A Multilingual Ontology Matcher

State-of-the-art multilingual ontology matchers use machine translation to reduce the problem to the monolingual case. We investigate an alternative, self-contained solution based on semantic matching where labels are parsed by multilingual natural language processing and then matched using a language-independent knowledge base acting as an interlingua. As the method relies on the availability of domain vocabularies in the languages supported, matching and vocabulary enrichment become joint, mutually reinforcing tasks. In particular, we propose a vocabulary enrichment method that uses the matcher's output to detect and generate missing items semi-automatically. Vocabularies developed in this manner can then be reused for other domain-specic natural language understanding tasks.