Comprehensive Study: How the Context Information of Different Granularity Affects Dialogue State Tracking?

Puhai Yang, Heyan Huang, Xian-Ling Mao


Abstract
Dialogue state tracking (DST) plays a key role in task-oriented dialogue systems to monitor the user’s goal. In general, there are two strategies to track a dialogue state: predicting it from scratch and updating it from previous state. The scratch-based strategy obtains each slot value by inquiring all the dialogue history, and the previous-based strategy relies on the current turn dialogue to update the previous dialogue state. However, it is hard for the scratch-based strategy to correctly track short-dependency dialogue state because of noise; meanwhile, the previous-based strategy is not very useful for long-dependency dialogue state tracking. Obviously, it plays different roles for the context information of different granularity to track different kinds of dialogue states. Thus, in this paper, we will study and discuss how the context information of different granularity affects dialogue state tracking. First, we explore how greatly different granularities affect dialogue state tracking. Then, we further discuss how to combine multiple granularities for dialogue state tracking. Finally, we apply the findings about context granularity to few-shot learning scenario. Besides, we have publicly released all codes.
Anthology ID:
2021.acl-long.193
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:
2481–2491
Language:
URL:
https://aclanthology.org/2021.acl-long.193
DOI:
10.18653/v1/2021.acl-long.193
Bibkey:
Cite (ACL):
Puhai Yang, Heyan Huang, and Xian-Ling Mao. 2021. Comprehensive Study: How the Context Information of Different Granularity Affects 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 2481–2491, Online. Association for Computational Linguistics.
Cite (Informal):
Comprehensive Study: How the Context Information of Different Granularity Affects Dialogue State Tracking? (Yang et al., ACL 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.acl-long.193.pdf
Video:
 https://aclanthology.org/2021.acl-long.193.mp4
Code
 yangpuhai/Granularity-in-DST