Using lexico-syntactic ontology design patterns for ontology creation and population
Diana Maynard, Adam Funk, Wim Peters · 2009
Abstract. In this paper we discuss the use of information extraction techniques involving lexico-syntactic patterns to generate ontological information from unstructured text and either create a new ontology from scratch or augment an existing ontology with new entities. We refine the patterns using a term extraction tool and some semantic restrictions derived from WordNet and VerbNet, in order to prevent the overgeneration that occurs with the use of the Ontology Design Patterns for this purpose. We present two applications developed in GATE and available as plugins for the NeOn Toolkit: one for general use on all kinds of text, and one for specific use in the fisheries domain. Key words: natural language processing, relation extraction, ontology