A Comparative Study on Schema-Guided Dialogue State Tracking

Jie Cao, Yi Zhang


Abstract
Frame-based state representation is widely used in modern task-oriented dialog systems to model user intentions and slot values. However, a fixed design of domain ontology makes it difficult to extend to new services and APIs. Recent work proposed to use natural language descriptions to define the domain ontology instead of tag names for each intent or slot, thus offering a dynamic set of schema. In this paper, we conduct in-depth comparative studies to understand the use of natural language description for schema in dialog state tracking. Our discussion mainly covers three aspects: encoder architectures, impact of supplementary training, and effective schema description styles. We introduce a set of newly designed bench-marking descriptions and reveal the model robustness on both homogeneous and heterogeneous description styles in training and evaluation.
Anthology ID:
2021.naacl-main.62
Volume:
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Month:
June
Year:
2021
Address:
Online
Editors:
Kristina Toutanova, Anna Rumshisky, Luke Zettlemoyer, Dilek Hakkani-Tur, Iz Beltagy, Steven Bethard, Ryan Cotterell, Tanmoy Chakraborty, Yichao Zhou
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
782–796
Language:
URL:
https://aclanthology.org/2021.naacl-main.62
DOI:
10.18653/v1/2021.naacl-main.62
Bibkey:
Cite (ACL):
Jie Cao and Yi Zhang. 2021. A Comparative Study on Schema-Guided Dialogue State Tracking. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 782–796, Online. Association for Computational Linguistics.
Cite (Informal):
A Comparative Study on Schema-Guided Dialogue State Tracking (Cao & Zhang, NAACL 2021)
Copy Citation:
PDF:
https://preview.aclanthology.org/improve-issue-templates/2021.naacl-main.62.pdf
Video:
 https://preview.aclanthology.org/improve-issue-templates/2021.naacl-main.62.mp4