UECA-Prompt: Universal Prompt for Emotion Cause Analysis

Xiaopeng Zheng, Zhiyue Liu, Zizhen Zhang, Zhaoyang Wang, Jiahai Wang


Abstract
Emotion cause analysis (ECA) aims to extract emotion clauses and find the corresponding cause of the emotion. Existing methods adopt fine-tuning paradigm to solve certain types of ECA tasks. These task-specific methods have a deficiency of universality. And the relations among multiple objectives in one task are not explicitly modeled. Moreover, the relative position information introduced in most existing methods may make the model suffer from dataset bias. To address the first two problems, this paper proposes a universal prompt tuning method to solve different ECA tasks in the unified framework. As for the third problem, this paper designs a directional constraint module and a sequential learning module to ease the bias. Considering the commonalities among different tasks, this paper proposes a cross-task training method to further explore the capability of the model. The experimental results show that our method achieves competitive performance on the ECA datasets.
Anthology ID:
2022.coling-1.613
Volume:
Proceedings of the 29th International Conference on Computational Linguistics
Month:
October
Year:
2022
Address:
Gyeongju, Republic of Korea
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
7031–7041
Language:
URL:
https://aclanthology.org/2022.coling-1.613
DOI:
Bibkey:
Cite (ACL):
Xiaopeng Zheng, Zhiyue Liu, Zizhen Zhang, Zhaoyang Wang, and Jiahai Wang. 2022. UECA-Prompt: Universal Prompt for Emotion Cause Analysis. In Proceedings of the 29th International Conference on Computational Linguistics, pages 7031–7041, Gyeongju, Republic of Korea. International Committee on Computational Linguistics.
Cite (Informal):
UECA-Prompt: Universal Prompt for Emotion Cause Analysis (Zheng et al., COLING 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.coling-1.613.pdf
Data
Xia and Ding, 2019