Seed-based event trigger labeling: How far can event descriptions get us?

The task of event trigger labeling is typi-cally addressed in the standard supervised setting: triggers for each target event type are annotated as training data, based on annotation guidelines. We propose an al-ternative approach, which takes the exam-ple trigger terms mentioned in the guide-lines as seeds, and then applies an event-independent similarity-based classifier for trigger labeling. This way we can skip manual annotation for new event types, while requiring only minimal annotated training data for few example events at system setup. Our method is evaluated on the ACE-2005 dataset, achieving 5.7% Fx improvement over a state-of-the-art super-vised system which uses the full training data.