Instance-based ontology mapping is a promising family of solutions to a class of ontology alignment problems. It crucially depends on measuring the similarity between sets of annotated instances. In this paper we study how the choice of co-occurrence measures affects the performance of instance-based mapping. To this end, we have implemented a number of different statistical co-occurrence measures. We have prepared an extensive test case using vocabularies of thousands of terms, millions of instances, and hundreds of thousands of co-annotated items. We have obtained a human Gold Standard judgement for part of the mapping-space. We then study how the different co-occurrence measures and a number of algorithmic variations perform on our benchmark dataset as compared against the Gold Standard. Our systematic study shows excellent results of instance-based matching in general, where the more simple measures often outperform more sophisticated statistical co-occurrence measures.
%0 Book Section
%1 citeulike:4039753
%A Isaac, Antoine
%A van der Meij, Lourens
%A Schlobach, Stefan
%A Wang, Shenghui
%D 2008
%J The Semantic Web
%K aswc07, iswc07
%P 253--266
%R http://dx.doi.org/10.1007/978-3-540-76298-0\_19
%T An Empirical Study of Instance-Based Ontology Matching
%U http://dx.doi.org/10.1007/978-3-540-76298-0\_19
%X Instance-based ontology mapping is a promising family of solutions to a class of ontology alignment problems. It crucially depends on measuring the similarity between sets of annotated instances. In this paper we study how the choice of co-occurrence measures affects the performance of instance-based mapping. To this end, we have implemented a number of different statistical co-occurrence measures. We have prepared an extensive test case using vocabularies of thousands of terms, millions of instances, and hundreds of thousands of co-annotated items. We have obtained a human Gold Standard judgement for part of the mapping-space. We then study how the different co-occurrence measures and a number of algorithmic variations perform on our benchmark dataset as compared against the Gold Standard. Our systematic study shows excellent results of instance-based matching in general, where the more simple measures often outperform more sophisticated statistical co-occurrence measures.
@incollection{citeulike:4039753,
abstract = {Instance-based ontology mapping is a promising family of solutions to a class of ontology alignment problems. It crucially depends on measuring the similarity between sets of annotated instances. In this paper we study how the choice of co-occurrence measures affects the performance of instance-based mapping. To this end, we have implemented a number of different statistical co-occurrence measures. We have prepared an extensive test case using vocabularies of thousands of terms, millions of instances, and hundreds of thousands of co-annotated items. We have obtained a human Gold Standard judgement for part of the mapping-space. We then study how the different co-occurrence measures and a number of algorithmic variations perform on our benchmark dataset as compared against the Gold Standard. Our systematic study shows excellent results of instance-based matching in general, where the more simple measures often outperform more sophisticated statistical co-occurrence measures.},
added-at = {2009-02-13T13:22:04.000+0100},
author = {Isaac, Antoine and van der Meij, Lourens and Schlobach, Stefan and Wang, Shenghui},
biburl = {https://www.bibsonomy.org/bibtex/2a9089fb09bdd4efa8898158ea6951217/conchuir},
citeulike-article-id = {4039753},
doi = {http://dx.doi.org/10.1007/978-3-540-76298-0\_19},
interhash = {45179a67762d525b6cb36364e20f7da0},
intrahash = {a9089fb09bdd4efa8898158ea6951217},
journal = {The Semantic Web},
keywords = {aswc07, iswc07},
pages = {253--266},
posted-at = {2009-02-12 18:11:48},
priority = {2},
timestamp = {2009-02-13T13:22:05.000+0100},
title = {An Empirical Study of Instance-Based Ontology Matching},
url = {http://dx.doi.org/10.1007/978-3-540-76298-0\_19},
year = 2008
}