Mapping terms to UMLS concepts of the same semantic type.

We are interested in mapping terms from the biomedical literature to controlled terminologies. For clinical and related terms, we rely on the MetaMap program for mapping terms to the UMLS Metathesaurus, accepting term assignments that have a reasonable match score. In a sizable number of cases, terms are ambiguous, and MetaMap proposes several mapping candidates. To address these cases prior studies investigated Word Sense Disambiguation (WSD) strategies for selecting between concepts of different semantic types. Here, we investigated the situation where MetaMap proposes concepts that share the same semantic type. We present an ontology-based strategy for selecting between these concepts.