Simulated Annealing-based Ontology Matching

Majid Mohammadi, Wout Hofman, Yao-Hua Tan
2019 ACM Transactions on Management Information Systems  
You share, we take care!' -Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in Ontology alignment is a fundamental task to reconcile the heterogeneity among various information systems using distinct information sources. The evolutionary algorithms (EAs) have been already considered as the primary strategy to develop an ontology alignment system. However, such systems have two significant drawbacks: they either need a ground truth that is often
more » ... le, or they utilize the population-based EAs in a way that they require massive computation and memory. This article presents a new ontology alignment system, called SANOM, which uses the well-known simulated annealing as the principal technique to find the mappings between two given ontologies while no ground truth is available. In contrast to populationbased EAs, the simulated annealing need not generate populations, which makes it significantly swift and memory-efficient for the ontology alignment problem. This article models the ontology alignment problem as optimizing the fitness of a state whose optimum is obtained by using the simulated annealing. A complex fitness function is developed that takes advantage of various similarity metrics including string, linguistic, and structural similarities. A randomized warm initialization is specially tailored for the simulated annealing to expedite its convergence. The experiments illustrate that SANOM is competitive with the state-of-the-art and is significantly superior to other EA-based systems. 3:2 M. Mohammadi et al. The heterogeneity among various data sources is a major impediment to the path of interoperability. This difference among information systems calls for the need to design an automatic solution to make them interact. Ontology matching, or alignment, is one approach to make the heterogeneous information systems interoperable by finding the semantically identical concepts of two ontologies that are stated in distinct ways. The ontology alignment systems usually take advantage of multiple similarity measures to find similar entities. However, the way to decide among various similarity measures is a fundamental issue to attack.
doi:10.1145/3314948 fatcat:se7adklo4jgxdnnmon624umr6m