A Lightweight Approach for Evaluating Sufficiency of Ontologies

Abstract

Abstract1 Ontologies have emerged as a common way of representing knowledge. Recently, people with minimal domain background or ontology engineering are developing ontologies, leading to a corpus of informal and under-evaluated ontologies. Existing ontology evaluation approaches require rigorous application of formal methods and knowledge of domain experts that can be cumbersome or tedious. We propose a lightweight approach for evaluating sufficiency of ontologies based on Natural Language Processing techniques. The approach consists of verifying the extent of coverage of concepts and relationships of ontologies against words in domain corpus. As a case study, we applied our approach to evaluate sufficiency of ontology in two example domains -Education (Curriculum) and Security (Phishing). We show that our approach yields promising results, is less effort intensive and is comparable with existing evaluation methods.

A Deep Learning Approach for Ontology Enrichment from Unstructured Text

“…5 sources. This evaluation is done without factoring sufficiency requirement [34] of new terms in text to evaluate identification of ontology terms by OntoEnricher.…”

“…The procedure to extract concepts and instances from (web page) text, during testing stage is detailed here. To avoid usage of every unstructured (web page) text to enrich an ontology, a lightweight evaluation technique [34] that checks for sufficiency of new security terms is deployed. After passing the sufficiency evaluation as a pre-processing stage, co-reference resolution is applied and then noun chunks are extracted from web page.…”