{"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/lattice-cnns-for-matching-based-chinese","title":"Lattice CNNs for Matching Based Chinese Question Answering","arxiv_id":"1902.09087","date":"2019-02-25","proceeding":null,"authors":["Yuxuan Lai","Yansong Feng","Xiaohan Yu","Zheng Wang","Kun Xu","Dongyan Zhao"],"abstract":"Short text matching often faces the challenges that there are great word\nmismatch and expression diversity between the two texts, which would be further\naggravated in languages like Chinese where there is no natural space to segment\nwords explicitly. In this paper, we propose a novel lattice based CNN model\n(LCNs) to utilize multi-granularity information inherent in the word lattice\nwhile maintaining strong ability to deal with the introduced noisy information\nfor matching based question answering in Chinese. We conduct extensive\nexperiments on both document based question answering and knowledge based\nquestion answering tasks, and experimental results show that the LCNs models\ncan significantly outperform the state-of-the-art matching models and strong\nbaselines by taking advantages of better ability to distill rich but\ndiscriminative information from the word lattice input.","url_abs":"http://arxiv.org/abs/1902.09087v1","url_pdf":"http://arxiv.org/pdf/1902.09087v1.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":"lattice-cnns-for-matching-based-chinese","repo_url":"https://github.com/Erutan-pku/LCN-for-Chinese-QA","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"text-matching","task_name":"Text Matching"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1902.09087","atlas_url":"https://app.syntology.ai/?focus=1902.09087","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}