An Information Extraction Process for Semi-automatic Ontology Population

Most knowledge is available in unstructured texts, however, it must be represented and handled automatically to become truly useful for the construction knowledge-based systems. Ontologies are an approach for knowledge representation capable of expressing a set of entities and their relationships, constraints, axioms and vocabulary of a given domain. Ontology population looks for identifying instances of concepts, relationships and properties of an ontology. Manual population by domain experts and knowledge engineers is an expensive and time consuming task so, automatic or semi-automatic approaches are needed. This article proposes a process for semi-automatic population of ontologies from text focusing on the application of natural language processing and information extraction techniques to acquire and classify ontology instances. Some experiments using a legal corpus were conducted in order to evaluate it. Initial results are promising and indicate that our approach can extract instances with high effectiveness.