Creating Ontologies for Content Representation—The OntoSeed Suite

Abstract

Due to the inherent difficulties associated with manual ontology building, knowledge acquisition and reuse are often seen as methods that can make this tedious process easier. In this paper we present an NLP-based method to aid ontology design in a specific setting, namely that of semantic annotation of text. The method uses the World Wide Web in its analysis of the domain-specific documents, eliminating the need for linguistic knowledge and resources, and suggests ways to specify domain ontologies in a "linguistics-friendly" format in order to improve further ontology-based natural language processing tasks such as semantic annotation. We evaluate the method on a corpora in a real-world setting in the medical domain and compare the costs and the benefits of the NLP-based ontology engineering approach against a similar reuseoriented experiment.