Event extraction from trimmed dependency graphs

Abstract

We describe the approach to event extraction which the JulieLab Team from FSU Jena (Germany) pursued to solve Task 1 in the "BioNLP'09 Shared Task on Event Extraction". We incorporate manually curated dictionaries and machine learning methodologies to sort out associated event triggers and arguments on trimmed dependency graph structures. Trimming combines pruning irrelevant lexical material from a dependency graph and decorating particularly relevant lexical material from that graph with more abstract conceptual class information. Given that methodological framework, the JulieLab Team scored on 2nd rank among 24 competing teams, with 45.8% precision, 47.5% recall and 46.7% F1-score on all 3,182 events.