Combining Ontology Modules for Scientific Text Annotation

Abstract

Semantic annotation enables the inclusion of semantic information (ontology concepts), readable through software agents, into the most varied types of documents available on the Web. This operation facilitates search and access to relevant information. However, it is not an easy task, since the content to be annotated can be associated to multiple large ontologies. This article presents an approach based on the association of techniques and methods of ontology modularization, that enables the construction of a structure composed of concepts over one or more ontologies. This reduced structure is useful for automated semantic annotation of scientific texts. In addition, the structure attends a research specific interest. In order to evaluate this approach, a software tool was implemented. An experiment in the biomedical field, on a Corpus of 500 scientific papers, was conducted and showed good results, conforming the applicability of this approach.