Joint Event Extraction with Hierarchical Policy Network

Peixin Huang, Xiang Zhao, Ryuichi Takanobu, Zhen Tan, Weidong Xiao


Abstract
Most existing work on event extraction (EE) either follows a pipelined manner or uses a joint structure but is pipelined in essence. As a result, these efforts fail to utilize information interactions among event triggers, event arguments, and argument roles, which causes information redundancy. In view of this, we propose to exploit the role information of the arguments in an event and devise a Hierarchical Policy Network (HPNet) to perform joint EE. The whole EE process is fulfilled through a two-level hierarchical structure consisting of two policy networks for event detection and argument detection. The deep information interactions among the subtasks are realized, and it is more natural to deal with multiple events issue. Extensive experiments on ACE2005 and TAC2015 demonstrate the superiority of HPNet, leading to state-of-the-art performance and is more powerful for sentences with multiple events.
Anthology ID:
2020.coling-main.239
Volume:
Proceedings of the 28th International Conference on Computational Linguistics
Month:
December
Year:
2020
Address:
Barcelona, Spain (Online)
Venue:
COLING
SIG:
Publisher:
International Committee on Computational Linguistics
Note:
Pages:
2653–2664
Language:
URL:
https://aclanthology.org/2020.coling-main.239
DOI:
10.18653/v1/2020.coling-main.239
Bibkey:
Copy Citation:
PDF:
https://aclanthology.org/2020.coling-main.239.pdf