Light-Weight Cross-Lingual Ontology Matching with LYAM++ - LIRMM - Laboratoire d’Informatique, de Robotique et de Microélectronique de Montpellier Access content directly
Conference Papers Year : 2015

Light-Weight Cross-Lingual Ontology Matching with LYAM++

Abstract

During the last decade, several automatic ontology matching systems were developed to address the problem of ontology heterogene-ity. Aligning cross-lingual ontologies is among the current challenging issues in the field of ontology matching. The majority of the existing approaches rely on machine translation to deal with this problem. However, inherent problems of machine translation are imprecision and ambiguity. In this paper, we propose a novel approach to the cross-lingual ontol-ogy matching task, relying on the large multilingual semantic network BabelNet as a source of background knowledge to assist the matching process. We have designed and tested a novel orchestration of the components of the matching workflow. Our approach is implemented under the form of a prototype named LYAM++ (Yet Another Matcher–Light)— a fully automatic cross-lingual ontology matching system that does not rely on machine translation. We report the results of our experiments that show that LYAM++ outperforms considerably the best techniques in the state-of-the-art according to the obtained results on the MultiFarm datasets of the Ontology Alignment Evaluation Initiative 2014.
Fichier principal
Vignette du fichier
cr.pdf (454.53 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

lirmm-01408025 , version 1 (02-12-2016)

Identifiers

Cite

Abdel Nasser Tigrine, Zohra Bellahsene, Konstantin Todorov. Light-Weight Cross-Lingual Ontology Matching with LYAM++. ODBASE: Ontologies, DataBases, and Applications of Semantics, Oct 2015, Rhodos, Greece. pp.527-544, ⟨10.1007/978-3-319-26148-5_36⟩. ⟨lirmm-01408025⟩
169 View
470 Download

Altmetric

Share

Gmail Facebook X LinkedIn More