Automatic Knowledge Base Evolution by Learning Instances
This addresses the need for structuring rapidly growing web data automatically, though it appears incremental as it builds on existing ontology evolution techniques.
The paper tackles the challenge of fully-automated knowledge base evolution on the Semantic Web by proposing a data-driven algorithm that refines incomplete knowledge bases and RDF triples, achieving automated ontology evolution through iterative instance generalization and class matching.
Knowledge base is the way to store structured and unstructured data throughout the web. Since the size of the web is increasing rapidly, there are huge needs to structure the knowledge in a fully automated way. However fully-automated knowledge-base evolution on the Semantic Web is a major challenges, although there are many ontology evolution techniques available. Therefore learning ontology automatically can contribute to the semantic web society significantly. In this paper, we propose full-automated ontology learning algorithm to generate refined knowledge base from incomplete knowledge base and rdf-triples. Our algorithm is data-driven approach which is based on the property of each instance. Ontology class is being elaborated by generalizing frequent property of its instances. By using that developed class information, each instance can find its most relatively matching class. By repeating these two steps, we achieve fully-automated ontology evolution from incomplete basic knowledge base.