Concepts and relations in ontologies and in other knowledge organisation systems are usually annotated with natural language labels. Most ontology matchers rely on such labels in element-level matching techniques. When labels in different languages need to be matched, however, state-of-the-art tools tend to use online machine translation services to reduce the problem to monolingual English-only matching. We investigate a different, self-contained solution based on semantic matching where labels are parsed by multilingual natural language processing and then matched using language-independent background knowledge acting as an interlingua. We evaluate and compare results produced by machine translation and by our approach using NuSM, the multilingual version of the SMATCH semantic matcher. We then combine the outputs of the two techniques in order to boost either precision or recall—the choice being driven by application needs—beyond the results produced by either technique alone.

Cross-Lingual Semantic Matching

Bella, Gabor;Giunchiglia, Fausto;
2016-01-01

Abstract

Concepts and relations in ontologies and in other knowledge organisation systems are usually annotated with natural language labels. Most ontology matchers rely on such labels in element-level matching techniques. When labels in different languages need to be matched, however, state-of-the-art tools tend to use online machine translation services to reduce the problem to monolingual English-only matching. We investigate a different, self-contained solution based on semantic matching where labels are parsed by multilingual natural language processing and then matched using language-independent background knowledge acting as an interlingua. We evaluate and compare results produced by machine translation and by our approach using NuSM, the multilingual version of the SMATCH semantic matcher. We then combine the outputs of the two techniques in order to boost either precision or recall—the choice being driven by application needs—beyond the results produced by either technique alone.
2016
Journal of Web Semantics
Elsevier
Bella, Gabor; Giunchiglia, Fausto; Mcneill, Fiona
File in questo prodotto:
Non ci sono file associati a questo prodotto.

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11572/151643
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo

Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact