Pattern-based bootstrapping framework for biomedical relation extraction

摘要

The progress made in the realm of '-omics' technologies has led to a tremendous increase in the quantum of biomedical research published. Information extraction from this huge unstructured mass of data needs automation through text mining methods. Biomedical relation extraction is one such vital automation processes for extracting biomedical relations hidden in scientific literature. In the recent past, several supervised machine learning methods have been used to identify biomedical relations. However, given the variations in textual expression, huge corpus size and small task-specific training data, semi-supervised techniques appear to perform better. To this end, we propose a system that uses the semi-supervised bootstrapping algorithm to extract biomedical relations from text. The unlabelled corpus used contains sentences with biomedical entities represented as patterns with the dependency tree feature. Bootstrapping starts with a seed set and iteratively learns new patterns from the unlabelled corpus. We have designed a three-level masking technique to generate new patterns, and incorporated three types of scoring to help select appropriate patterns. The pattern-based bootstrapping method performs well with a minimum seed set. The system is able to extract 37,450 patterns from the unlabelled corpus that represents different biomedical relations. These patterns, in turn, are able to identify 460,886 relation pairs with 1327 single, and 1012 coupled, trigger words that convey the semantics of the biomedical relation. More than 64% of the identified relations have evidence in the CTD database.