{"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/multi-domain-dialogue-acts-and-response-co","title":"Multi-Domain Dialogue Acts and Response Co-Generation","arxiv_id":"2004.12363","date":"2020-04-26","proceeding":"ACL 2020 6","authors":["Kai Wang","Junfeng Tian","Rui Wang","Xiaojun Quan","Jianxing Yu"],"abstract":"Generating fluent and informative responses is of critical importance for task-oriented dialogue systems. Existing pipeline approaches generally predict multiple dialogue acts first and use them to assist response generation. There are at least two shortcomings with such approaches. First, the inherent structures of multi-domain dialogue acts are neglected. Second, the semantic associations between acts and responses are not taken into account for response generation. To address these issues, we propose a neural co-generation model that generates dialogue acts and responses concurrently. Unlike those pipeline approaches, our act generation module preserves the semantic structures of multi-domain dialogue acts and our response generation module dynamically attends to different acts as needed. We train the two modules jointly using an uncertainty loss to adjust their task weights adaptively. Extensive experiments are conducted on the large-scale MultiWOZ dataset and the results show that our model achieves very favorable improvement over several state-of-the-art models in both automatic and human evaluations.","url_abs":"https://arxiv.org/abs/2004.12363v1","url_pdf":"https://arxiv.org/pdf/2004.12363v1.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":"multi-domain-dialogue-acts-and-response-co","repo_url":"https://github.com/InitialBug/MarCo-Dialog","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"response-generation","task_name":"Response Generation"},{"task_slug":"task-oriented-dialogue-systems","task_name":"Task-Oriented Dialogue Systems"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2004.12363","atlas_url":"https://app.syntology.ai/?focus=2004.12363","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}