{"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/stochastic-answer-networks-for-squad-20","title":"Stochastic Answer Networks for SQuAD 2.0","arxiv_id":"1809.09194","date":"2018-09-24","proceeding":null,"authors":["Xiaodong Liu","Wei Li","Yuwei Fang","Aerin Kim","Kevin Duh","Jianfeng Gao"],"abstract":"This paper presents an extension of the Stochastic Answer Network (SAN), one\nof the state-of-the-art machine reading comprehension models, to be able to\njudge whether a question is unanswerable or not. The extended SAN contains two\ncomponents: a span detector and a binary classifier for judging whether the\nquestion is unanswerable, and both components are jointly optimized.\nExperiments show that SAN achieves the results competitive to the\nstate-of-the-art on Stanford Question Answering Dataset (SQuAD) 2.0. To\nfacilitate the research on this field, we release our code:\nhttps://github.com/kevinduh/san_mrc.","url_abs":"http://arxiv.org/abs/1809.09194v1","url_pdf":"http://arxiv.org/pdf/1809.09194v1.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":"stochastic-answer-networks-for-squad-20","repo_url":"https://github.com/kevinduh/san_mrc","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"stochastic-answer-networks-for-squad-20","repo_url":"https://github.com/Xaniar87/SAN_SQuAD2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"stochastic-answer-networks-for-squad-20","repo_url":"https://github.com/aerinkim/squad_2018","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"stochastic-answer-networks-for-squad-20","repo_url":"https://github.com/lduml/blog","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"stochastic-answer-networks-for-squad-20","repo_url":"https://github.com/yongbowin/san_mrc_annotation","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"machine-reading-comprehension","task_name":"Machine Reading Comprehension"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"reading-comprehension","task_name":"Reading Comprehension"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1809.09194","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}