Recent Trends in Deep Learning Based Textual Emotion Cause Extraction

Xinxin Su, Zhen Huang, Yunxiang Zhao, Yifan Chen, Yong Dou, Hengyue Pan

Abstract: Emotion Cause Extraction Field (ECEF) focuses on the cause that triggers an emotion in a document. Traditional ECEF aims to extract the cause based on a given emotion while recent ECEF focuses more on extracting both the emotion and its corresponding cause. ECEF has attracted a lot of attention due to the significant developments in deep learning techniques, especially machine reading comprehension and neural network-based information retrieval. However, a comprehensive review of existing approaches and recent trends in ECEF is lacking. In this paper, we present a thorough survey to summarise existing methods for ECEF, including those for Emotion Cause Extraction (ECE), Emotion Cause Pair Extraction (ECPE), and Conversational Emotion Cause Extraction Field (CECEF). We also detail the widely used public datasets and discuss the limitations and prospects of existing methods in ECEF.