Affective Decoding for Empathetic Response Generation

Chengkun Zeng, Guanyi Chen, Chenghua Lin*, Ruizhe Li, Zhigang Chen

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingPublished conference contribution

2 Citations (Scopus)

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.

Original languageEnglish
Title of host publicationINLG 2021 - 14th International Conference on Natural Language Generation, Proceedings
EditorsAnya Belz, Angela Fan, Ehud Reiter, Yaji Sripada
PublisherAssociation for Computational Linguistics (ACL)
Pages331-340
Number of pages10
ISBN (Electronic)9781954085510
Publication statusPublished - 2021
Event14th International Conference on Natural Language Generation, INLG 2021 - Virtual, Online, United Kingdom
Duration: 20 Sep 202124 Sep 2021

Publication series

NameINLG 2021 - 14th International Conference on Natural Language Generation, Proceedings

Conference

Conference14th International Conference on Natural Language Generation, INLG 2021
Country/TerritoryUnited Kingdom
CityVirtual, Online
Period20/09/2124/09/21

Fingerprint

Dive into the research topics of 'Affective Decoding for Empathetic Response Generation'. Together they form a unique fingerprint.

Cite this