Improving Empathetic Dialogue Generation by Dynamically Infusing Commonsense Knowledge

Hua Cai, Xuli Shen, Qing Xu, Weilin Shen, Xiaomei Wang, Weifeng Ge, Xiaoqing Zheng, Xiangyang Xue


Abstract
In empathetic conversations, individuals express their empathy towards others. Previous work has mainly focused on generating empathetic responses by utilizing the speaker’s emotion. Besides, external commonsense knowledge has been applied to enhance the system’s understandings of the speaker’s situation. However, given an event, commonsense knowledge base contains various relations, potentially leading to confusion for the dialogue system. Consequently, inconsistencies arise among the emotion, generated response and speaker’s contextual information. To this end, we propose a novel approach for empathetic response generation, which incorporates an adaptive module for commonsense knowledge selection to ensure consistency between the generated empathetic responses and the speaker’s situation. This selected knowledge is used to refine the commonsense cognition and empathy expression for generated responses. Experimental results show that our approach significantly outperforms baseline models in both automatic and human evaluations, exhibiting the generation of more coherent and empathetic responses. Moreover, case studies highlight the interpretability of knowledge selection in the responses and the effectiveness of adaptive module in our model. Code: https://github.com/Hanscal/DCKS.
Anthology ID:
2023.findings-acl.498
Volume:
Findings of the Association for Computational Linguistics: ACL 2023
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
7858–7873
Language:
URL:
https://aclanthology.org/2023.findings-acl.498
DOI:
10.18653/v1/2023.findings-acl.498
Bibkey:
Cite (ACL):
Hua Cai, Xuli Shen, Qing Xu, Weilin Shen, Xiaomei Wang, Weifeng Ge, Xiaoqing Zheng, and Xiangyang Xue. 2023. Improving Empathetic Dialogue Generation by Dynamically Infusing Commonsense Knowledge. In Findings of the Association for Computational Linguistics: ACL 2023, pages 7858–7873, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
Improving Empathetic Dialogue Generation by Dynamically Infusing Commonsense Knowledge (Cai et al., Findings 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.findings-acl.498.pdf