Generate, Evaluate, and Select: A Dialogue System with a Response Evaluator for Diversity-Aware Response Generation

Ryoma Sakaeda, Daisuke Kawahara


Abstract
We aim to overcome the lack of diversity in responses of current dialogue systems and to develop a dialogue system that is engaging as a conversational partner. We propose a generator-evaluator model that evaluates multiple responses generated by a response generator and selects the best response by an evaluator. By generating multiple responses, we obtain diverse responses. We conduct human evaluations to compare the output of the proposed system with that of a baseline system. The results of the human evaluations showed that the proposed system’s responses were often judged to be better than the baseline system’s, and indicated the effectiveness of the proposed method.
Anthology ID:
2022.naacl-srw.10
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:
76–82
Language:
URL:
https://aclanthology.org/2022.naacl-srw.10
DOI:
10.18653/v1/2022.naacl-srw.10
Bibkey:
Cite (ACL):
Ryoma Sakaeda and Daisuke Kawahara. 2022. Generate, Evaluate, and Select: A Dialogue System with a Response Evaluator for Diversity-Aware Response Generation. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Student Research Workshop, pages 76–82, Hybrid: Seattle, Washington + Online. Association for Computational Linguistics.
Cite (Informal):
Generate, Evaluate, and Select: A Dialogue System with a Response Evaluator for Diversity-Aware Response Generation (Sakaeda & Kawahara, NAACL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.naacl-srw.10.pdf
Video:
 https://aclanthology.org/2022.naacl-srw.10.mp4