Optimizing Ontology Alignment in Vector Space

Shu-Chuan Chu, Xingsi Xue, Jeng-Shyang Pan, Xiaojing Wu

Research output: Contribution to journalArticlepeer-review

21 Citations (Scopus)

Abstract

Ontology matching technique aims at determining the identical entities, which can effectively solve the ontology heterogeneity problem and implement the collaborations among ontology-based intelligent systems. Typically, an ontology consists of a set of concepts which are described by various properties, and they define a space such that each distinct concept and property represents one dimension in that space. Therefore, it is an effective way to model an ontology in a vector space, and use the vector space based similarity measure to calculate two entities’ similarity. In this work, the entities’ structure information is utilized to model an ontology in a vector space, and then, their linguistic information is used to reduce the number of dimensions, which can improve the efficiency of the similarity calculation and entity matching process. After that, a discrete optimization model is constructed for the ontology matching problem, and a compact Evolutionary Algorithm (cEA) based ontology matching technique is proposed to efficiently address it. The experiment uses the benchmark track provided by Ontology Alignment Evaluation Initiative (OAEI) to test our proposal’s performance, and the comparing results with state-of-the-art ontology matching systems show that our approach can efficiently determine high-quality ontology alignments.
Original languageEnglish
Pages (from-to)15-22
Number of pages8
JournalJournal of Internet Technology
Volume21
Issue number1
DOIs
Publication statusPublished - Jan 2020
Externally publishedYes

Keywords

  • Ontology matching
  • Vector space
  • Compact evolutionary algorithm

Fingerprint Dive into the research topics of 'Optimizing Ontology Alignment in Vector Space'. Together they form a unique fingerprint.

Cite this