{"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/a-knowledge-grounded-neural-conversation","title":"A Knowledge-Grounded Neural Conversation Model","arxiv_id":"1702.01932","date":"2017-02-07","proceeding":null,"authors":["Marjan Ghazvininejad","Chris Brockett","Ming-Wei Chang","Bill Dolan","Jianfeng Gao","Wen-tau Yih","Michel Galley"],"abstract":"Neural network models are capable of generating extremely natural sounding\nconversational interactions. Nevertheless, these models have yet to demonstrate\nthat they can incorporate content in the form of factual information or\nentity-grounded opinion that would enable them to serve in more task-oriented\nconversational applications. This paper presents a novel, fully data-driven,\nand knowledge-grounded neural conversation model aimed at producing more\ncontentful responses without slot filling. We generalize the widely-used\nSeq2Seq approach by conditioning responses on both conversation history and\nexternal \"facts\", allowing the model to be versatile and applicable in an\nopen-domain setting. Our approach yields significant improvements over a\ncompetitive Seq2Seq baseline. Human judges found that our outputs are\nsignificantly more informative.","url_abs":"http://arxiv.org/abs/1702.01932v2","url_pdf":"http://arxiv.org/pdf/1702.01932v2.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":"a-knowledge-grounded-neural-conversation","repo_url":"https://github.com/DSTC-MSR-NLP/DSTC7-End-to-End-Conversation-Modeling","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"a-knowledge-grounded-neural-conversation","repo_url":"https://github.com/mgalley/DSTC7-End-to-End-Conversation-Modeling","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"slot-filling","task_name":"Slot Filling"},{"task_slug":"model","task_name":"model"}],"methods":[{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"seq2seq","method_name":"Seq2Seq"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1702.01932","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}