Biomedical event extraction without training data

Abstract

We describe our system for the BioNLP 2009 event detection task.It is designed to be as domain-independent and unsupervised as possible.Nevertheless, the precisions achieved for single theme event classes range from 75% to 92%, while maintaining reasonable recall.The overall F-scores achieved were 36.44% and 30.80% on the development and the test sets respectively.