Cybernetics and Computer Engineering, 2021, 3(205)
GRITSENKO V.I.1, Corresponding Member of NAS of Ukraine,
Director of International Research and Training Center for Information Technologies and Systems of the National Academy of Sciences of Ukraine and Ministry of Education and Science of Ukraine
GLADUN A.Ya.1, PhD (Engineering),
Senior Researcher of the Department of Complex Research of Information Technologies and Systems
Researcher of the Department of Complex Research of Information Technologies and Systems
Martínez-Béjar R.2, PhD (Informatics),
Professof at the Department of Information and Communication Engineering
1 International Research and Training Center for Information Technologies and Systems of the National Academy of Sciences of Ukraine and Ministry of Education and Science of Ukraine, 40, Acad. Glushkov av., Kyiv, 03187, Ukraine
2 Department of Information and Communication Engineering and Artificial Intelligence University of Murcia CP 30180 Bullas, Spain
SEMANTICAL SIMILARITY EVALUATION METHOD OF CONCEPTS FOR COMPARISON OF ONTOLOGIES IN APPLIED PROBLEMS OF ARTIFICIAL INTELLIGENCE
Introduction. The expediency of reapplication of ontology in applied intelligent information systems (IIS), which are focused on functioning in the open Web environment on the basis of Semantic Web technologies, is substantiated in the work. Features of ontology storage and management platforms and their metadata are analyzed. Possibilities of searching in ontology repositories and their reuse in IIS are considered. The mechanisms of ontology search based on semantic processing of their metadata, analysis of ontology structure using metrics of semantic similarity between their concepts related to the current user task are presented.
The purpose of the article is the development of algorithms and methods for evaluating semantic models, which consist in combining qualitative (ontological) representation of knowledge with quantitative (numerical) evaluation of ontologies and their parameters (semantic proximity, semantic distance, semantic affinity) aimed at finding similarities different ontologies
Methods. Methods of ontological analysis of objects of the subject area, theoretical and multiple approaches to determine the degree of closeness of two objects by comparing their properties (feature matching) and traditional methods of statistical analysis are used to solve the tasks set in the work.
Results. The proposed method of estimating semantic similarity allows on the basis of semantic analysis of natural annotations of metadata both ontologies and data (including Big Data) to perform the task of their interpretation and selection to the problem to be solved by the applied IIS or application. The obtained results allow to create original IIS for artificial intelligence in economics, medicine, national security, defense and social sphere.
Conclusion. We proposed an original approach to the evaluation and analysis of metadata (ontologies, data), based on semantic analysis of metadata and determining the semantic similarity of structural data models (ontologies, data) and the formation of a ranked set of related ontologies to solve problems of artificial intelligence. The application of methods for defining semantically similar concepts is presented as a tool for semantic comparison of the structure of ontologies, which were found in the repository under formal conditions, with a poorly structured PM-description. At present, there is no generally accepted standard for presenting metadata, so the proposed methods of analysis of PM annotations are the most adequate means of comparing the semantics of ontologies, data with the problems for which they can be used.
Keywords: semantic similarity, formal ontology model, metadata, metadata standards, intelligent information system, ontology repository.
1. Vasyukov V.L. Formal ontology and artificial intelligence. Moscow: IP RAS, 2006, 140 p.
2. Gladun A.Ya., Rogushina Yu.V. Ontology repositories as a means of reusing knowledge for recognizing information objects. Design Ontology. 2013, No. 1 (7), pp.35-50.
3. Torsten Hahmann Ontology repositories: A treasure trove for content ontology design patterns. Proceedigs of 8th Inter. Workshop on Modular Ontologies (WoMO-2014), Rio de Janeiro, Brazil, 2014.
4. Kenneth Baclawski Todd Schneider The open ontology repository initiative: Requirements and research challenges. Proc. 8th International Semantic Web Conference, ISWC 2009, Chantilly, VA, USA, 2010.
5. Rachel Heery, Sheila Anderson. Digital repositories review, February 2005.
6. W. H. Inmon. Building the Data Warehouse, 3rd Ed. Wiley, New York, 2002.
7. Jens Hartmann, York Sure, Raul Palma, Peter Haase, Mari Carmen Suarez-Figueroa, Rudi Studer, Asuncion Gomez-Perez. Ontology metadata vocabulary and applications. Int Conf on Ontologies, Databases and Applications of Semantics. Workshop on Web Semantics (SWWS), Oct 2005.
8. Vekhorev M.N., Panteleev M.G. Construction of repositories of ontological knowledge bases. Software products and systems. 2011, No. 3 (3), pp.67-89.
