Affective Decoding for Empathetic Response Generation

Chengkun Zeng, Guanyi Chen, Chenghua Lin, Ruizhe Li, Zhi Chen


Abstract
Understanding speaker’s feelings and producing appropriate responses with emotion connection is a key communicative skill for empathetic dialogue systems. In this paper, we propose a simple technique called Affective Decoding for empathetic response generation. Our method can effectively incorporate emotion signals during each decoding step, and can additionally be augmented with an auxiliary dual emotion encoder, which learns separate embeddings for the speaker and listener given the emotion base of the dialogue. Extensive empirical studies show that our models are perceived to be more empathetic by human evaluations, in comparison to several strong mainstream methods for empathetic responding.
Anthology ID:
2021.inlg-1.37
Volume:
Proceedings of the 14th International Conference on Natural Language Generation
Month:
August
Year:
2021
Address:
Aberdeen, Scotland, UK
Editors:
Anya Belz, Angela Fan, Ehud Reiter, Yaji Sripada
Venue:
INLG
SIG:
SIGGEN
Publisher:
Association for Computational Linguistics
Note:
Pages:
331–340
Language:
URL:
https://aclanthology.org/2021.inlg-1.37
DOI:
10.18653/v1/2021.inlg-1.37
Bibkey:
Cite (ACL):
Chengkun Zeng, Guanyi Chen, Chenghua Lin, Ruizhe Li, and Zhi Chen. 2021. Affective Decoding for Empathetic Response Generation. In Proceedings of the 14th International Conference on Natural Language Generation, pages 331–340, Aberdeen, Scotland, UK. Association for Computational Linguistics.
Cite (Informal):
Affective Decoding for Empathetic Response Generation (Zeng et al., INLG 2021)
Copy Citation:
PDF:
https://preview.aclanthology.org/add_acl24_videos/2021.inlg-1.37.pdf
Code
 zenggo/affective-decoding-4-empathetic-dialog