Key points are not available for this paper at this time.
We explore a rule-based methodology for the BioNLP'09 Shared Task on Event Extraction, using dependency parsing as the underlying principle for extracting and characterizing events. We approach the speculation and negation detection task with the same principle. Evaluation results demonstrate the utility of this syntax-based approach and point out some shortcomings that need to be addressed in future work.
Kilicoglu et al. (Thu,) studied this question.