{"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/convolutional-neural-network-architectures-1","title":"Convolutional Neural Network Architectures for Matching Natural Language Sentences","arxiv_id":"1503.03244","date":"2015-03-11","proceeding":"NeurIPS 2014 12","authors":["Baotian Hu","Zhengdong Lu","Hang Li","Qingcai Chen"],"abstract":"Semantic matching is of central importance to many natural language tasks\n\\cite{bordes2014semantic,RetrievalQA}. A successful matching algorithm needs to\nadequately model the internal structures of language objects and the\ninteraction between them. As a step toward this goal, we propose convolutional\nneural network models for matching two sentences, by adapting the convolutional\nstrategy in vision and speech. The proposed models not only nicely represent\nthe hierarchical structures of sentences with their layer-by-layer composition\nand pooling, but also capture the rich matching patterns at different levels.\nOur models are rather generic, requiring no prior knowledge on language, and\ncan hence be applied to matching tasks of different nature and in different\nlanguages. The empirical study on a variety of matching tasks demonstrates the\nefficacy of the proposed model on a variety of matching tasks and its\nsuperiority to competitor models.","url_abs":"http://arxiv.org/abs/1503.03244v1","url_pdf":"http://arxiv.org/pdf/1503.03244v1.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":"convolutional-neural-network-architectures-1","repo_url":"https://github.com/Elvirasun28/quora-question-duplicate","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"convolutional-neural-network-architectures-1","repo_url":"https://github.com/SJHBXShub/Question_pair","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}}],"tasks":[{"task_slug":"question-answering","task_name":"Question Answering"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/question-answering-on-semevalcqa","task":"Question Answering","dataset":"SemEvalCQA","model":"ARC-II","rank_in_archive_order":4,"of":5,"metrics":{"MAP":"0.780","P@1":"0.753"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1503.03244","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}