Abstract
Ontology matching is an effective method to realize intercommunication and interoperability between heterogeneous systems. The essence of ontology matching is to discover the similar entity pairs between source ontology and target ontology, which is a process calculating the similarity between entities in ontologies. The similarity can be calculated utilizing various features between entity pairs, such as string similarity, structural similarity, and semantic similarity. The larger the ontology scale, the lower the efficiency and accuracy rate of ontology matching. As the ontology scale increases, the amount of entities in ontologies will be larger and the ontologies will become more heterogeneous. This paper proposes an innovative method of matching large scale ontologies based on filter and verification, which firstly reduces the heterogeneous of large scale ontologies in the filter phase and then matches the reduced ontologies in the verification phase. Large scale ontologies will be partitioned into several subontologies to get a proper scale before matching. The benchmark of Anatomy and Food in OAEI is adopted to evaluate the proposed method, and the experimental result illuminates that the recall rate is improved in the situation of retaining efficiency and accuracy rate using the proposed method.
Highlights
Ontology matching can solve the problems of intercommunication and interoperability between heterogeneous systems
Aiming at solving the problems existing in large-scale ontology matching, a method of matching large-scale ontologies based on filter and verification was proposed in this paper. e proposed method included two phases: filter phase and verification phase
Ontology was partitioned into several subontologies
Summary
Ontology matching can solve the problems of intercommunication and interoperability between heterogeneous systems. While the degree of heterogeneity between ontologies is increasing, as previously mentioned, a mass of entities lost their candidate access by this strategy, which results in reducing the recall rate of ontology matching. Is approach firstly partitioned large-scale ontology to some blocks and matched pairs of blocks to generate alignments. A method of matching large-scale ontologies based on filter and verification is proposed It reduces the heterogeneity by partitioning ontologies into several subontologies not blocks. The entities are allowed to appear in different subontologies repetitively which is the key cause to improve the recall rate of large-scale ontology matching. 3. Framework e framework of the proposed method deploys the filter and verification strategy whose main idea is to reduce the scale of ontologies before matching them. (53) subOntoSetTO blockSetTO (54) //Step 5: matching sub-ontologies (55) for every pair sub-ontologies (subSO[i], subTO[i]) in subOntoSetSO, subOntoSetTO: (56) //matchStruc by V-DOC in [18]. (57) structureAlignment matchStruc(subSO[i], subTO[i]) (58) //matchSema by GMO in [19]. (59) sematicAlignment matchSema(subSO[i], subTO[i], structureAlignment) (60) A.add(structureAlignment), A.add(sematicAlignment) (61) end for ALGORITHM 1: Pseudocode description of the framework
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
