Mind the Cultural Gap: Bridging Language-Specific DBpedia Chapters for Question Answering - INRIA - Institut National de Recherche en Informatique et en Automatique Accéder directement au contenu
Chapitre D'ouvrage Année : 2014

Mind the Cultural Gap: Bridging Language-Specific DBpedia Chapters for Question Answering

Résumé

In order to publish information extracted from language specific pages of Wikipedia in a structured way, the Semantic Web community has started an effort of internationalization of DBpedia. Language specific DBpedia chapters can contain very different information from one language to another, in particular they provide more details on certain topics, or fill information gaps. Language specific DBpedia chapters are well connected through instance interlinking, extracted from Wikipedia. An alignment between properties is also carried out by DBpedia contributors as a mapping from the terms in Wikipedia to a common ontology, enabling the exploitation of information coming from language specific DBpedia chapters. However, the mapping process is currently incomplete, it is time-consuming as it is performed manually, and it may lead to the introduction of redundant terms in the ontology. In this chapter we first propose an approach to automatically extend the existing alignments, and we then present an extension of QAKiS, a system for Question Answering over Linked Data that allows to query language specific DB-pedia chapters relying on the above mentioned property alignment. In the current version of QAKiS, English, French and German DBpedia chapters are queried using a natural language interface.
Fichier principal
Vignette du fichier
CabrioCojanGandon.pdf (490.73 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01171872 , version 1 (06-07-2015)

Identifiants

Citer

Elena Cabrio, Julien Cojan, Fabien Gandon. Mind the Cultural Gap: Bridging Language-Specific DBpedia Chapters for Question Answering. Paul Buitelaar; Philipp Cimiano. Towards the Multilingual Semantic Web, Springer-Verlag Berlin Heidelberg, 2014, ⟨10.1007/978-3-662-43585-4_9⟩. ⟨hal-01171872⟩
294 Consultations
247 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More