Addressing Domain Changes in Task-oriented Conversational Agents through Dialogue Adaptation

Tiziano Labruna, Bernardo Magnini


Abstract
Recent task-oriented dialogue systems are trained on annotated dialogues, which, in turn, reflect certain domain information (e.g., restaurants or hotels in a given region). However, when such domain knowledge changes (e.g., new restaurants open), the initial dialogue model may become obsolete, decreasing the overall performance of the system. Through a number of experiments, we show, for instance, that adding 50% of new slot-values reduces of about 55% the dialogue state-tracker performance. In light of such evidence, we suggest that automatic adaptation of training dialogues is a valuable option for re-training obsolete models. We experimented with a dialogue adaptation approach based on fine-tuning a generative language model on domain changes, showing that a significant reduction of performance decrease can be obtained.
Anthology ID:
2023.eacl-srw.16
Volume:
Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics: Student Research Workshop
Month:
May
Year:
2023
Address:
Dubrovnik, Croatia
Editors:
Elisa Bassignana, Matthias Lindemann, Alban Petit
Venue:
EACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
149–158
Language:
URL:
https://aclanthology.org/2023.eacl-srw.16
DOI:
10.18653/v1/2023.eacl-srw.16
Bibkey:
Cite (ACL):
Tiziano Labruna and Bernardo Magnini. 2023. Addressing Domain Changes in Task-oriented Conversational Agents through Dialogue Adaptation. In Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics: Student Research Workshop, pages 149–158, Dubrovnik, Croatia. Association for Computational Linguistics.
Cite (Informal):
Addressing Domain Changes in Task-oriented Conversational Agents through Dialogue Adaptation (Labruna & Magnini, EACL 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.eacl-srw.16.pdf
Video:
 https://aclanthology.org/2023.eacl-srw.16.mp4