An End-to-End Multi-task Learning Network with Scope Controller for Emotion-Cause Pair Extraction

摘要：

　　Emotion-cause pair extraction(ECPE)aims to extract all potential pairs of emotions and corresponding causes in a document.It has an advantage over traditional emotion cause extraction(ECE)that it does not require annotat-ing emotions manually.Existing methods for ECPE task are based on two-step framework.However,they ignore the fact that the emotion-cause pair is regarded as a whole unit and there are cascading errors in two-step framework.In this paper,we propose an end-to-end hierarchical neural network model,which directly extracts emotion-cause pairs and enhances mutual interaction between emotions and causes via multi-task learning.In addition,we introduce a scope controller to constrain the emotion-cause pair predictions in a high probability area,accord-ing to the position correlation between emotions and causes.The experimental results demonstrate that our method achieves the state-of-the-art performance and improves F-measure by 2.24%.

关键词： Emotion-cause pair extraction Multi-task learning Emotion cause analysis Scope controller

作者: Rui Fan Yufan Wang Tingting He

作者单位: Hubei Provincial Key Laboratory of Artificial Intelligence and Smart Learning,China Central Normal U Hubei Provincial Key Laboratory of Artificial Intelligence and Smart Learning,China Central Normal U

会议类型: 国际会议

会议名称: 9th CCF International Conference on Natural Language Processing and Chinese Computing (NLPCC 2020)

会议地点: 郑州

会议语种:英文

页码: 764-776

在线出版日期: 2020-10-14（万方平台首次上网日期，不代表论文的发表时间）