Dialogue State Tracking with a Language Model using Schema-Driven Prompting

Chia-Hsuan Lee, Hao Cheng, Mari Ostendorf


Abstract
Task-oriented conversational systems often use dialogue state tracking to represent the user’s intentions, which involves filling in values of pre-defined slots. Many approaches have been proposed, often using task-specific architectures with special-purpose classifiers. Recently, good results have been obtained using more general architectures based on pretrained language models. Here, we introduce a new variation of the language modeling approach that uses schema-driven prompting to provide task-aware history encoding that is used for both categorical and non-categorical slots. We further improve performance by augmenting the prompting with schema descriptions, a naturally occurring source of in-domain knowledge. Our purely generative system achieves state-of-the-art performance on MultiWOZ 2.2 and achieves competitive performance on two other benchmarks: MultiWOZ 2.1 and M2M. The data and code will be available at https://github.com/chiahsuan156/DST-as-Prompting.
Anthology ID:
2021.emnlp-main.404
Volume:
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2021
Address:
Online and Punta Cana, Dominican Republic
Editors:
Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4937–4949
Language:
URL:
https://aclanthology.org/2021.emnlp-main.404
DOI:
10.18653/v1/2021.emnlp-main.404
Bibkey:
Cite (ACL):
Chia-Hsuan Lee, Hao Cheng, and Mari Ostendorf. 2021. Dialogue State Tracking with a Language Model using Schema-Driven Prompting. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 4937–4949, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
Dialogue State Tracking with a Language Model using Schema-Driven Prompting (Lee et al., EMNLP 2021)
Copy Citation:
PDF:
https://preview.aclanthology.org/naacl24-info/2021.emnlp-main.404.pdf
Video:
 https://preview.aclanthology.org/naacl24-info/2021.emnlp-main.404.mp4
Code
 chiahsuan156/dst-as-prompting
Data
MultiWOZ