9. Taylor C. An Introduction to Metadata. The University of Queensland, Australia. URL: http://www.libraty.uq.edu.au/papers/ctmeta4.html
10. Corcho O. Ontology based document annotation: trends and open research problems. Journal of Metadata, Semantics and Ontologies. Vol. 1, Issue 1, January 2006. URL: http://www.dia.fi.upm.es/~ocorcho/documents/IJMSO2006_Corcho.pdf.
11. ISO 15489-1:2016 Information and documentation – Records management – Part 1: Concepts and principles.
12. ISO 15836-1:2017 Information and documentation – The Dublin Core metadata element set – Part 1: Core elements.
13. ISO 15836-2:2019 Information and documentation – The Dublin Core metadata element set – Part 2: DCMI Properties and
14. DSTU ISO 15489-1: 2018 Information and documentation. Records management. Part 1. Concepts and principles (ISO 15489-1: 2016, IDT).
15. DSTU ISO 15836-1: 2018 Information and documentation. Dublin Core Metadata Element Set. Part 1. Basic elements (ISO 15836-1: 2017, IDT).
16. Gladun A., Khala K., Subach I. Ontological Approach to Big Data Analytics in Cybersecurity Domain. Collection “Information Technology and Security”. 2020, Vol. 8, No. 2, pp.120-132. DOI: https://doi.org/10.20535/2411-1031.2020.8.2.222559.
URL: http://its.iszzi.kpi.ua/article/view/222559 (Last accessed: dd.mm.yyyy)
17. Obrst L., Ceusters W., Mani I., Ray S., Smith B. The evaluation of ontologies. Semantic web. 2020, pp. 139-158.
18. Gomez-Perez, A. Ontology evaluation. Handbook on ontologies. Springer, Berlin, Heidelberg, 2004, pp. 251-273
19. Leo Obrst, Werner Ceusters, Inderjeet Mani, Steve Ray, Barry Smith. The evaluation of ontologies. In Christopher J.O. Baker and Kei-Hoi Cheung, editors, Revolutionizing Knowledge Discovery in the Life Sciences, chapter 7. Springer, Berlin, 2007, pp.- 139-158.
20. Obrst, L. Ontologies for semantically interoperable systems. Proceedings of the 12th International Conference on Information and knowledge management, 2003, pp. 366-369.
21. Gangemi A., Catenacci C., Ciaramita M., Lehmann J. Modelling ontology evaluation and validation. European Semantic Web Conference. Springer, Berlin, Heidelberg, 2006, pp. 140-154.
22. Jens Hartmann, Raul Palma, and Asunci’on Gomez-Perez “Ontology Repositories”. Chapter in Handbook on Ontologies, Springer, 2009, pp 551-571.
23. Yimin Wang, Jie Bao, Peter Haase, and Guilin Qi. Evaluating formalisms for modular ontologies in distributed information systems. Proc. of the First Inter Conf on Web Reasoning and Rule Systems (RR2007), LNCS 4524, (June, 2007, Innsbruck). Innsbruck, Austria, p 178-182.
24. Jens Hartmann, Raul Palma. OMV – Ontology Metadata Vocabulary. Semantic Web. 2006, Vol. 2.0, URL: http://omv.ontoware.org/
25. Palma R., Hartmann J., Haase P. OMV Ontology Metadata Vocabulary. SemanticWeb. 2009, 76p. URL: http://kent.dl.sourceforge.net/project/omv2/OMV%20Documentation/OMV-Reportv2.4.1.pdf. (Last accessed: dd.mm.yyyy)
26. Hartmann, Jens, Raul Palma, Peter Haase, Asuncion Gomez-Perez. “Ontology Metadata Vocabulary-OMV.” 2007.
27. Welcome to OMV – Ontology Metadata Vocabulary URL: http://omv2.sourceforge.net/.
28. A.Y. Gladun, K.A. Khala Ontology-based semantic similarity to metadata analysis in the information security domain. Prombles in programming. 2021, N2, pp.34-41. DOI: htpps://doi.org/10.15407/pp2021.02.034. URL: http://pp.isofts.kiev.ua/ojs1/article/view/459
29. Tversky A. Features of Similarity. Psychological Rev. 1977, V. 84, p. 327.
30. Rogushina J. Use of Semantic Similarity Estimates for Unstructured Data Analysis. CEUR Vol-2577, Selected Papers of the XIX International Scientific and Practical Conference “Information Technologies and Security” (ITS 2019), Kyiv, 2019, pp. 246-258. URL: http://ceur-ws.org/Vol-2577/paper20.pdf.
31. A.Ya. Gladun, Yu.V. Rogushina. Development of domain thesaurus as a set of ontology concepts with use of semantic similarity and elements of combinatorial optimization. Prombles in programming. 2021, N2, pp. 3-15. DOI: htpps://doi.org/10.15407/pp2021.02.003. URL: http://pp.isofts.kiev.ua/ojs1/article/view/456