Communication Dans Un Congrès Année : 2015

Domain-adapted named-entity linker using Linked Data

Résumé

We present REDEN, a tool for graph-based Named Entity Linking that allows for the disambiguation of entities using domainspecific Linked Data sources and different configurations (e.g. context size). It takes TEI-annotated texts as input and outputs them enriched with external references (URIs). The possibility of customizing indexes built from various knowledge sources by defining temporal and spatial extents makes REDEN particularly suited to handle domain-specific corpora such as enriched digital editions in the Digital Humanities.

Domaines

Fichier principal
Vignette du fichier
named_entity.pdf (295.91 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence
Loading...

Dates et versions

hal-01203356 , version 1 (22-09-2015)

Licence

Identifiants

  • HAL Id : hal-01203356 , version 1

Citer

Francesca Frontini, Carmen Brando, Jean-Gabriel Ganascia. Domain-adapted named-entity linker using Linked Data. Workshop on NLP Applications: Completing the Puzzle co-located with the 20th International Conference on Applications of Natural Language to Information Systems (NLDB 2015), Jun 2015, Passau, Germany. ⟨hal-01203356⟩
409 Consultations
331 Téléchargements

Partager

  • More