Ontology learning from biomedical natural language documents using UMLS

  • Authors:
  • Juana María Ruiz-Martínez;Rafael Valencia-García;Jesualdo Tomás Fernández-Breis;Francisco García-Sánchez;Rodrigo Martínez-Béjar

  • Affiliations:
  • University of Murcia, Spain;University of Murcia, Spain;University of Murcia, Spain;University of Murcia, Spain;University of Murcia, Spain

  • Venue:
  • Expert Systems with Applications: An International Journal
  • Year:
  • 2011

Quantified Score

Hi-index 12.06

Visualization

Abstract

The generation of new knowledge is continuous in biomedical domains, thus biomedical literature is becoming harder to understand. Ontologies provide vocabulary standardization, so they can be helpful to facilitate the understanding of biomedical texts. In this work, a methodology for building biomedical ontologies from texts is presented. This approach relies on natural language processing and incremental knowledge acquisition techniques to obtain the relevant concepts and relations to be included in an OWL ontology. Additionally, we provide an algorithm to connect the isolated concepts regions in the ontology using UMLS. We also discuss in this paper the experiment carried out to validate our approach and its positive results in terms of performance and scalability.