Building a Personalized Dialogue System with Prompt-Tuning

Tomohito Kasahara, Daisuke Kawahara, Nguyen Tung, Shengzhe Li, Kenta Shinzato, Toshinori Sato


Abstract
Dialogue systems without consistent responses are not attractive. In this study, we build a dialogue system that can respond based on a given character setting (persona) to bring consistency. Considering the trend of the rapidly increasing scale of language models, we propose an approach that uses prompt-tuning, which has low learning costs, on pre-trained large-scale language models. The results of the automatic and manual evaluations in English and Japanese show that it is possible to build a dialogue system with more natural and personalized responses with less computational resources than fine-tuning.
Anthology ID:
2022.naacl-srw.13
Volume:
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Student Research Workshop
Month:
July
Year:
2022
Address:
Hybrid: Seattle, Washington + Online
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
96–105
Language:
URL:
https://aclanthology.org/2022.naacl-srw.13
DOI:
10.18653/v1/2022.naacl-srw.13
Bibkey:
Cite (ACL):
Tomohito Kasahara, Daisuke Kawahara, Nguyen Tung, Shengzhe Li, Kenta Shinzato, and Toshinori Sato. 2022. Building a Personalized Dialogue System with Prompt-Tuning. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Student Research Workshop, pages 96–105, Hybrid: Seattle, Washington + Online. Association for Computational Linguistics.
Cite (Informal):
Building a Personalized Dialogue System with Prompt-Tuning (Kasahara et al., NAACL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.naacl-srw.13.pdf
Video:
 https://aclanthology.org/2022.naacl-srw.13.mp4
Data
DailyDialog