BREAK: Breaking the Dialogue State Tracking Barrier with Beam Search and Re-ranking

Seungpil Won, Heeyoung Kwak, Joongbo Shin, Janghoon Han, Kyomin Jung


Abstract
Despite the recent advances in dialogue state tracking (DST), the joint goal accuracy (JGA) of the existing methods on MultiWOZ 2.1 still remains merely 60%. In our preliminary error analysis, we find that beam search produces a pool of candidates that is likely to include the correct dialogue state. Motivated by this observation, we introduce a novel framework, called BREAK (Beam search and RE-rAnKing), that achieves outstanding performance on DST. BREAK performs DST in two stages: (i) generating k-best dialogue state candidates with beam search and (ii) re-ranking the candidates to select the correct dialogue state. This simple yet powerful framework shows state-of-the-art performance on all versions of MultiWOZ and M2M datasets. Most notably, we push the joint goal accuracy to 80-90% on MultiWOZ 2.1-2.4, which is an improvement of 23.6%, 26.3%, 21.7%, and 10.8% over the previous best-performing models, respectively. The data and code will be available at https://github.com/tony-won/DST-BREAK
Anthology ID:
2023.acl-long.159
Volume:
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2832–2846
Language:
URL:
https://aclanthology.org/2023.acl-long.159
DOI:
10.18653/v1/2023.acl-long.159
Bibkey:
Cite (ACL):
Seungpil Won, Heeyoung Kwak, Joongbo Shin, Janghoon Han, and Kyomin Jung. 2023. BREAK: Breaking the Dialogue State Tracking Barrier with Beam Search and Re-ranking. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 2832–2846, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
BREAK: Breaking the Dialogue State Tracking Barrier with Beam Search and Re-ranking (Won et al., ACL 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/dois-2013-emnlp/2023.acl-long.159.pdf
Video:
 https://preview.aclanthology.org/dois-2013-emnlp/2023.acl-long.159.mp4