Extracting Protein-Protein Interactions from the Literature Using the Hidden Vector State Model

Full text available as:

PDF (Version of Record) - Repository staff only - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader Download (381Kb) | Request Copy from OU Author

Abstract

In the field of bioinformatics in solving biological problems, the huge amount of knowledge is often locked in textual documents such as scientific publications. Hence there is an increasing focus on extracting information from this vast amount of scientific literature. In this paper, we present an information extraction system which employs a semantic parser using the Hidden Vector State (HVS) model for protein-protein interactions. Unlike other hierarchical parsing models which require fully annotated treebank data for training, the HVS model can be trained using only lightly annotated data whilst simultaneously retaining sufficient ability to capture the hierarchical structure needed to robustly extract task domain semantics. When applied in extracting protein-protein interactions information from medical literature, we found that it performed better than other established statistical methods and achieved 47.9% and 72.8% in recall and precision respectively.