Diable: Efficient Dialogue State Tracking as Operations on Tables

Pietro Lesci, Yoshinari Fujinuma, Momchil Hardalov, Chao Shang, Yassine Benajiba, Lluis Marquez


Abstract
Sequence-to-sequence state-of-the-art systems for dialogue state tracking (DST) use the full dialogue history as input, represent the current state as a list with all the slots, and generate the entire state from scratch at each dialogue turn. This approach is inefficient, especially when the number of slots is large and the conversation is long. We propose Diable, a new task formalisation that simplifies the design and implementation of efficient DST systems and allows one to easily plug and play large language models. We represent the dialogue state as a table and formalise DST as a table manipulation task. At each turn, the system updates the previous state by generating table operations based on the dialogue context. Extensive experimentation on the MultiWoz datasets demonstrates that Diable (i) outperforms strong efficient DST baselines, (ii) is 2.4x more time efficient than current state-of-the-art methods while retaining competitive Joint Goal Accuracy, and (iii) is robust to noisy data annotations due to the table operations approach.
Anthology ID:
2023.findings-acl.615
Original:
2023.findings-acl.615v1
Version 2:
2023.findings-acl.615v2
Version 3:
2023.findings-acl.615v3
Volume:
Findings of the Association for Computational Linguistics: ACL 2023
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
9697–9719
Language:
URL:
https://aclanthology.org/2023.findings-acl.615
DOI:
10.18653/v1/2023.findings-acl.615
Bibkey:
Cite (ACL):
Pietro Lesci, Yoshinari Fujinuma, Momchil Hardalov, Chao Shang, Yassine Benajiba, and Lluis Marquez. 2023. Diable: Efficient Dialogue State Tracking as Operations on Tables. In Findings of the Association for Computational Linguistics: ACL 2023, pages 9697–9719, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
Diable: Efficient Dialogue State Tracking as Operations on Tables (Lesci et al., Findings 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.findings-acl.615.pdf