{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/a-broad-coverage-challenge-corpus-for","title":"A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference","arxiv_id":"1704.05426","date":"2017-04-18","proceeding":"NAACL 2018 6","authors":["Adina Williams","Nikita Nangia","Samuel R. Bowman"],"abstract":"This paper introduces the Multi-Genre Natural Language Inference (MultiNLI)\ncorpus, a dataset designed for use in the development and evaluation of machine\nlearning models for sentence understanding. In addition to being one of the\nlargest corpora available for the task of NLI, at 433k examples, this corpus\nimproves upon available resources in its coverage: it offers data from ten\ndistinct genres of written and spoken English--making it possible to evaluate\nsystems on nearly the full complexity of the language--and it offers an\nexplicit setting for the evaluation of cross-genre domain adaptation.","url_abs":"http://arxiv.org/abs/1704.05426v4","url_pdf":"http://arxiv.org/pdf/1704.05426v4.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"a-broad-coverage-challenge-corpus-for","repo_url":"https://github.com/hpprc/simple-simcse-ja","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"a-broad-coverage-challenge-corpus-for","repo_url":"https://github.com/jabalazs/repeval_rivercorners","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"a-broad-coverage-challenge-corpus-for","repo_url":"https://github.com/nyu-mll/multiNLI","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"a-broad-coverage-challenge-corpus-for","repo_url":"https://github.com/yyhappier/shortcutsuite","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"machine-learning","task_name":"BIG-bench Machine Learning"},{"task_slug":"domain-adaptation","task_name":"Domain Adaptation"},{"task_slug":"natural-language-inference","task_name":"Natural Language Inference"},{"task_slug":"sentence","task_name":"Sentence"}],"methods":[],"datasets_introduced":[{"slug":"multinli","name":"MultiNLI","full_name":"Multi-Genre Natural Language Inference"}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1704.05426","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}