{"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/dynamic-coattention-networks-for-question","title":"Dynamic Coattention Networks For Question Answering","arxiv_id":"1611.01604","date":"2016-11-05","proceeding":null,"authors":["Caiming Xiong","Victor Zhong","Richard Socher"],"abstract":"Several deep learning models have been proposed for question answering.\nHowever, due to their single-pass nature, they have no way to recover from\nlocal maxima corresponding to incorrect answers. To address this problem, we\nintroduce the Dynamic Coattention Network (DCN) for question answering. The DCN\nfirst fuses co-dependent representations of the question and the document in\norder to focus on relevant parts of both. Then a dynamic pointing decoder\niterates over potential answer spans. This iterative procedure enables the\nmodel to recover from initial local maxima corresponding to incorrect answers.\nOn the Stanford question answering dataset, a single DCN model improves the\nprevious state of the art from 71.0% F1 to 75.9%, while a DCN ensemble obtains\n80.4% F1.","url_abs":"http://arxiv.org/abs/1611.01604v4","url_pdf":"http://arxiv.org/pdf/1611.01604v4.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":"dynamic-coattention-networks-for-question","repo_url":"https://github.com/BAJUKA/SQuAD-NLP","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"dynamic-coattention-networks-for-question","repo_url":"https://github.com/Lou1sM/AML-Project","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"dynamic-coattention-networks-for-question","repo_url":"https://github.com/Lou1sM/AdvancedML-Project-Dynamic-Coattention-Networks","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"dynamic-coattention-networks-for-question","repo_url":"https://github.com/andreiilie1/dynamic_coattention_networks","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"dynamic-coattention-networks-for-question","repo_url":"https://github.com/lmn-extracts/dcn_plus","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"dynamic-coattention-networks-for-question","repo_url":"https://github.com/wasimusu/MachineRC","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"question-answering","task_name":"Question Answering"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/open-domain-question-answering-on-squad11","task":"Open-Domain Question Answering","dataset":"SQuAD1.1","model":"DCN","rank_in_archive_order":2,"of":3,"metrics":{"EM":"66.2"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-squad11","task":"Question Answering","dataset":"SQuAD1.1","model":"Dynamic Coattention Networks (ensemble)","rank_in_archive_order":148,"of":213,"metrics":{"EM":"71.625","F1":"80.383"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-squad11","task":"Question Answering","dataset":"SQuAD1.1","model":"Dynamic Coattention Networks (single model)","rank_in_archive_order":178,"of":213,"metrics":{"EM":"66.233","F1":"75.896"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-squad11-dev","task":"Question Answering","dataset":"SQuAD1.1 dev","model":"DCN","rank_in_archive_order":45,"of":55,"metrics":{"EM":"65.4","F1":"75.6"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1611.01604","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}