CLOE: a cross-lingual ontology enrichment using multi-agent architecture

ABSTRACT

This article proposes across-lingual ontology enrichment (CLOE) approach for enriching ontologies from amultilingual text or other ontologies. Athree-level hierarchical multi-agent model has been built, where each node is modelled as an agent. This has several advantages: ontologies can be used to enrich other ontologies in adifferent language, several ontologies can be enriched at the same time, and domain-independent. A prototype for the proposed approach has been implemented. Evaluation results are promising, showing considerable precision and recall scores. We believe that this approach is the first such attempt to enrich multiple ontologies using adomain-independent approach.

KEYWORDS:

• Cross-lingual ontology enrichment
• natural language processing
• semantic web
• knowledge management
• ontology mapping

Acknowledgments

Said Fathalla and Shimaa Ibrahim would like to thank and acknowledge the Ministry of Higher Education (MoHE) of Egypt for providing scholarships to conduct this study as well as the University of Bonn, Germany for offering all facilities required to do this work.

Disclosure statement

No potential conflict of interest was reported by the authors.

Notes

1. https://opennlp.apache.org/docs/1.8.2/apidocs/opennlp-tools/overview-summary.html.

2. https://tika.apache.org/1.17/api/.

3. https://developers.google.com/api-client-library/java/apis/translate/v2.

4. https://goo.gl/DnnPnv.

5. http://qwone.com/ jason/20Newsgroups/.