{"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-question-focused-multi-factor-attention","title":"A Question-Focused Multi-Factor Attention Network for Question Answering","arxiv_id":"1801.08290","date":"2018-01-25","proceeding":null,"authors":["Souvik Kundu","Hwee Tou Ng"],"abstract":"Neural network models recently proposed for question answering (QA) primarily\nfocus on capturing the passage-question relation. However, they have minimal\ncapability to link relevant facts distributed across multiple sentences which\nis crucial in achieving deeper understanding, such as performing multi-sentence\nreasoning, co-reference resolution, etc. They also do not explicitly focus on\nthe question and answer type which often plays a critical role in QA. In this\npaper, we propose a novel end-to-end question-focused multi-factor attention\nnetwork for answer extraction. Multi-factor attentive encoding using\ntensor-based transformation aggregates meaningful facts even when they are\nlocated in multiple sentences. To implicitly infer the answer type, we also\npropose a max-attentional question aggregation mechanism to encode a question\nvector based on the important words in a question. During prediction, we\nincorporate sequence-level encoding of the first wh-word and its immediately\nfollowing word as an additional source of question type information. Our\nproposed model achieves significant improvements over the best prior\nstate-of-the-art results on three large-scale challenging QA datasets, namely\nNewsQA, TriviaQA, and SearchQA.","url_abs":"http://arxiv.org/abs/1801.08290v1","url_pdf":"http://arxiv.org/pdf/1801.08290v1.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-question-focused-multi-factor-attention","repo_url":"https://github.com/nusnlp/amanda","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"open-domain-question-answering","task_name":"Open-Domain Question Answering"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"reading-comprehension","task_name":"Reading Comprehension"},{"task_slug":"sentence","task_name":"Sentence"},{"task_slug":"triviaqa","task_name":"TriviaQA"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/open-domain-question-answering-on-searchqa","task":"Open-Domain Question Answering","dataset":"SearchQA","model":"AMANDA","rank_in_archive_order":11,"of":14,"metrics":{"EM":"-","F1":"-","N-gram F1":"56.6","Unigram Acc":"46.8"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-newsqa","task":"Question Answering","dataset":"NewsQA","model":"AMANDA","rank_in_archive_order":14,"of":18,"metrics":{"EM":"48.4","F1":"63.7"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}