Unsupervised Web-based Automatic Annotation

The success of the Semantic Web depends both on the definition of ontologies used to represent the knowledge as on the annotations performed of the web contents. As manual approaches have low scalability, there is a need of tools capable to generate all this knowledge in an automatic and reliable way. In this paper is presented a complete algorithm to annotate web contents in an automatic and unsupervised manner. It is structured in a three-stepped procedure, based on the usage of several concept similarity measures and linguistic patterns. It is able to detect the entities to annotate, the candidate classes of these entities and, finally, associate them with the classes of an ontology. Sonic prospective results are presented.