Authors : M. Sundara Rajan and S.P. Rajagopalan
Abstract: Medical NLP systems, generally designed to analyze medical texts for decision support or indexing purposes, have to deal with ambiguities in language. Information Retrieval (IR) in the Medical Domain often ignores word senses in document relevance calculations. This is largely due to the fact that word sense disambiguation is not an easy task. However, in IR some of the strictest requirements of traditional approach to detailed disambiguation can be relaxed. This study discusses a successfully implemented approach to using word senses in IR tasks, which can be combined with various IR methods for successful use in the Medical Domain.
M. Sundara Rajan and S.P. Rajagopalan , 2007. Information Retrieval in Medical Domain Using Root Sense Tagging Approach . International Journal of Soft Computing, 2: 592-594.