Modelling Ontology Evaluation and Validation

We present a comprehensive approach to ontology evaluation and validation, which have become a crucial problem for the development of semantic technologies. Existing evaluation methods are integrated into one sigle framework by means of a formal model. This model consists, firstly, of a meta-ontology called O2, that characterises ontologies as semiotic objects. Based on O2 and an analysis of existing methodologies, we identify three main types of measures for evaluation: structural measures, that are typical of ontologies represented as graphs; functional measures, that are related to the intended use of an ontology and of its components; and usability-profiling measures, that depend on the level of annotation of the considered ontology. The meta-ontology is then complemented with an ontology of ontology validation called oQual, which provides the means to devise the best set of criteria for choosing an ontology over others in the context of a given project. Finally, we provide a small example of how to apply oQual-derived criteria to a validation case.

[1]  D. Bernardi.  Reasoning on UML Class Diagrams using Description Logic Based Systems , 2001 .

[2]  Yorick Wilks,et al.  Data Driven Ontology Evaluation , 2004, LREC.

[3]  Asunción Gómez-Pérez,et al.  Ontology Evaluation , 2004, Handbook on Ontologies.

[4]  Nicola Guarino,et al.  Won-derWeb Deliverable D17: The WonderWeb Library of Foundational Ontologies , 2002 .

[5]  Asunción Gómez-Pérez,et al.  ONTOMETRIC: A Method to Choose the Appropriate Ontology , 2004, J. Database Manag..

[6]  Luc Steels,et al.  Components of Expertise , 1990, AI Mag..

[7]  Aldo Gangemi,et al.  Ontology Design Patterns for Semantic Web Content , 2005, SEMWEB.

[8]  Letha H. Etzkorn,et al.  Cohesion Metrics for Ontology Design and Application , 2005 .

[9]  Aldo Gangemi,et al.  Ontology evaluation and validation An integrated formal model for the quality diagnostic task , 2005 .

[10]  Nicola Guarino,et al.  Supporting ontological analysis of taxonomic relationships , 2001, Data Knowl. Eng..

[11]  Giuseppe De Giacomo,et al.  Reasoning on UML Class Diagrams using Description Logic Based Systems , 2001 .

[12]  Michael Uschold,et al.  Ontologies: principles, methods and applications , 1996, The Knowledge Engineering Review.

[13]  Jukka Hyönä,et al.  Perspective Effects on Online Text Processing , 2002 .

[14]  Massimo Poesio,et al.  Attribute-Based and Value-Based Clustering: An Evaluation , 2004, EMNLP.

[15]  Aldo Gangemi,et al.  Unsupervised Learning of Semantic Relations between Concepts of a Molecular Biology Ontology , 2005, IJCAI.

[16]  Nicola Guarino,et al.  WonderWeb Deliverable D18 Ontology Library , 2003 .

[17]  Mark A. Musen,et al.  Ontology versioning in an ontology management framework , 2004, IEEE Intelligent Systems.

[18]  R. Porzel,et al.  A Task-based Approach for Ontology Evaluation , 2022 .

[19]  Asunción Gómez-Pérez,et al.  Ontology Metadata Vocabulary and Applications , 2005, OTM Workshops.

[20]  Asunción Gómez-Pérez,et al.  Why Evaluate Ontology Technologies? Because It Works! , 2004, IEEE Intell. Syst..