StyEmp: Stylizing Empathetic Response Generation via Multi-Grained Prefix Encoder and Personality Reinforcement

Yahui Fu, Chenhui Chu, Tatsuya Kawahara


Abstract
Recent approaches for empathetic response generation mainly focus on emotional resonance and user understanding, without considering the system’s personality. Consistent personality is evident in real human expression and is important for creating trustworthy systems. To address this problem, we propose StyEmp, which aims to stylize the empathetic response generation with a consistent personality. Specifically, it incorporates a multi-grained prefix mechanism designed to capture the intricate relationship between a system’s personality and its empathetic expressions. Furthermore, we introduce a personality reinforcement module that leverages contrastive learning to calibrate the generation model, ensuring that responses are both empathetic and reflective of a distinct personality. Automatic and human evaluations on the EMPATHETICDIALOGUES benchmark show that StyEmp outperforms competitive baselines in terms of both empathy and personality expressions. Our code is available at https://github.com/fuyahuii/StyEmp.
Anthology ID:
2024.sigdial-1.15
Volume:
Proceedings of the 25th Annual Meeting of the Special Interest Group on Discourse and Dialogue
Month:
September
Year:
2024
Address:
Kyoto, Japan
Editors:
Tatsuya Kawahara, Vera Demberg, Stefan Ultes, Koji Inoue, Shikib Mehri, David Howcroft, Kazunori Komatani
Venue:
SIGDIAL
SIG:
SIGDIAL
Publisher:
Association for Computational Linguistics
Note:
Pages:
172–185
Language:
URL:
https://aclanthology.org/2024.sigdial-1.15
DOI:
10.18653/v1/2024.sigdial-1.15
Bibkey:
Cite (ACL):
Yahui Fu, Chenhui Chu, and Tatsuya Kawahara. 2024. StyEmp: Stylizing Empathetic Response Generation via Multi-Grained Prefix Encoder and Personality Reinforcement. In Proceedings of the 25th Annual Meeting of the Special Interest Group on Discourse and Dialogue, pages 172–185, Kyoto, Japan. Association for Computational Linguistics.
Cite (Informal):
StyEmp: Stylizing Empathetic Response Generation via Multi-Grained Prefix Encoder and Personality Reinforcement (Fu et al., SIGDIAL 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.sigdial-1.15.pdf