Span-level emotion cause analysis with neural sequence tagging

• Main Authors: LI, Xiangju, GAO, Wei, FENG, Shi, WANG, Daling, JOTY, Shafiq
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2021
• Subjects: neural network; sequence tagging; span-level emotion cause analysis; Artificial Intelligence and Robotics; Theory and Algorithms
• Online Access: https://ink.library.smu.edu.sg/sis_research/6688; https://ink.library.smu.edu.sg/context/sis_research/article/7691/viewcontent/3459637.3482186.pdf
• Institution: Singapore Management University

This paper addresses the task of span-level emotion cause analysis (SECA). It is a finer-grained emotion cause analysis (ECA) task, which aims to identify the specific emotion cause span(s) behind certain emotions in text. In this paper, we formalize SECA as a sequence tagging task for which several variants of neural network-based sequence tagging models to extract specific emotion cause span(s) in the given context. These models combine different types of encoding and decoding approaches. Furthermore, to make our models more "emotionally sensitive'', we utilize the multi-head attention mechanism to enhance the representation of context. Experimental evaluations conducted on two benchmark datasets demonstrate the effectiveness of the proposed models.