The task of event detection and classification is central to most information retrieval applications. We show that a Transformer based architecture can effectively model event extraction as a sequence labeling task. We propose a combination of sentence level and token level training objectives that significantly boosts the performance of a BERT based event extraction model. Our approach achieves a new state-of-the-art performance on ACE 2005 data for English and Chinese. We also test our model on ERE Spanish, achieving an average gain of 2 absolute F1 points over prior best performing model.
@article{arxiv.2009.07188,
title = {Event Presence Prediction Helps Trigger Detection Across Languages},
author = {Parul Awasthy and Tahira Naseem and Jian Ni and Taesun Moon and Radu Florian},
journal= {arXiv preprint arXiv:2009.07188},
year = {2020}
}