Large scale ontology vistualisation using ontology extraction

Abstract

The semantic web relies on ontologies to provide its required taxonomies. Often, ontologies tend to grow very large, introducing a number of problems. One of these problems is the difficulty in viewing and browsing of these ontologies by humans. Although visualisation techniques attempt to improve this by offering better graphical representations, they fail to fully resolve the issue, as they do not fully utilise the semantics that the ontology harbours. Ontologies are typically treated as graphs, which are unable to express and utilise several features that enable the rich semantics of the ontologies. This paper presents how these shortcomings can be overcome by reusing database principles. Solutions in the database for analogue problems such as Data Warehousing, to resolve information overload, are based on the notion of a view. This paper reinterprets this notion for ontologies, resulting in an ontology extraction methodology. This methodology uses optimisation schemes to allow integration and interpretation of semantic related features of ontologies. Using the methodology as a preprocessing step to visualisation, allows for better results for viewing and browsing large scale ontologies. A number of possible outcomes using this methodology are discussed.