{"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/improving-response-selection-in-multi-turn","title":"Improving Response Selection in Multi-Turn Dialogue Systems by Incorporating Domain Knowledge","arxiv_id":"1809.03194","date":"2018-09-10","proceeding":"CONLL 2018 10","authors":["Debanjan Chaudhuri","Agustinus Kristiadi","Jens Lehmann","Asja Fischer"],"abstract":"Building systems that can communicate with humans is a core problem in\nArtificial Intelligence. This work proposes a novel neural network architecture\nfor response selection in an end-to-end multi-turn conversational dialogue\nsetting. The architecture applies context level attention and incorporates\nadditional external knowledge provided by descriptions of domain-specific\nwords. It uses a bi-directional Gated Recurrent Unit (GRU) for encoding context\nand responses and learns to attend over the context words given the latent\nresponse representation and vice versa.In addition, it incorporates external\ndomain specific information using another GRU for encoding the domain keyword\ndescriptions. This allows better representation of domain-specific keywords in\nresponses and hence improves the overall performance. Experimental results show\nthat our model outperforms all other state-of-the-art methods for response\nselection in multi-turn conversations.","url_abs":"http://arxiv.org/abs/1809.03194v3","url_pdf":"http://arxiv.org/pdf/1809.03194v3.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":"improving-response-selection-in-multi-turn","repo_url":"https://github.com/SmartDataAnalytics/AK-DE-biGRU","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[],"methods":[{"method_slug":"gru","method_name":"GRU"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1809.03194","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}