Ontology Matching using Neural Networks: Survey and Analysis

Abstract

Ontology matching is an effective method to establish interoperability between heterogeneous ontologies. Artificial neural networks are powerful computational models biologically inspired from human brain, and the way how they learn and process information. They have proved their efficiency in many fields. In this paper, we aim at studying all the different ontology matching approaches based on neural networks, in order to conclude how to ideally make use of these machine learning models to match heterogeneous ontologies.