EmpHi: Generating Empathetic Responses with Human-like Intents

Mao Yan Chen, Siheng Li, Yujiu Yang


Abstract
In empathetic conversations, humans express their empathy to others with empathetic intents. However, most existing empathetic conversational methods suffer from a lack of empathetic intents, which leads to monotonous empathy. To address the bias of the empathetic intents distribution between empathetic dialogue models and humans, we propose a novel model to generate empathetic responses with human-consistent empathetic intents, EmpHi for short. Precisely, EmpHi learns the distribution of potential empathetic intents with a discrete latent variable, then combines both implicit and explicit intent representation to generate responses with various empathetic intents. Experiments show that EmpHi outperforms state-of-the-art models in terms of empathy, relevance, and diversity on both automatic and human evaluation. Moreover, the case studies demonstrate the high interpretability and outstanding performance of our model.
Anthology ID:
2022.naacl-main.78
Volume:
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Month:
July
Year:
2022
Address:
Seattle, United States
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1063–1074
Language:
URL:
https://aclanthology.org/2022.naacl-main.78
DOI:
10.18653/v1/2022.naacl-main.78
Bibkey:
Cite (ACL):
Mao Yan Chen, Siheng Li, and Yujiu Yang. 2022. EmpHi: Generating Empathetic Responses with Human-like Intents. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 1063–1074, Seattle, United States. Association for Computational Linguistics.
Cite (Informal):
EmpHi: Generating Empathetic Responses with Human-like Intents (Chen et al., NAACL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.naacl-main.78.pdf
Code
 mattc95/emphi