Article Preview
Top1. Introduction
In the early 2000s, Tim Berners-Lee (Hendler, Berners-Lee, & Miller, 2002) explained what could be a “semantic Web” evolution.
The evolution of the Web of documents, websites, gave access, via forms to databases. These research results, readable for humans, are “unreadable” for the machines.
The Semantic Web is defined by Berners-Lee et al (Berners-Lee, Hendler, & Lassila, 2001). as an extension of the current Web in which information is given well-defined meaning, better enabling computers and people to work in cooperation.
In the context of the semantic Web, semantic interoperability based on ontologies has become an important challenge. Today, several disciplines have emerged to improve this interoperability and solve problems of ontological heterogeneity, such as alignment, integration and fusion.
The alignment of ontologies is a complex task based on the definition of the correspondences between ontologies. It is a discipline aimed at improving interoperability between heterogeneous ontologies. It connects ontologies with each other to make integration tasks possible, information sharing between systems easier, searching for more relevant information, and so on.
At present, several methods have been proposed to solve the heterogeneity. Zghal et al. (Zghal, Yahia, Nguifo, & Slimani, 2007) and Pushpakumar et al. (Pushpakumar, Srirangam, Baba, Meenachi, & Balasubramanian, 2016) are based on the semantic and structural similarity between the entities of two ontologies. Cotterell et al. (Cotterell & Medina, 2013), Albagli et al. (Albagli, Ben-Eliyahu-Zohary, & Shimony, 2012) and Sonntag et al. (Sonntag, Hake, Fettke, & Loos, 2016) are used learning machines to classify the corresponding entities. These works give good results, but also many gaps, such as the selection of good thresholds or the use of linear classifiers. To remedy these problems, this paper presents a hybrid ontology alignment method, by calculating the terminological, extensional, structural, and linguistic similarity between the entities, to construct a similarity table.
This paper is organized as follows: Section 2 deals with similarity measurements and ontology alignment. Section 3 describes the architecture of our system and how it works. In section 4, the evaluation procedure to test the performance of our system is described. The conclusion is given in section 5.