Concept Discovery for Language Understanding in an Information-Query Dialogue System - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2011

Concept Discovery for Language Understanding in an Information-Query Dialogue System

Nathalie Camelin
Boris Detienne
Stéphane Huet
Dominique Quadri
  • Fonction : Auteur
  • PersonId : 964572
Fabrice Lefèvre

Résumé

Most recent efficient statistical approaches for natural language understanding require a segmental annotation of training data. Such an annotation implies both to determine the concepts in a sentence and to link them to their corresponding word segments. In this paper we propose a two-steps alternative to the fully manual annotation of data: an initial unsupervised concept discovery, based on latent Dirichlet allocation, is followed by an automatic segmentation using integer linear optimisation. The relation between discovered topics and task-dependent concepts is evaluated on a spoken dialogue task for which a reference annotation is available. Topics and concepts are shown close enough to achieve a potential reduction of one half of the manual annotation cost.
Fichier principal
Vignette du fichier
KDIR11.pdf (138.01 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01314539 , version 1 (27-02-2019)

Identifiants

  • HAL Id : hal-01314539 , version 1

Citer

Nathalie Camelin, Boris Detienne, Stéphane Huet, Dominique Quadri, Fabrice Lefèvre. Concept Discovery for Language Understanding in an Information-Query Dialogue System. International Conference on Knowledge Discovery and Information Retrieval (KDIR), Oct 2011, Paris, France. ⟨hal-01314539⟩

Collections

UNIV-AVIGNON LIA
67 Consultations
78 Téléchargements

Partager

Gmail Facebook X LinkedIn More