{"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/a-sequence-to-sequence-approach-to-dialogue","title":"A Sequence-to-Sequence Approach to Dialogue State Tracking","arxiv_id":"2011.09553","date":"2020-11-18","proceeding":"ACL 2021 5","authors":["Yue Feng","Yang Wang","Hang Li"],"abstract":"This paper is concerned with dialogue state tracking (DST) in a task-oriented dialogue system. Building a DST module that is highly effective is still a challenging issue, although significant progresses have been made recently. This paper proposes a new approach to dialogue state tracking, referred to as Seq2Seq-DU, which formalizes DST as a sequence-to-sequence problem. Seq2Seq-DU employs two BERT-based encoders to respectively encode the utterances in the dialogue and the descriptions of schemas, an attender to calculate attentions between the utterance embeddings and the schema embeddings, and a decoder to generate pointers to represent the current state of dialogue. Seq2Seq-DU has the following advantages. It can jointly model intents, slots, and slot values; it can leverage the rich representations of utterances and schemas based on BERT; it can effectively deal with categorical and non-categorical slots, and unseen schemas. In addition, Seq2Seq-DU can also be used in the NLU (natural language understanding) module of a dialogue system. Experimental results on benchmark datasets in different settings (SGD, MultiWOZ2.2, MultiWOZ2.1, WOZ2.0, DSTC2, M2M, SNIPS, and ATIS) show that Seq2Seq-DU outperforms the existing methods.","url_abs":"https://arxiv.org/abs/2011.09553v2","url_pdf":"https://arxiv.org/pdf/2011.09553v2.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":"a-sequence-to-sequence-approach-to-dialogue","repo_url":"https://github.com/sweetalyssum/Seq2Seq-DU","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"dialogue-state-tracking","task_name":"Dialogue State Tracking"},{"task_slug":"multi-domain-dialogue-state-tracking","task_name":"Multi-domain Dialogue State Tracking"},{"task_slug":"natural-language-understanding","task_name":"Natural Language Understanding"}],"methods":[{"method_slug":"dst","method_name":"DST"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/classification-on-sgd","task":"Classification","dataset":"SGD","model":"SGD_ss","rank_in_archive_order":1,"of":1,"metrics":{"F1 (Seqeval)":"2020"},"uses_additional_data":false},{"leaderboard":"/sota/dialogue-state-tracking-on-second-dialogue","task":"Dialogue State Tracking","dataset":"Second dialogue state tracking challenge","model":"Seq2Seq-DU-w/oSchema","rank_in_archive_order":1,"of":7,"metrics":{"Joint":"85"},"uses_additional_data":false},{"leaderboard":"/sota/dialogue-state-tracking-on-wizard-of-oz","task":"Dialogue State Tracking","dataset":"Wizard-of-Oz","model":"Seq2Seq-DU-w/oSchema","rank_in_archive_order":2,"of":10,"metrics":{"Joint":"91.2"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2011.09553","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}