{"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/sequential-dialogue-context-modeling-for","title":"Sequential Dialogue Context Modeling for Spoken Language Understanding","arxiv_id":"1705.03455","date":"2017-05-08","proceeding":"WS 2017 8","authors":["Ankur Bapna","Gokhan Tur","Dilek Hakkani-Tur","Larry Heck"],"abstract":"Spoken Language Understanding (SLU) is a key component of goal oriented\ndialogue systems that would parse user utterances into semantic frame\nrepresentations. Traditionally SLU does not utilize the dialogue history beyond\nthe previous system turn and contextual ambiguities are resolved by the\ndownstream components. In this paper, we explore novel approaches for modeling\ndialogue context in a recurrent neural network (RNN) based language\nunderstanding system. We propose the Sequential Dialogue Encoder Network, that\nallows encoding context from the dialogue history in chronological order. We\ncompare the performance of our proposed architecture with two context models,\none that uses just the previous turn context and another that encodes dialogue\ncontext in a memory network, but loses the order of utterances in the dialogue\nhistory. Experiments with a multi-domain dialogue dataset demonstrate that the\nproposed architecture results in reduced semantic frame error rates.","url_abs":"http://arxiv.org/abs/1705.03455v3","url_pdf":"http://arxiv.org/pdf/1705.03455v3.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":"sequential-dialogue-context-modeling-for","repo_url":"https://github.com/sunbopds/SDEN-Pytorch-master","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"goal-oriented-dialogue-systems","task_name":"Goal-Oriented Dialogue Systems"},{"task_slug":"spoken-language-understanding","task_name":"Spoken Language Understanding"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1705.03455","atlas_url":"https://app.syntology.ai/?focus=1705.03455","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}