{"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/natural-language-comprehension-with-the","title":"Natural Language Comprehension with the EpiReader","arxiv_id":"1606.02270","date":"2016-06-07","proceeding":"EMNLP 2016 11","authors":["Adam Trischler","Zheng Ye","Xingdi Yuan","Kaheer Suleman"],"abstract":"We present the EpiReader, a novel model for machine comprehension of text.\nMachine comprehension of unstructured, real-world text is a major research goal\nfor natural language processing. Current tests of machine comprehension pose\nquestions whose answers can be inferred from some supporting text, and evaluate\na model's response to the questions. The EpiReader is an end-to-end neural\nmodel comprising two components: the first component proposes a small set of\ncandidate answers after comparing a question to its supporting text, and the\nsecond component formulates hypotheses using the proposed candidates and the\nquestion, then reranks the hypotheses based on their estimated concordance with\nthe supporting text. We present experiments demonstrating that the EpiReader\nsets a new state-of-the-art on the CNN and Children's Book Test machine\ncomprehension benchmarks, outperforming previous neural models by a significant\nmargin.","url_abs":"http://arxiv.org/abs/1606.02270v2","url_pdf":"http://arxiv.org/pdf/1606.02270v2.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-cnn-daily-mail","task":"Question Answering","dataset":"CNN / Daily Mail","model":"EpiReader","rank_in_archive_order":9,"of":16,"metrics":{"CNN":"74"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-childrens-book-test","task":"Question Answering","dataset":"Children's Book Test","model":"EpiReader","rank_in_archive_order":7,"of":8,"metrics":{"Accuracy-CN":"67.4%","Accuracy-NE":"69.7%"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1606.02270","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}