Exploiting Dependency Information for Feature-Based Protein-Protein Interaction Extraction

This paper investigates the combination of diverse lexical, syntactic and semantic information in feature-based protein-protein interaction extraction using SVM. Our study illustrates that dependency information as well as base phrase chunking information is very effective for feature-based PPI extraction while the full parse feature have less effect on the overall performance. Experimental evaluation on the AIMed corpus shows that our system achieves a promising performance of 54.7 in F-measure, surpassing other state-of-the-art feature-based ones.