Biomedical Relationship Extraction from Literature Based on Bio-semantic Token Subsequences

摘要

Relationship Extraction (RE) from biomedical literature is an important and challenging problem in both text mining and bioinformatics. Although various approaches have been proposed to extract protein-protein interaction types, their accuracy rates leave a large room for further exploration of more effective methods. In this paper, two supervised learning algorithms based on newly-defined ȁC;bio-semantic token subsequenceȁD; are proposed for multi-class biomedical relationship extraction. The first approach calculates a ȁC;bio-semantic token subsequence kernelȁD;, while the second one explicitly extracts weighted features from bio-semantic token subsequences. The proposed structure called ȁC;bio-semantic token subsequenceȁD; is able to capture semantic features from natural language sentences for biomedical RE. Two supervised learning algorithms based on the proposed structure outperform the state-of-the-art biomedical RE methods on multi-class protein-protein interaction extraction.