Ontology Learning Algorithms

Abstract

This chapter presents the ontology learning algorithms developed and used in the context of the ontology learning framework. According to the phases of the ontology learning cycle described in chapter 4 a bundle of algorithms is presented that support ontology extraction and maintenance. An important aspect of all algorithms is that they support the idea of an “incremental growing ontology structure”. In the last chapter it has been introduced how existing ontologies may be imported and used within our framework as background knowledge. The reader may note that all algorithms presented also work without any given conceptual structures in the form of a baseline ontology. However, if some kind of conceptual structures are available, the algorithms profit from the existing background knowledge (e.g. in the form of already existing conceptual structures such as a concept hierarchy) for the generation of further conceptual structures building on the existing ones.KeywordsAssociation RuleKullback Leibler DivergenceConcept HierarchyTaxonomic RelationOntology EngineeringThese keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.