Explicit Semantic Analysis for computing semantic relatedness of biomedical text

Explicit Semantic Analysis (ESA) with Wikipedia as its knowledge-base has been found to perform well for finding the semantic relatedness between text fragments. It has also been found that in the case of text fragments whose domain is already known, such as those extracted from research papers or complete documents pertaining to specific domains, it is more beneficial to use a knowledge-base corresponding to that domain instead of Wikipedia. We propose a method for calculating the semantic relatedness of text related to diseases, conditions, and wellness issues that uses ESA with MedlinePlus as its knowledge-base, and provides an improvement in the computation of semantic relatedness scores over the current state-of-the-art for the biomedical domain.