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 language | English |
---|---|
Title of host publication | INLG 2021 - 14th International Conference on Natural Language Generation, Proceedings |
Editors | Anya Belz, Angela Fan, Ehud Reiter, Yaji Sripada |
Publisher | Association for Computational Linguistics (ACL) |
Pages | 331-340 |
Number of pages | 10 |
ISBN (Electronic) | 9781954085510 |
Publication status | Published - 2021 |
Event | 14th International Conference on Natural Language Generation, INLG 2021 - Virtual, Online, United Kingdom Duration: 20 Sept 2021 → 24 Sept 2021 |
Publication series
Name | INLG 2021 - 14th International Conference on Natural Language Generation, Proceedings |
---|
Conference
Conference | 14th International Conference on Natural Language Generation, INLG 2021 |
---|---|
Country/Territory | United Kingdom |
City | Virtual, Online |
Period | 20/09/21 → 24/09/21 |
Bibliographical note
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.