Event Presence Prediction Helps Trigger Detection Across Languages
This improves event extraction for information retrieval applications across multiple languages, though it appears incremental.
The authors tackled event detection and classification by proposing a Transformer-based architecture with combined sentence-level and token-level training objectives, achieving new state-of-the-art performance on ACE 2005 for English and Chinese and a 2-point F1 gain on ERE Spanish.
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.