{"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/incorporating-loose-structured-knowledge-into","title":"Incorporating Loose-Structured Knowledge into Conversation Modeling via Recall-Gate LSTM","arxiv_id":"1605.05110","date":"2016-05-17","proceeding":null,"authors":["Zhen Xu","Bingquan Liu","Baoxun Wang","Chengjie Sun","Xiaolong Wang"],"abstract":"Modeling human conversations is the essence for building satisfying chat-bots\nwith multi-turn dialog ability. Conversation modeling will notably benefit from\ndomain knowledge since the relationships between sentences can be clarified due\nto semantic hints introduced by knowledge. In this paper, a deep neural network\nis proposed to incorporate background knowledge for conversation modeling.\nThrough a specially designed Recall gate, domain knowledge can be transformed\ninto the extra global memory of Long Short-Term Memory (LSTM), so as to enhance\nLSTM by cooperating with its local memory to capture the implicit semantic\nrelevance between sentences within conversations. In addition, this paper\nintroduces the loose structured domain knowledge base, which can be built with\nslight amount of manual work and easily adopted by the Recall gate. Our model\nis evaluated on the context-oriented response selecting task, and experimental\nresults on both two datasets have shown that our approach is promising for\nmodeling human conversations and building key components of automatic chatting\nsystems.","url_abs":"http://arxiv.org/abs/1605.05110v2","url_pdf":"http://arxiv.org/pdf/1605.05110v2.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":"incorporating-loose-structured-knowledge-into","repo_url":"https://github.com/taesunwhang/BERT-ResSel","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1605.05110","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}