This project aims to examine measuring similarity between concepts and individuals in ontologies. As a toolbox owlready2 [1] is used.
The research began with research on existing measures [2, 3, 4, 5]. These measures can be split into three groups:
- 1. Measures for concepts' similarity:
- 1.1 Measures based only on the topological features of graphical representation of an ontology.
- 1.2 Measures based on the topological features and information content of concepts.
- 2. Measures for individuals' similarity.
The outcome of the project has been submitted to be presented as a poster during PP-RAI 2023.
1 Poznan University of Technology, Faculty of Computing and Telecommunication
- Lamy JB, Owlready: Ontology-oriented programming in Python with automatic classification and high level constructs for biomedical ontologies, In: Artificial Intelligence In Medicine, 2017
- Dekang Lin, An Information-Theoretic Definition of Similarity. In: International Conference on Machine Learning, 1998
- P. Resnik, Semantic Similarity in a Taxonomy: An Information-Based Measure and its Application to Problems of Ambiguity in Natural Language, In: Journal of Artificial Intelligence Research 11, 1999
- Amos Tversky, Features of Similarity, In: Psychological Review 84, 1977
- Zhibiao Wu and Martha Palmer, Verb Semantics and Lexical Selection In: 32nd Annual Meeting of the Association for Computational Linguistics, 1994