A Cheap and Dirty Cross-Lingual Linking Service in the Cloud - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

A Cheap and Dirty Cross-Lingual Linking Service in the Cloud

Résumé

In this paper, we describe the application of Linguistic Linked Open Data (LLOD) technology for dynamic cross-lingual querying on demand. Whereas most related research is focusing on providing a static linking, i.e., cross-lingual inference, and then storing the resulting links, we demonstrate the application of the federation capabilities of SPARQL to perform lexical linking on the fly. In the end, we provide a baseline functionality that uses the connection of two web services-a SPARQL end point for multilingual lexical data and another SPARQL end point for querying an English language knowledge graph-in order to perform querying an English language knowledge graph using foreign language labels. We argue that, for low-resource languages where substantial native knowledge graphs are lacking, this functionality can be used to lower the language barrier by allowing to formulate cross-linguistically applicable queries mediated by a multilingual dictionary.
Fichier principal
Vignette du fichier
LDL_2022___Chiarcos___S_rasset.pdf (164.92 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03695216 , version 1 (14-06-2022)

Identifiants

  • HAL Id : hal-03695216 , version 1

Citer

Christian Chiarcos, Gilles Sérasset. A Cheap and Dirty Cross-Lingual Linking Service in the Cloud. 8th Workshop on Linked Data in Linguistics (LDL-2022), Jun 2022, Marseille, France. ⟨hal-03695216⟩
46 Consultations
56 Téléchargements

Partager

Gmail Facebook X LinkedIn More