Paper: Detecting Relations in the Gene Regulation Network

ACL ID W13-2020
Title Detecting Relations in the Gene Regulation Network
Venue Proceedings of the BioNLP Shared Task 2013 Workshop
Session
Year 2013
Authors

The BioNLP Shared Task 2013 is organ- ised to further advance the field of in- formation extraction in biomedical texts. This paper describes our entry in the Gene Regulation Network in Bacteria (GRN) part, for which our system finished in sec- ond place (out of five). To tackle this re- lation extraction task, we employ a basic Support Vector Machine framework. We discuss our findings in constructing local and contextual features, that augment our precision with as much as 7.5%. We touch upon the interaction type hierarchy inher- ent in the problem, and the importance of the evaluation procedure to encourage ex- ploration of that structure.