TY - JOUR
T1 - Latent Semantic Indexing of medical diagnoses using UMLS semantic structures.
AU - Chute, C. G.
AU - Yang, Y.
AU - Evans, D. A.
N1 - Copyright:
This record is sourced from MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine
PY - 1991
Y1 - 1991
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=0026396174&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=0026396174&partnerID=8YFLogxK
M3 - Article
C2 - 1807584
AN - SCOPUS:0026396174
SP - 185
EP - 189
JO - Proceedings / the ... Annual Symposium on Computer Application [sic] in Medical Care. Symposium on Computer Applications in Medical Care
JF - Proceedings / the ... Annual Symposium on Computer Application [sic] in Medical Care. Symposium on Computer Applications in Medical Care
SN - 0195-4210
ER -