We study the task of span-level emotion cause analysis (SECA), which is focused on identifying the specific emotion cause span(s) triggering a certain emotion in the text. Compared to the popular clause-level emotion cause analysis (CECA), it is a finer-grained emotion cause analysis (ECA) task. Existing SECA method relies on the manually engineered features, which is labor-intensive and not generalized well. In this paper, we design a BERT-based graph attention network for emotion cause span(s) identification. The proposed model takes advantage the structure of BERT to capture the relationship information between emotion and text, and utilizes graph attention network to model the structure information of the text. Our SECA method can be easily used for extracting clause-level emotion causes for CECA as well. Experimental results show that the proposed method consistently outperform the state-of-the-art ECA methods on benchmark emotion cause dataset.
Span-Level Emotion Cause Analysis by BERT-based Graph Attention Network
Xiangju Li, Wei Gao, Shi Feng, Wang Daling, and Shafiq Joty. In Proceedings of The 30th ACM International Conference on Information and Knowledge Management (CIKM'21 (short paper)) , pages xx-xx, 2021.
Abstract BibTex Slides