Transition-based Directed Graph Construction for Emotion-Cause Pair Extraction

Chuang Fan, Chaofa Yuan, Jiachen Du, Lin Gui, Min Yang, Ruifeng Xu


Abstract
Emotion-cause pair extraction aims to extract all potential pairs of emotions and corresponding causes from unannotated emotion text. Most existing methods are pipelined framework, which identifies emotions and extracts causes separately, leading to a drawback of error propagation. Towards this issue, we propose a transition-based model to transform the task into a procedure of parsing-like directed graph construction. The proposed model incrementally generates the directed graph with labeled edges based on a sequence of actions, from which we can recognize emotions with the corresponding causes simultaneously, thereby optimizing separate subtasks jointly and maximizing mutual benefits of tasks interdependently. Experimental results show that our approach achieves the best performance, outperforming the state-of-the-art methods by 6.71% (p<0.01) in F1 measure.
Anthology ID:
2020.acl-main.342
Volume:
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2020
Address:
Online
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3707–3717
Language:
URL:
https://www.aclweb.org/anthology/2020.acl-main.342
DOI:
10.18653/v1/2020.acl-main.342
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/2020.acl-main.342.pdf
Video:
 http://slideslive.com/38928888