{"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/end-to-end-conversation-modeling-track-in","title":"End-to-end Conversation Modeling Track in DSTC6","arxiv_id":"1706.07440","date":"2017-06-22","proceeding":null,"authors":["Chiori Hori","Takaaki Hori"],"abstract":"End-to-end training of neural networks is a promising approach to automatic\nconstruction of dialog systems using a human-to-human dialog corpus. Recently,\nVinyals et al. tested neural conversation models using OpenSubtitles. Lowe et\nal. released the Ubuntu Dialogue Corpus for researching unstructured multi-turn\ndialogue systems. Furthermore, the approach has been extended to accomplish\ntask oriented dialogs to provide information properly with natural\nconversation. For example, Ghazvininejad et al. proposed a knowledge grounded\nneural conversation model [3], where the research is aiming at combining\nconversational dialogs with task-oriented knowledge using unstructured data\nsuch as Twitter data for conversation and Foursquare data for external\nknowledge.However, the task is still limited to a restaurant information\nservice, and has not yet been tested with a wide variety of dialog tasks. In\naddition, it is still unclear how to create intelligent dialog systems that can\nrespond like a human agent.\n  In consideration of these problems, we proposed a challenge track to the 6th\ndialog system technology challenges (DSTC6) using human-to-human dialog data to\nmimic human dialog behaviors. The focus of the challenge track is to train\nend-to-end conversation models from human-to-human conversation and accomplish\nend-to-end dialog tasks in various situations assuming a customer service, in\nwhich a system plays a role of human agent and generates natural and\ninformative sentences in response to user's questions or comments given dialog\ncontext.","url_abs":"http://arxiv.org/abs/1706.07440v2","url_pdf":"http://arxiv.org/pdf/1706.07440v2.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":"end-to-end-conversation-modeling-track-in","repo_url":"https://github.com/dialogtekgeek/DSTC6-End-to-End-Conversation-Modeling","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1706.07440","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}