Evaluating ontology extraction tools using a comprehensive evaluation framework

Abstract

Ontologies are a key component of the Semantic Web; thus, they are widely used in various applications. However, most ontologies are still built manually, a time-consuming activity which requires many resources. Several tools such as ontology editing tools, ontology merging tools, and ontology extraction tools have therefore been proposed to speed up ontology development. To minimize building time, one promising solution is the automation of the ontology development process. Consequently, the need for an automatic ontology extraction tool has increased in the last two decades and many tools have been developed for this purpose. However, there is still no comprehensive framework for evaluating such tools. In this paper, we proposed a set of criteria for evaluating ontology extraction tools and carried out an evaluation experiment on four ontology extraction tools (i.e., OntoLT, Text2Onto, OntoBuilder, and DODDLE-OWL) using our proposed evaluation framework. Based on the results of our experiment, we concluded that ontology extraction tools still lack the ability to automate the extraction process fully and thus require functional performance improvement.