Eliciting Rich Positive Emotions in Dialogue Generation

Ziwei Gong, Qingkai Min, Yue Zhang


Abstract
Positive emotion elicitation aims at evoking positive emotion states in human users in open-domain dialogue generation. However, most work focuses on inducing a single-dimension of positive sentiment using human annotated datasets, which limits the scale of the training dataset. In this paper, we propose to model various emotions in large unannotated conversations, such as joy, trust and anticipation, by leveraging a latent variable to control the emotional intention of the response. Our proposed emotion-eliciting-Conditional-Variational-AutoEncoder (EE-CVAE) model generates more diverse and emotionally-intelligent responses compared to single-dimension baseline models in human evaluation.
Anthology ID:
2023.sicon-1.1
Volume:
Proceedings of the First Workshop on Social Influence in Conversations (SICon 2023)
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Kushal Chawla, Weiyan Shi
Venue:
SICon
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1–8
Language:
URL:
https://aclanthology.org/2023.sicon-1.1
DOI:
10.18653/v1/2023.sicon-1.1
Bibkey:
Cite (ACL):
Ziwei Gong, Qingkai Min, and Yue Zhang. 2023. Eliciting Rich Positive Emotions in Dialogue Generation. In Proceedings of the First Workshop on Social Influence in Conversations (SICon 2023), pages 1–8, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
Eliciting Rich Positive Emotions in Dialogue Generation (Gong et al., SICon 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.sicon-1.1.pdf
Video:
 https://aclanthology.org/2023.sicon-1.1.mp4