Event Argument Identification on Dependency Graphs with Bidirectional LSTMs

Alex Judea, Michael Strube


Abstract
In this paper we investigate the performance of event argument identification. We show that the performance is tied to syntactic complexity. Based on this finding, we propose a novel and effective system for event argument identification. Recurrent Neural Networks learn to produce meaningful representations of long and short dependency paths. Convolutional Neural Networks learn to decompose the lexical context of argument candidates. They are combined into a simple system which outperforms a feature-based, state-of-the-art event argument identifier without any manual feature engineering.
Anthology ID:
I17-1083
Volume:
Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
Month:
November
Year:
2017
Address:
Taipei, Taiwan
Editors:
Greg Kondrak, Taro Watanabe
Venue:
IJCNLP
SIG:
Publisher:
Asian Federation of Natural Language Processing
Note:
Pages:
822–831
Language:
URL:
https://aclanthology.org/I17-1083
DOI:
Bibkey:
Cite (ACL):
Alex Judea and Michael Strube. 2017. Event Argument Identification on Dependency Graphs with Bidirectional LSTMs. In Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 822–831, Taipei, Taiwan. Asian Federation of Natural Language Processing.
Cite (Informal):
Event Argument Identification on Dependency Graphs with Bidirectional LSTMs (Judea & Strube, IJCNLP 2017)
Copy Citation:
PDF:
https://aclanthology.org/I17-1083.pdf