{"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/attention-over-attention-neural-networks-for","title":"Attention-over-Attention Neural Networks for Reading Comprehension","arxiv_id":"1607.04423","date":"2016-07-15","proceeding":"ACL 2017 7","authors":["Yiming Cui","Zhipeng Chen","Si Wei","Shijin Wang","Ting Liu","Guoping Hu"],"abstract":"Cloze-style queries are representative problems in reading comprehension.\nOver the past few months, we have seen much progress that utilizing neural\nnetwork approach to solve Cloze-style questions. In this paper, we present a\nnovel model called attention-over-attention reader for the Cloze-style reading\ncomprehension task. Our model aims to place another attention mechanism over\nthe document-level attention, and induces \"attended attention\" for final\npredictions. Unlike the previous works, our neural network model requires less\npre-defined hyper-parameters and uses an elegant architecture for modeling.\nExperimental results show that the proposed attention-over-attention model\nsignificantly outperforms various state-of-the-art systems by a large margin in\npublic datasets, such as CNN and Children's Book Test datasets.","url_abs":"http://arxiv.org/abs/1607.04423v4","url_pdf":"http://arxiv.org/pdf/1607.04423v4.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":"attention-over-attention-neural-networks-for","repo_url":"https://github.com/OlavHN/attention-over-attention","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"attention-over-attention-neural-networks-for","repo_url":"https://github.com/kevinkwl/AoAReader","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"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":"AoA Reader","rank_in_archive_order":8,"of":16,"metrics":{"CNN":"74.4"},"uses_additional_data":false},{"leaderboard":"/sota/question-answering-on-childrens-book-test","task":"Question Answering","dataset":"Children's Book Test","model":"AoA reader","rank_in_archive_order":3,"of":8,"metrics":{"Accuracy-CN":"69.4%","Accuracy-NE":"72%"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1607.04423","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}