Continual Dialogue State Tracking via Example-Guided Question Answering

Hyundong Cho, Andrea Madotto, Zhaojiang Lin, Khyathi Chandu, Satwik Kottur, Jing Xu, Jonathan May, Chinnadhurai Sankar


Abstract
Dialogue systems are frequently updated to accommodate new services, but naively updating them by continually training with data for new services in diminishing performance on previously learnt services. Motivated by the insight that dialogue state tracking (DST), a crucial component of dialogue systems that estimates the user’s goal as a conversation proceeds, is a simple natural language understanding task, we propose reformulating it as a bundle of granular example-guided question answering tasks to minimize the task shift between services and thus benefit continual learning. Our approach alleviates service-specific memorization and teaches a model to contextualize the given question and example to extract the necessary information from the conversation. We find that a model with just 60M parameters can achieve a significant boost by learning to learn from in-context examples retrieved by a retriever trained to identify turns with similar dialogue state changes. Combining our method with dialogue-level memory replay, our approach attains state of the art performance on DST continual learning metrics without relying on any complex regularization or parameter expansion methods.
Anthology ID:
2023.emnlp-main.235
Volume:
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
Month:
December
Year:
2023
Address:
Singapore
Editors:
Houda Bouamor, Juan Pino, Kalika Bali
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3873–3886
Language:
URL:
https://aclanthology.org/2023.emnlp-main.235
DOI:
10.18653/v1/2023.emnlp-main.235
Bibkey:
Cite (ACL):
Hyundong Cho, Andrea Madotto, Zhaojiang Lin, Khyathi Chandu, Satwik Kottur, Jing Xu, Jonathan May, and Chinnadhurai Sankar. 2023. Continual Dialogue State Tracking via Example-Guided Question Answering. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 3873–3886, Singapore. Association for Computational Linguistics.
Cite (Informal):
Continual Dialogue State Tracking via Example-Guided Question Answering (Cho et al., EMNLP 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.emnlp-main.235.pdf
Video:
 https://aclanthology.org/2023.emnlp-main.235.mp4