Hi-DST: A Hierarchical Approach for Scalable and Extensible Dialogue State Tracking

Suvodip Dey, Maunendra Sankar Desarkar


Abstract
Dialogue State Tracking (DST) is a sub-task of task-based dialogue systems where the user intention is tracked through a set of (domain, slot, slot-value) triplets. Existing DST models can be difficult to extend for new datasets with larger domains/slots mainly due to either of the two reasons- i) prediction of domain-slot as a pair, and ii) dependency of model parameters on the number of slots and domains. In this work, we propose to address these issues using a Hierarchical DST (Hi-DST) model. At a given turn, the model first detects a change in domain followed by domain prediction if required. Then it decides suitable action for each slot in the predicted domains and finds their value accordingly. The model parameters of Hi-DST are independent of the number of domains/slots. Due to the hierarchical modeling, it achieves O(|M|+|N|) belief state prediction for a single turn where M and N are the set of unique domains and slots respectively. We argue that the hierarchical structure helps in the model explainability and makes it easily extensible to new datasets. Experiments on the MultiWOZ dataset show that our proposed model achieves comparable joint accuracy performance to state-of-the-art DST models.
Anthology ID:
2021.sigdial-1.23
Volume:
Proceedings of the 22nd Annual Meeting of the Special Interest Group on Discourse and Dialogue
Month:
July
Year:
2021
Address:
Singapore and Online
Editors:
Haizhou Li, Gina-Anne Levow, Zhou Yu, Chitralekha Gupta, Berrak Sisman, Siqi Cai, David Vandyke, Nina Dethlefs, Yan Wu, Junyi Jessy Li
Venue:
SIGDIAL
SIG:
SIGDIAL
Publisher:
Association for Computational Linguistics
Note:
Pages:
218–227
Language:
URL:
https://aclanthology.org/2021.sigdial-1.23
DOI:
10.18653/v1/2021.sigdial-1.23
Bibkey:
Cite (ACL):
Suvodip Dey and Maunendra Sankar Desarkar. 2021. Hi-DST: A Hierarchical Approach for Scalable and Extensible Dialogue State Tracking. In Proceedings of the 22nd Annual Meeting of the Special Interest Group on Discourse and Dialogue, pages 218–227, Singapore and Online. Association for Computational Linguistics.
Cite (Informal):
Hi-DST: A Hierarchical Approach for Scalable and Extensible Dialogue State Tracking (Dey & Desarkar, SIGDIAL 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.sigdial-1.23.pdf
Video:
 https://www.youtube.com/watch?v=ldnP2Cn_7F0
Code
 suvodipdey/hi-dst
Data
MultiWOZSGDSQuAD