Extending Event Detection to New Types with Learning from Keywords

Viet Dac Lai, Thien Nguyen


Abstract
Traditional event detection classifies a word or a phrase in a given sentence for a set of prede- fined event types. The limitation of such pre- defined set is that it prevents the adaptation of the event detection models to new event types. We study a novel formulation of event detec- tion that describes types via several keywords to match the contexts in documents. This fa- cilitates the operation of the models to new types. We introduce a novel feature-based attention mechanism for convolutional neural networks for event detection in the new for- mulation. Our extensive experiments demon- strate the benefits of the new formulation for new type extension for event detection as well as the proposed attention mechanism for this problem
Anthology ID:
D19-5532
Volume:
Proceedings of the 5th Workshop on Noisy User-generated Text (W-NUT 2019)
Month:
November
Year:
2019
Address:
Hong Kong, China
Venues:
EMNLP | WNUT | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
243–248
Language:
URL:
https://www.aclweb.org/anthology/D19-5532
DOI:
10.18653/v1/D19-5532
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/D19-5532.pdf