Boundary detection with BERT for span-level emotion cause analysis

• Main Authors: LI, Xiangju, GAO, Wei, FENG, Shi, ZHANG, Yifei, WANG, Daling
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2021
• Subjects: Theory and Algorithms
• Online Access: https://ink.library.smu.edu.sg/sis_research/6575; https://ink.library.smu.edu.sg/context/sis_research/article/7578/viewcontent/2021.findings_acl.60.pdf
• Institution: Singapore Management University

Emotion cause analysis (ECA) has been anemerging topic in natural language processing,which aims to identify the reasons behind acertain emotion expressed in the text. MostECA methods intend to identify the clausewhich contains the cause of a given emotion,but such clause-level ECA (CECA) can be ambiguous and imprecise. In this paper, we aimat span-level ECA (SECA) by detecting theprecise boundaries of text spans conveying accurate emotion causes from the given context.We formulate this task as sequence labelingand position identification problems and design two neural methods to solve them. Experiments on two benchmark ECA datasets showthat the proposed methods substantially outperform the existing ECA models.