TY - GEN
T1 - Affective Decoding for Empathetic Response Generation
AU - Zeng, Chengkun
AU - Chen, Guanyi
AU - Lin, Chenghua
AU - Li, Ruizhe
AU - Chen, Zhigang
N1 - Funding Information:
This work is supported by the awards made by the UK Engineering and Physical Sciences Research Council (EP/P011829/1) and Ningbo Natural Science Foundation (202003N4320, 202003N4321). We thank anonymous reviewers for their insightful comments.
PY - 2021
Y1 - 2021
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85123275155&partnerID=8YFLogxK
M3 - Published conference contribution
AN - SCOPUS:85123275155
T3 - INLG 2021 - 14th International Conference on Natural Language Generation, Proceedings
SP - 331
EP - 340
BT - INLG 2021 - 14th International Conference on Natural Language Generation, Proceedings
A2 - Belz, Anya
A2 - Fan, Angela
A2 - Reiter, Ehud
A2 - Sripada, Yaji
PB - Association for Computational Linguistics (ACL)
T2 - 14th International Conference on Natural Language Generation, INLG 2021
Y2 - 20 September 2021 through 24 September 2021
ER -