Publication Type
Conference Proceeding Article
Version
publishedVersion
Publication Date
8-2021
Abstract
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.
Discipline
Theory and Algorithms
Research Areas
Data Science and Engineering
Publication
Findings of the Association for Computational Linguistics
First Page
676
Last Page
682
Identifier
10.18653/v1/2021.findings-acl.60
Publisher
Association for Computational Linguistics
City or Country
USA
Citation
LI, Xiangju; GAO, Wei; FENG, Shi; ZHANG, Yifei; and WANG, Daling.
Boundary detection with BERT for span-level emotion cause analysis. (2021). Findings of the Association for Computational Linguistics. 676-682.
Available at: https://ink.library.smu.edu.sg/sis_research/6575
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-No Derivative Works 4.0 International License.
Additional URL
http://doi.org/10.18653/v1/2021.findings-acl.60