet-combining-local-convolution-with-global","title":"QANet: Combining Local Convolution with Global Self-Attention for Reading Comprehension","date":"2018-04-23","arxiv_id":"1804.09541","repositories_listed":15,"syntology":{"n":19,"n_ran":7,"n_unverified":12,"n_pointer_only":2}},{"url":"/paper/deberta-decoding-enhanced-bert-with","title":"DeBERTa: Decoding-enhanced BERT with Disentangled Attention","date":"2020-06-05","arxiv_id":"2006.03654","repositories_listed":14,"syntology":{"n":13,"n_ran":4,"n_unverified":9,"n_pointer_only":3}},{"url":"/paper/ms-marco-a-human-generated-machine-reading","title":"MS MARCO: A Human Generated MAchine Reading COmprehension Dataset","date":"2016-11-28","arxiv_id":"1611.09268","repositories_listed":14,"syntology":{"n":33,"n_ran":3,"n_unverified":30,"n_pointer_only":0}},{"url":"/paper/teaching-machines-to-read-and-comprehend","title":"Teaching Machines to Read and Comprehend","date":"2015-06-10","arxiv_id":"1506.03340","repositories_listed":12,"syntology":{"n":2,"n_ran":0,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/know-what-you-dont-know-unanswerable","title":"Know What You Don't Know: Unanswerable Questions for SQuAD","date":"2018-06-11","arxiv_id":"1806.03822","repositories_listed":11,"syntology":null},{"url":"/paper/megatron-lm-training-multi-billion-parameter","title":"Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism","date":"2019-09-17","arxiv_id":"1909.08053","repositories_listed":10,"syntology":{"n":47,"n_ran":12,"n_unverified":35,"n_pointer_only":15}},{"url":"/paper/learning-to-ask-neural-question-generation","title":"Learning to Ask: Neural Question Generation for Reading Comprehension","date":"2017-04-29","arxiv_id":"1705.00106","repositories_listed":10,"syntology":null},{"url":"/paper/reading-wikipedia-to-answer-open-domain","title":"Reading Wikipedia to Answer Open-Domain Questions","date":"2017-03-31","arxiv_id":"1704.00051","repositories_listed":10,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/mt5-a-massively-multilingual-pre-trained-text","title":"mT5: A massively multilingual pre-trained text-to-text transformer","date":"2020-10-22","arxiv_id":"2010.11934","repositories_listed":8,"syntology":{"n":13,"n_ran":0,"n_unverified":13,"n_pointer_only":0}},{"url":"/paper/a-unified-mrc-framework-for-named-entity","title":"A Unified MRC Framework for Named Entity Recognition","date":"2019-10-25","arxiv_id":"1910.11476","repositories_listed":8,"syntology":{"n":5,"n_ran":2,"n_unverified":3,"n_pointer_only":2}},{"url":"/paper/palm-scaling-language-modeling-with-pathways-1","title":"PaLM: Scaling Language Modeling with Pathways","date":"2022-04-05","arxiv_id":"2204.02311","repositories_listed":7,"syntology":{"n":37,"n_ran":30,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/knowledge-guided-text-retrieval-and-reading","title":"Knowledge Guided Text Retrieval and Reading for Open Domain Question Answering","date":"2019-11-10","arxiv_id":"1911.03868","repositories_listed":7,"syntology":{"n":6,"n_ran":4,"n_unverified":2,"n_pointer_only":4}},{"url":"/paper/sdnet-contextualized-attention-based-deep","title":"SDNet: Contextualized Attention-based Deep Network for Conversational Question Answering","date":"2018-12-10","arxiv_id":"1812.03593","repositories_listed":6,"syntology":null},{"url":"/paper/stochastic-answer-networks-for-machine","title":"Stochastic Answer Networks for Machine Reading Comprehension","date":"2017-12-10","arxiv_id":"1712.03556","repositories_listed":6,"syntology":null},{"url":"/paper/pangu-a-large-scale-autoregressive-pretrained","title":"PanGu-$α$: Large-scale Autoregressive Pretrained Chinese Language Models with Auto-parallel Computation","date":"2021-04-26","arxiv_id":"2104.12369","repositories_listed":5,"syntology":null},{"url":"/paper/stochastic-answer-networks-for-squad-20","title":"Stochastic Answer Networks for SQuAD 2.0","date":"2018-09-24","arxiv_id":"1809.09194","repositories_listed":5,"syntology":null},{"url":"/paper/multi-task-learning-for-machine-reading","title":"Multi-task Learning with Sample Re-weighting for Machine Reading Comprehension","date":"2018-09-18","arxiv_id":"1809.06963","repositories_listed":5,"syntology":null},{"url":"/paper/machine-comprehension-using-match-lstm-and","title":"Machine Comprehension Using Match-LSTM and Answer Pointer","date":"2016-08-29","arxiv_id":"1608.07905","repositories_listed":5,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":3}},{"url":"/paper/klue-korean-language-understanding-evaluation","title":"KLUE: Korean Language Understanding Evaluation","date":"2021-05-20","arxiv_id":"2105.09680","repositories_listed":4,"syntology":null},{"url":"/paper/learning-dense-representations-of-phrases-at","title":"Learning Dense Representations of Phrases at Scale","date":"2020-12-23","arxiv_id":"2012.12624","repositories_listed":4,"syntology":null},{"url":"/paper/break-it-down-a-question-understanding","title":"Break It Down: A Question Understanding Benchmark","date":"2020-01-31","arxiv_id":"2001.11770","repositories_listed":4,"syntology":null},{"url":"/paper/dice-loss-for-data-imbalanced-nlp-tasks","title":"Dice Loss for Data-imbalanced NLP Tasks","date":"2019-11-07","arxiv_id":"1911.02855","repositories_listed":4,"syntology":{"n":3,"n_ran":0,"n_unverified":3,"n_pointer_only":0}}],"syntology_records":19,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":2,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}