Abstract
The relational files within the UMLS Metathesaurus contain rich semantic associations to main concepts. We invoked the technique of Latent Semantic Indexing to generate information matrices based on these relationships and created "semantic vectors" using singular value decomposition. Evaluations were made on the complete set and subsets of Metathesaurus main concepts with the semantic type "Disease or Syndrome." Real number matrices were created with main concepts, lexical variants, synonyms, and associated expressions. Ancestors, children, siblings, and related terms were added to alternative matrices, preserving the hierarchical direction of the relation as the imaginary component of a complex number. Preliminary evaluation suggests that this technique is robust. A major advantage is the exploitation of semantic features which derive from a statistical decomposition of UMLS structures, possibly reducing dependence on the tedious construction of semantic frames by humans.
Full text
PDFSelected References
These references are in PubMed. This may not be the complete list of references from this article.
- Hersh W. R., Greenes R. A. SAPHIRE--an information retrieval system featuring concept matching, automatic indexing, probabilistic retrieval, and hierarchical relationships. Comput Biomed Res. 1990 Oct;23(5):410–425. doi: 10.1016/0010-4809(90)90031-7. [DOI] [PubMed] [Google Scholar]