A Sequence-to-Sequence Approach to Dialogue State Tracking

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.
Anthology ID:
2021.acl-long.135
Volume:
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
Month:
August
Year:
2021
Address:
Online
Venues:
ACL | IJCNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1714–1725
Language:
URL:
https://aclanthology.org/2021.acl-long.135
DOI:
10.18653/v1/2021.acl-long.135
Bibkey:
Cite (ACL):
Yue Feng, Yang Wang, and Hang Li. 2021. A Sequence-to-Sequence Approach to Dialogue State Tracking. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 1714–1725, Online. Association for Computational Linguistics.
Cite (Informal):
A Sequence-to-Sequence Approach to Dialogue State Tracking (Feng et al., ACL-IJCNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.acl-long.135.pdf
Video:
 https://aclanthology.org/2021.acl-long.135.mp4
Code
 sweetalyssum/Seq2Seq-DU
Data
Dialogue State Tracking ChallengeMultiWOZSGDSNIPSWizard-of-Oz