Paper: Not all links are equal: Exploiting Dependency Types for the Extraction of Protein-Protein Interactions from Text

ACL ID W11-0201
Title Not all links are equal: Exploiting Dependency Types for the Extraction of Protein-Protein Interactions from Text
Venue Workshop on Biomedical Natural Language Processing
Session
Year 2011
Authors

The extraction of protein-protein interactions (PPIs) reported in scientific publications is one of the most studied topics in Text Mining in the Life Sciences, as such algorithms can sub- stantially decrease the effort for databases cu- rators. The currently best methods for this task are based on analyzing the dependency tree (DT) representation of sentences. Many approaches exploit only topological features and thus do not yet fully exploit the informa- tion contained in DTs. We show that incor- porating the grammatical information encoded in the types of the dependencies in DTs no- ticeably improves extraction performance by using a pattern matching approach. We au- tomatically infer a large set of linguistic pat- terns using only information about interact- ing proteins. Patterns are ...