{"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/end-to-end-answer-chunk-extraction-and","title":"End-to-End Answer Chunk Extraction and Ranking for Reading Comprehension","arxiv_id":"1610.09996","date":"2016-10-31","proceeding":null,"authors":["Yang Yu","Wei zhang","Kazi Hasan","Mo Yu","Bing Xiang","Bo-Wen Zhou"],"abstract":"This paper proposes dynamic chunk reader (DCR), an end-to-end neural reading\ncomprehension (RC) model that is able to extract and rank a set of answer\ncandidates from a given document to answer questions. DCR is able to predict\nanswers of variable lengths, whereas previous neural RC models primarily\nfocused on predicting single tokens or entities. DCR encodes a document and an\ninput question with recurrent neural networks, and then applies a word-by-word\nattention mechanism to acquire question-aware representations for the document,\nfollowed by the generation of chunk representations and a ranking module to\npropose the top-ranked chunk as the answer. Experimental results show that DCR\nachieves state-of-the-art exact match and F1 scores on the SQuAD dataset.","url_abs":"http://arxiv.org/abs/1610.09996v2","url_pdf":"http://arxiv.org/pdf/1610.09996v2.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":[],"tasks":[{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"reading-comprehension","task_name":"Reading Comprehension"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/question-answering-on-squad11","task":"Question Answering","dataset":"SQuAD1.1","model":"Dynamic Chunk Reader","rank_in_archive_order":187,"of":213,"metrics":{"EM":"62.499","F1":"70.956"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-squad11-dev","task":"Question Answering","dataset":"SQuAD1.1 dev","model":"DCR","rank_in_archive_order":49,"of":55,"metrics":{"EM":" 62.5","F1":"71.2"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1610.09996","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}