Bayesian Networks for Matcher Composition in Automatic Schema Matching

Daniel Nikovski, Alan Esenther, Xiang Ye, Mitsuteru Shiba, Shigenobu Takayama

2012

Abstract

We propose a method for accurate combining of evidence supplied by multiple individual matchers regarding whether two data schema elements match (refer to the same object or concept), or not, in the field of automatic schema matching. The method uses a Bayesian network to model correctly the statistical correlations between the similarity values produced by individual matchers that use the same or similar information, in order to avoid overconfidence in match probability estimates and improve the accuracy of matching. Experimental results under several testing protocols suggest that the matching accuracy of the Bayesian composite matcher can significantly exceed that of the individual component matchers.

Paper Citation

in Harvard Style

Nikovski D., Esenther A., Ye X., Shiba M. and Takayama S. (2012). Bayesian Networks for Matcher Composition in Automatic Schema Matching . In Proceedings of the 14th International Conference on Enterprise Information Systems - Volume 1: ICEIS, ISBN 978-989-8565-10-5, pages 48-55. DOI: 10.5220/0004001500480055

in Bibtex Style

@conference{iceis12,
author={Daniel Nikovski and Alan Esenther and Xiang Ye and Mitsuteru Shiba and Shigenobu Takayama},
title={Bayesian Networks for Matcher Composition in Automatic Schema Matching},
booktitle={Proceedings of the 14th International Conference on Enterprise Information Systems - Volume 1: ICEIS,},
year={2012},
pages={48-55},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004001500480055},
isbn={978-989-8565-10-5},
}

in EndNote Style

TY - CONF
JO - Proceedings of the 14th International Conference on Enterprise Information Systems - Volume 1: ICEIS,
TI - Bayesian Networks for Matcher Composition in Automatic Schema Matching
SN - 978-989-8565-10-5
AU - Nikovski D.
AU - Esenther A.
AU - Ye X.
AU - Shiba M.
AU - Takayama S.
PY - 2012
SP - 48
EP - 55
DO - 10.5220/0004001500480055