Language-based Construction of Explorable News Graphs for Journalists - Université de Nantes Accéder directement au contenu
Communication Dans Un Congrès Année : 2017

Language-based Construction of Explorable News Graphs for Journalists

Résumé

Faced with ever-growing news archives, media professionals are in need of advanced tools to explore the information surrounding specific events. This problem is most commonly answered by browsing news datasets, going from article to article and viewing unaltered original content. In this article, we introduce an efficient way to generate links between news items, allowing such browsing through an easily explorable graph, and enrich this graph by automatically typing links in order to inform the user on the nature of the relation between two news pieces. User evaluations are conducted on real world data with journalists in order to assess for the interest of both the graph representation and link typing in a press reviewing task, showing the system to be of significant help for their work.
Fichier principal
Vignette du fichier
EMNLP_2017_Workshop.pdf (524.02 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01578932 , version 1 (30-08-2017)

Identifiants

  • HAL Id : hal-01578932 , version 1

Citer

Rémi Bois, Guillaume Gravier, Eric Jamet, Maxime Robert, Emmanuel Morin, et al.. Language-based Construction of Explorable News Graphs for Journalists. Empirical Methods in Natural Language Processing - Workshop on Natural Language Processing meets Journalism, 2017, Copenhague, Denmark. ⟨hal-01578932⟩
771 Consultations
163 Téléchargements

Partager

Gmail Facebook X LinkedIn More