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
- 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)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-2/2023.eacl-srw.16.pdf