ESCoT: Towards Interpretable Emotional Support Dialogue Systems

Tenggan Zhang, Xinjie Zhang, Jinming Zhao, Li Zhou, Qin Jin

Abstract
Understanding the reason for emotional support response is crucial for establishing connections between users and emotional support dialogue systems. Previous works mostly focus on generating better responses but ignore interpretability, which is extremely important for constructing reliable dialogue systems. To empower the system with better interpretability, we propose an emotional support response generation scheme, named Emotion-Focused and Strategy-Driven Chain-of-Thought (ESCoT), mimicking the process of identifying, understanding, and regulating emotions. Specially, we construct a new dataset with ESCoT in two steps: (1) Dialogue Generation where we first generate diverse conversation situations, then enhance dialogue generation using richer emotional support strategies based on these situations; (2) Chain Supplement where we focus on supplementing selected dialogues with elements such as emotion, stimuli, appraisal, and strategy reason, forming the manually verified chains. Additionally, we further develop a model to generate dialogue responses with better interpretability. We also conduct extensive experiments and human evaluations to validate the effectiveness of the proposed ESCoT and generated dialogue responses. Our dataset, code, and model will be released.
Anthology ID:
2024.acl-long.723
Volume:
Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Lun-Wei Ku, Andre Martins, Vivek Srikumar
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
13395–13412
Language:
URL:
https://aclanthology.org/2024.acl-long.723
DOI:
10.18653/v1/2024.acl-long.723
Bibkey:
Cite (ACL):
Tenggan Zhang, Xinjie Zhang, Jinming Zhao, Li Zhou, and Qin Jin. 2024. ESCoT: Towards Interpretable Emotional Support Dialogue Systems. In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 13395–13412, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
ESCoT: Towards Interpretable Emotional Support Dialogue Systems (Zhang et al., ACL 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/dois-2013-emnlp/2024.acl-long.723.pdf
PDF Search