Abstract

AbstractAs a knowledge representation tool, ontologies have been widely applied in many fields such as knowledge management and information integration, etc. Ontology measurement is an important challenge in the field of knowledge management in order to manage the development of ontology based systems and reduce the risk of project failure. This paper proposes a generic implementation framework for stable semantic ontology measurement. Through this framework, an ontology will be measured according to its semantic enriched representation model (SERM). The SERM model of an ontology can be used for stably measuring the semantics of the ontology. Then ontology metrics are integrated into the framework to measure candidate ontologies according to its SERM model. The related experiments are made to show that the framework can effectively measure the semantics of ontologies.

Highlights

  • Ontology engineering is a subfield of knowledge engineering [1,2], and has spurred the development and application of ontologies

  • Current ontology measurement is made based on original representation model (ORM) models which cannot perform stable semantic ontology measurement for more expressive ontologies, so our experiment analysis concentrates on two aspects for validating the effectiveness of our methodology

  • If the ontology metrics related to path and depth are applied for measuring the ontology, the ontology measurement based on ORM model possibly does not work

Read more

Summary

Introduction

Ontology engineering is a subfield of knowledge engineering [1,2], and has spurred the development and application of ontologies. As a knowledge representation tool, ontologies provide the shared semantic vocabulary that agrees on domains of interest. The ontologies often built in real world have more expressivity, which include many concepts residing in complex concept constructors If these approaches are used to measure more expressive ontologies, they will possibly neglect much of the implicit semantic information of ontologies. We propose a generic implementation framework for stably and automatically measuring the semantics of ontologies. An ontology transformation approach is adopted to generate the semantic enriched representation model (SERM) of an ontology.

Related work
Representation and Measurement for Ontologies
Overview of Generic Framework
Semantic Enriched Representation Model
Eliminating IR Cycles
Avoiding Double Counting
Uniqueness of SERM Models
Entity Summarization
Integrating Ontology Metrics into Framework
Experiments and Analysis
Measurement Effectiveness for Less Expressive Ontologies
Comparison between ORM and SERM Models for More Expressive Ontologies
Data Sets and Selection of Ontology Metrics
10. Conclusion
Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call