{"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-joint-learning-of-natural-language","title":"End-to-End Joint Learning of Natural Language Understanding and Dialogue Manager","arxiv_id":"1612.00913","date":"2016-12-03","proceeding":null,"authors":["Xuesong Yang","Yun-Nung Chen","Dilek Hakkani-Tur","Paul Crook","Xiujun Li","Jianfeng Gao","Li Deng"],"abstract":"Natural language understanding and dialogue policy learning are both\nessential in conversational systems that predict the next system actions in\nresponse to a current user utterance. Conventional approaches aggregate\nseparate models of natural language understanding (NLU) and system action\nprediction (SAP) as a pipeline that is sensitive to noisy outputs of\nerror-prone NLU. To address the issues, we propose an end-to-end deep recurrent\nneural network with limited contextual dialogue memory by jointly training NLU\nand SAP on DSTC4 multi-domain human-human dialogues. Experiments show that our\nproposed model significantly outperforms the state-of-the-art pipeline models\nfor both NLU and SAP, which indicates that our joint model is capable of\nmitigating the affects of noisy NLU outputs, and NLU model can be refined by\nerror flows backpropagating from the extra supervised signals of system\nactions.","url_abs":"http://arxiv.org/abs/1612.00913v2","url_pdf":"http://arxiv.org/pdf/1612.00913v2.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-joint-learning-of-natural-language","repo_url":"https://github.com/XuesongYang/end2end_dialog","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"natural-language-understanding","task_name":"Natural Language Understanding"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}