Constructing Emotional Consensus and Utilizing Unpaired Data for Empathetic Dialogue Generation

Lei Shen, Jinchao Zhang, Jiao Ou, Xiaofang Zhao, Jie Zhou


Abstract
Researches on dialogue empathy aim to endow an agent with the capacity of accurate understanding and proper responding for emotions. Existing models for empathetic dialogue generation focus on the emotion flow in one direction, that is, from the context to response. We argue that conducting an empathetic conversation is a bidirectional process, where empathy occurs when the emotions of two interlocutors could converge on the same point, i.e., reaching an emotional consensus. Besides, we also find that the empathetic dialogue corpus is extremely limited, which further restricts the model performance. To address the above issues, we propose a dual-generative model, Dual-Emp, to simultaneously construct the emotional consensus and utilize some external unpaired data. Specifically, our model integrates a forward dialogue model, a backward dialogue model, and a discrete latent variable representing the emotional consensus into a unified architecture. Then, to alleviate the constraint of paired data, we extract unpaired emotional data from open-domain conversations and employ Dual-Emp to produce pseudo paired empathetic samples, which is more efficient and low-cost than the human annotation. Automatic and human evaluations demonstrate that our method outperforms competitive baselines in producing coherent and empathetic responses.
Anthology ID:
2021.findings-emnlp.268
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2021
Month:
November
Year:
2021
Address:
Punta Cana, Dominican Republic
Venue:
Findings
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
3124–3134
Language:
URL:
https://aclanthology.org/2021.findings-emnlp.268
DOI:
10.18653/v1/2021.findings-emnlp.268
Bibkey:
Cite (ACL):
Lei Shen, Jinchao Zhang, Jiao Ou, Xiaofang Zhao, and Jie Zhou. 2021. Constructing Emotional Consensus and Utilizing Unpaired Data for Empathetic Dialogue Generation. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 3124–3134, Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
Constructing Emotional Consensus and Utilizing Unpaired Data for Empathetic Dialogue Generation (Shen et al., Findings 2021)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingestion-script-update/2021.findings-emnlp.268.pdf
Video:
 https://preview.aclanthology.org/ingestion-script-update/2021.findings-emnlp.268.mp4