Paper: Dependency-Driven Feature-based Learning for Extracting Protein-Protein Interactions from Biomedical Text

ACL ID C10-2087
Title Dependency-Driven Feature-based Learning for Extracting Protein-Protein Interactions from Biomedical Text
Venue International Conference on Computational Linguistics
Session Poster Session
Year 2010
Authors

Recent kernel-based PPI extraction systems achieve promising perform- ance because of their capability to capture structural syntactic informa- tion, but at the expense of computa- tional complexity. This paper incorpo- rates dependency information as well as other lexical and syntactic knowl- edge in a feature-based framework. Our motivation is that, considering the large amount of biomedical literature being archived daily, feature-based methods with comparable performance are more suitable for practical applica- tions. Additionally, we explore the difference of lexical characteristics be- tween biomedical and newswire do- mains. Experimental evaluation on the AIMed corpus shows that our system achieves comparable performance of 54.7 in F1-Score with other state-of-the-art P...