Learning Ontology Alignments Using Recursive Neural Networks

The Semantic Web is based on technologies that make the content of the Web machine-understandable. In that framework, ontological knowledge representation has become an important tool for the analysis and understanding of multimedia information. Because of the distributed nature of the Semantic Web however, ontologies describing similar fields of knowledge are being developed and the data coming from similar but non-identical ontologies can be combined only if a semantic mapping between them is first established. This has lead to the development of several ontology alignment tools. We propose an automatic ontology alignment method based on the recursive neural network model that uses ontology instances to learn similarities between ontology concepts. Recursive neural networks are an extension of common neural networks, designed to process efficiently structured data. Since ontologies are a structured data representation, the model is inherently suitable for use with ontologies.

[1]  Marco Gori,et al.  A recursive neural network model for processing directed acyclic graphs with labeled edges , 2003, Proceedings of the International Joint Conference on Neural Networks, 2003..

[2]  Steffen Staab,et al.  Handbook on Ontologies in Information Systems , 2003 .

[3]  Erhard Rahm,et al.  Similarity Flooding: A Versatile Graph Matching Algorithm (Extended Technical Report) , 2001 .

[4]  Pedro M. Domingos,et al.  Ontology Matching: A Machine Learning Approach , 2004, Handbook on Ontologies.

[5]  Mark A. Musen,et al.  Anchor-PROMPT: Using Non-Local Context for Semantic Matching , 2001, OIS@IJCAI.

[6]  Mark A. Musen,et al.  PROMPT: Algorithm and Tool for Automated Ontology Merging and Alignment , 2000, AAAI/IAAI.

[7]  Franco Scarselli,et al.  Recursive processing of cyclic graphs , 2002, Proceedings of the 2002 International Joint Conference on Neural Networks. IJCNN'02 (Cat. No.02CH37290).

[8]  Erhard Rahm,et al.  Similarity flooding: a versatile graph matching algorithm and its application to schema matching , 2002, Proceedings 18th International Conference on Data Engineering.

[9]  Franco Scarselli,et al.  Recursive Processing of Directed Acyclic Graphs , 2001, WIRN.

[10]  Alessandro Sperduti,et al.  A general framework for adaptive processing of data structures , 1998, IEEE Trans. Neural Networks.

[11]  Alessandro Sperduti,et al.  Supervised neural networks for the classification of structures , 1997, IEEE Trans. Neural Networks.