In this paper, an improved multi-strategy ontology mapping method is proposed to improve the accuracy of the ontology mapping. The structural characteristics of ontology and the effect of instance mapping upon the similarity of ontology are considered generally. Furthermore, our approach represents and measures the structure of the conceptual nodes through the design of a “code” method, and judges the similarity of the nodes via utilizing the similarity of their ancestor nodes within the influential domain. A 1:1 mapping method is also put forward when operating the selection of initial candidates. In this paper, the tools of WordNet, Jena, protégé, etc. are employed. Finally, the experimental results show the promise of our approach and improve the recall and precision of the retrieve.
[1]
York Sure-Vetter,et al.
Ontology Mapping - An Integrated Approach
,
2004,
ESWS.
[2]
Pedro M. Domingos,et al.
Learning to map between ontologies on the semantic web
,
2002,
WWW '02.
[3]
Bo Hu,et al.
CROSI Mapping System (CMS) - Result of the 2005 Ontology Alignment Contest
,
2005,
Integrating Ontologies.
[4]
Heiner Stuckenschmidt,et al.
Applying Logical Constraints to Ontology Matching
,
2007,
KI.
[5]
Erhard Rahm,et al.
A survey of approaches to automatic schema matching
,
2001,
The VLDB Journal.