{"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/retrieve-and-refine-improved-sequence","title":"Retrieve and Refine: Improved Sequence Generation Models For Dialogue","arxiv_id":"1808.04776","date":"2018-08-14","proceeding":"WS 2018 10","authors":["Jason Weston","Emily Dinan","Alexander H. Miller"],"abstract":"Sequence generation models for dialogue are known to have several problems:\nthey tend to produce short, generic sentences that are uninformative and\nunengaging. Retrieval models on the other hand can surface interesting\nresponses, but are restricted to the given retrieval set leading to erroneous\nreplies that cannot be tuned to the specific context. In this work we develop a\nmodel that combines the two approaches to avoid both their deficiencies: first\nretrieve a response and then refine it -- the final sequence generator treating\nthe retrieval as additional context. We show on the recent CONVAI2 challenge\ntask our approach produces responses superior to both standard retrieval and\ngeneration models in human evaluations.","url_abs":"http://arxiv.org/abs/1808.04776v2","url_pdf":"http://arxiv.org/pdf/1808.04776v2.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":"retrieve-and-refine-improved-sequence","repo_url":"https://github.com/hihellohowareyou/RESREF_Chatbot_data_for_Korean","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"retrieval","task_name":"Retrieval"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1808.04776","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}