Advertisement

Automatic Extraction of Axioms from Wikipedia Using SPARQL

  • Lara Haidar-AhmadEmail author
  • Amal Zouaq
  • Michel Gagnon
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9989)

Abstract

Building rich axiomatic ontologies automatically is a step towards the realization of the Semantic Web. In this paper, we describe an automatic approach to extract complex classes’ axioms from Wikipedia definitions based on recurring syntactic structures. The objective is to enrich DBpedia concept descriptions with formal definitions. We leverage RDF to build a sentence representation and SPARQL to model patterns and their transformations, thus easing the querying of syntactic structures and the reusability of the extracted patterns. Our preliminary evaluation shows that we obtain satisfying results, which will be further improved.

Keywords

Query Answering Complete Axiom Ontology Learning Class Axiom Lightweight Ontology 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Notes

Acknowledgement

This research has been funded by the NSERC Discovery Grant Program.

References

  1. 1.
    De Marneffe, M.-C., Manning, C. D.: The Stanford typed dependencies representation. In: Proceedings of the Workshop on Cross-Framework and Cross-Domain Parser Evaluation. ACL (2008)Google Scholar
  2. 2.
    Bühmann, L., Fleischhacker, D., Lehmann, J., Melo, A., Völker, J.: Inductive lexical learning of class expressions. In: Janowicz, K., Schlobach, S., Lambrix, P., Hyvönen, E. (eds.) EKAW 2014. LNCS, vol. 8876, pp. 42–53. Springer, Switzerland (2014)Google Scholar
  3. 3.
    Völker, J., Haase, P., Hitzler, P.: Learning expressive ontologies. In: Proceedings of the Conference on ontology Learning and Population, pp. 45–69. IOS Press (2008)Google Scholar
  4. 4.
    Font, L., Zouaq, A., Gagnon, M.: Assessing the quality of domain concepts descriptions in DBpedia. In: SITIS 2015, pp. 254–261 (2015)Google Scholar

Copyright information

© Springer International Publishing AG 2016

Authors and Affiliations

  1. 1.Department of Computer and Software EngineeringEcole Polytechnique de MontrealMontrealCanada
  2. 2.School of Electrical Engineering and Computer ScienceUniversity of OttawaOttawaCanada

Personalised recommendations