A Learning Approach for Word Sense Disambiguation in the Biomedical Domain.
Hisham Al-Mubaid, Sandeep Gungu · 2011
Word sense disambiguation, WSD, task has been investigated extensively within the natural language processing domain. In the biomedical domain, word sense ambiguity is more widely spread with bioinformatics research effort devoted to it is not commensurate and is allowing for more development. In this paper, we present and evaluate a machine learning based approach for WSD. The main limitation with supervised methods is the requirement for manually disambiguated instances of the ambiguous word to be used for training. However, the advances in automatic text annotation and tagging techniques with the help of the plethora of knowledge sources like ontologies and text literature in the biomedical domain will help lessen this limitation. Our approach has been evaluated with the benchmark dataset NLM-WSD with three settings. The accuracy results showed that our method performs better than recently reported results of other published techniques. * corresponding author: