Computer Laboratory

Diarmuid Ó Séaghdha

Biomedical Event Extraction without Training Data


Andreas Vlachos, Paula Buttery, Diarmuid Ó Séaghdha and Ted Briscoe, BioNLP 2009

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.

  author = 	 {Andreas Vlachos and Paula Buttery and Diarmuid {\'O S\'eaghdha} and Ted Briscoe},
  title = 	 {Biomedical Event Extraction without Training Data},
  booktitle = 	 {Proceedings of BioNLP 2009},
  year =	 2009,
  address =	 {Boulder, CO}