Enhancing domain-specific ontologies at ease

Cristian Cardellino 1 Milagro Teruel 1 Raphaël Gazzotti 2 Laura Alemany 1 Serena Villata 2
2 WIMMICS - Web-Instrumented Man-Machine Interactions, Communities and Semantics
CRISAM - Inria Sophia Antipolis - Méditerranée , SPARKS - Scalable and Pervasive softwARe and Knowledge Systems
Abstract : We present a methodology to enhance domain-specific ontologies by (i) manual annotation of texts with the concepts in the domain ontology, (ii) matching annotated concepts with the closest YAGO-Wikipedia concept and (iii) using concepts from other ontologies that cover complementary domains. This method reduces the difficulty of aligning ontologies, because the alignment is carried out within the scope of an example. The resulting alignment is a partial connection between diverse ontologies, and also a strong connection to Linked Open Data. By aligning these ontologies, we are increasing the ontological coverage for texts in that domain. Moreover, by aligning domain ontologies to the Wikipedia (via YAGO) we can obtain manually annotated examples of some of the concepts, effectively populating the ontology with examples. We present two applications of this process in the legal domain. First, we annotate sentences of the European Court of Human Rights with the LKIF ontology, at the same time matching them with the YAGO ontology. Second, we annotate a corpus of customer questions and answers from an insurance web page with the OMG ontology for the insurance domain, matching it with the YAGO ontology and complementing it with a financial ontology.
Type de document :
Communication dans un congrès
XLII CLEI | 46JAIIO, SAOA17 - Conferencia Latinoamericana de Informática | Jornadas Argentinas de Informática, Simposio Argentino de Ontologías y sus Aplicaciones, Sep 2017, Córdoba, Argentina
Liste complète des métadonnées

Littérature citée [17 références]  Voir  Masquer  Télécharger

https://hal.archives-ouvertes.fr/hal-01626620
Contributeur : Raphaël Gazzotti <>
Soumis le : mardi 31 octobre 2017 - 09:41:20
Dernière modification le : jeudi 2 novembre 2017 - 01:07:46

Fichier

enhancing-domain-specific.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01626620, version 1

Collections

Citation

Cristian Cardellino, Milagro Teruel, Raphaël Gazzotti, Laura Alemany, Serena Villata. Enhancing domain-specific ontologies at ease. XLII CLEI | 46JAIIO, SAOA17 - Conferencia Latinoamericana de Informática | Jornadas Argentinas de Informática, Simposio Argentino de Ontologías y sus Aplicaciones, Sep 2017, Córdoba, Argentina. 〈hal-01626620〉

Partager

Métriques

Consultations de la notice

66

Téléchargements de fichiers

10