Event Detection with Trigger-Aware Lattice Neural Network

Ning Ding, Ziran Li, Zhiyuan Liu, Haitao Zheng, Zibo Lin

Abstract
Event detection (ED) aims to locate trigger words in raw text and then classify them into correct event types. In this task, neural net- work based models became mainstream in re- cent years. However, two problems arise when it comes to languages without natural delim- iters, such as Chinese. First, word-based mod- els severely suffer from the problem of word- trigger mismatch, limiting the performance of the methods. In addition, even if trigger words could be accurately located, the ambi- guity of polysemy of triggers could still af- fect the trigger classification stage. To ad- dress the two issues simultaneously, we pro- pose the Trigger-aware Lattice Neural Net- work (TLNN). (1) The framework dynami- cally incorporates word and character informa- tion so that the trigger-word mismatch issue can be avoided. (2) Moreover, for polysemous characters and words, we model all senses of them with the help of an external linguistic knowledge base, so as to alleviate the prob- lem of ambiguous triggers. Experiments on two benchmark datasets show that our model could effectively tackle the two issues and outperforms previous state-of-the-art methods significantly, giving the best results. The source code of this paper can be obtained from https://github.com/thunlp/TLNN.
Anthology ID:
D19-1033
Volume:
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
Month:
November
Year:
2019
Address:
Hong Kong, China
Venues:
EMNLP | IJCNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
347–356
Language:
URL:
https://aclanthology.org/D19-1033
DOI:
10.18653/v1/D19-1033
Bibkey:
Cite (ACL):
Ning Ding, Ziran Li, Zhiyuan Liu, Haitao Zheng, and Zibo Lin. 2019. Event Detection with Trigger-Aware Lattice Neural Network. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 347–356, Hong Kong, China. Association for Computational Linguistics.
Cite (Informal):
Event Detection with Trigger-Aware Lattice Neural Network (Ding et al., EMNLP-IJCNLP 2019)
Copy Citation:
PDF:
https://preview.aclanthology.org/remove-xml-comments/D19-1033.pdf
Code
 thunlp/TLNN
PDF Search Code