A machine reading comprehension framework for recognizing emotion cause in conversations

• Published in: Knowledge-based systems Vol. 289; p. 111532
• Main Authors: Zou, Jiajun, Zhang, Yexuan, Wu, Sixing, Yang, Jinshuai, Qin, Xuanmei, Ying, Lizhi, Jiang, Minghu, Huang, Yongfeng
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 08.04.2024
• Subjects: Conversations texts; Emotion; Emotion cause; Machine reading comprehension; Emotion; Conversations texts; Emotion cause; Machine reading comprehension
• ISSN: 0950-7051; 1872-7409
• DOI: 10.1016/j.knosys.2024.111532

Recognizing Emotion Cause in Conversations (RECC) is a key issue in modeling human cognitive processes, involving Conversational Causal Emotion Entailment task (C2E2) and Conversational Causal Span Extraction task (C2SE). Previous emotion cause extraction research has been concentrated at the clause level, detecting if the cause is in the text, not describing the underlying causes in texts well. In order to address this issue, we suggest a novel approach that can recognize emotion cause spans. These spans can represent or imply the causes for controlling emotions. In this paper, we use a Machine Reading Comprehension framework to Recognize the Emotion Cause in Conversations (MRC-RECC), at both the span level and clause level simultaneously. Specifically, we use two types of queries to build the associations between the two different subtasks: emotion causal entailment task and emotion causal span extraction task. Our framework can recognize emotion cause more effectively by using joint learning to make these two tasks complement each other. Experiments demonstrate that our MRC-RECC provides state-of-the-art performances, which can reason more emotion causes in conversation texts. The code can be found at https://github.com/Guangzidetiaoyue/MRC-RECCON. •We detect dynamic emotion causes in conversations from a cognitive perspective.•We recognize emotion causes in conversations at both the span level and clause level.•We achieve a new SOTA performance for detecting emotion cause in conversations.