The Semantic Web vision grounds on providing the current Web with structural knowledge that can be understandable by the machines without the intervention of human beings. Given that ontologies are a backbone technology for the Semantic Web, different mechanisms and methodologies for designing and building ontologies have been proposed. The need for overcoming the bottleneck provoked by the manual construction of ontologies has generated several studies and research on obtaining semiautomatic methods to build ontologies. Ontology learning from Web documents is considered to be an important activity to promote the Semantic Web. In this paper, an automatic method for acquiring knowledge from Spanish texts is described. The method is based on semantic roles, which have been employed in our research for extracting semantic relations between concepts. The method makes it possible to represent multiple semantic relations. A set of experiments have been performed with the approach implemented in the oncology domain that show promising results.
Key words: Ontology learning, semantic role labeling, information extraction, semantic web, ontology.
Copyright © 2023 Author(s) retain the copyright of this article.
This article is published under the terms of the Creative Commons Attribution License 4.0