Semantic Web Dog Food

Presented at: 5th European Semantic Web Conference (ESWC2008)

by Mauricio Espinoza, Asuncion Gomez-Perez, Eduardo Mena

Typically ontologies are described in a determined natural language. Organizations working in a multilingual environment demand multilingual ontologies. To solve this problem we propose LabelTranslator, a NeOn plug-in that automatically localize ontologies. Ontology localization consists in adapting an ontology to a concrete language and culture community. LabelTranslator takes as input an ontology whose labels are described in a source natural language and obtains the most probable translation of each ontology label in a target natural language. Our main contribution is the automatization of this process which reduces human efforts to localize manually the ontology. First, our system uses a translation service which obtains automatic translations of each ontology label (name of an ontology term) in English, German, or Spanish by consulting different linguistic resources such as lexical databases, bilingual dictionaries, and terminologies. Second, a ranking method is used to sort each ontology label according to similarity with its lexical and structural context. The experiments performed in order to evaluate the quality of translation show that our approach is a good approximation to enrich an ontology with multilingual information.

Keywords: multilingual ontologies, ontology localization, Natural language processing, Natural Language Processing, NLP, Ontology (computer science), Ontology (Computer Science), Semantic Web, Web Ontology Language

Resource URI on the dog food server: http://data.semanticweb.org/conference/eswc/2008/paper/284
Same as: http://revyu.com/things/eswc-2008-paper-enriching-an-information
Same as: http://semanticweb.org/id/Enriching_an_Ontology_with_Multilingual_Information

Explore this resource elsewhere:

• on Snorql
• on VisiNav
• on Sindice