Categorización de textos biomédicos usando UMLS

  1. Perea Ortega, José Manuel
  2. Montejo Ráez, Arturo
  3. Martín Valdivia, María Teresa
  4. Díaz Galiano, Manuel Carlos
Aldizkaria:
Procesamiento del lenguaje natural

ISSN: 1135-5948

Argitalpen urtea: 2008

Zenbakia: 40

Orrialdeak: 121-127

Mota: Artikulua

Beste argitalpen batzuk: Procesamiento del lenguaje natural

Laburpena

In this paper we present an automatic system for multi-label text categorization which makes use of UMLS (Unified Medical Language System). Our approach has been tested on a biomedical corpus which includes very short texts belonging to expedients of children with respiratory disseases. The corpus has been enriched by using those ontologies integrated in UMLS and the results obtained show that the term expansion approach proposed greatly improves the traditional categorization system.