2008 AnEmpiricalStudyOfInstanceBasedOntMatch

From GM-RKB
Jump to navigation Jump to search

Subject Headings: Instance-based Concept Mapping Task, Empirical Evaluation.

Notes

Quotes

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.

Introduction

Ontology mapping is the task of determining relations such as equivalence or subsumption between concepts of two separate ontologies.

Ontology mapping techniques are commonly divided into 4 broad categories:

  • lexical (detecting similarities between labels of concepts),
  • structural (using the structure of the ontologies),
  • based on background knowledge,
  • instance-based mapping (using classified instance data).

The basic idea of instance-based mapping is that the more significant the overlap of common instances of two concepts is, the more related these concepts are. The difficult question is how to define the notion of significance for such extension overlap. Previous investigations on instance-based mapping [2, 3] have shown that there are some crucial decisions to be made with this respect.

References

  • 1. Euzenat, J., Shvaiko, P.: Ontology Matching. Springer (2007)
  • 2. Vizine-Goetz, D.: Popular LCSH with Dewey Numbers: Subject headings for everyone. Annual Review of OCLC Research (1997)
  • 3. Avesani, P., Giunchiglia, F., Yatskevich, M.: A large scale taxonomy mapping evaluation. In: International Semantic Web Conference (ISWC), Galway (2005)
  • 4. Isaac, A., Matthezing, H., van der Meij, L., Schlobach, S., Wang, S., Zinn, C.: The value of usage scenarios for thesaurus alignment in cultural heritage context. Under submission.
  • 5. Pavel Shvaiko, and Jérôme Euzenat. (2005). “A Survey of Schema-based Matching Approaches.” In: Journal of Data Semantics, 4.
  • 6. Doerr M.: Semantic problems of thesaurus mapping. Journal of Digital Information 1(8) (2004)
  • 7. Christopher D. Manning, Schütze, H.: Foundations of Statistical Natural Language Processing. MIT Press, Cambridge, MA (1999)
  • 8. van Gendt, M., Isaac, A., van der Meij, L., Schlobach S.: Semantic Web Techniques for Multiple Views on Heterogeneous Collections: a Case Study. In: 10th European Conference on Digital Libraries (ECDL), Alicante, Spain (2006)
  • 9. Euzenat, J., Mochol, M., Shvaiko, P., Stuckenschmidt, H., vb, O., Svtek, V., van Hage, W.R., Yatskevich, M.: Results of the ontology alignment evaluation initiative (2006). In: Proceedings of the Ontology Matching Workshop at ISWC’06. (2006),


 AuthorvolumeDate ValuetitletypejournaltitleUrldoinoteyear
2008 AnEmpiricalStudyOfInstanceBasedOntMatchAntoine Isaac
Lourens van der Meij
Stefan Schlobach
Shenghui Wang
An Empirical Study of Instance-based Ontology Matchinghttp://www.few.vu.nl/~aisaac/papers/STITCH-Instance-ISWC07.pdf