Unsupervised structured semantic inference for spoken dialog reservation tasks

Alejandra Lorenzo 1 Lina Rojas-Barahona 1 Christophe Cerisara 1
1 SYNALP - Natural Language Processing : representations, inference and semantics
LORIA - NLPKD - Department of Natural Language Processing & Knowledge Discovery
Abstract : This work proposes a generative model to infer latent semantic structures on top of manual speech transcriptions in a spoken dialog reservation task. The proposed model is akin to a standard semantic role labeling system, except that it is unsupervised, it does not rely on any syntactic information and it exploits concepts derived from a domain-specific ontology. The semantic structure is obtained with un- supervised Bayesian inference, using the Metropolis-Hastings sampling algorithm. It is evaluated both in terms of attachment accuracy and purity-collocation for clustering, and compared with strong baselines on the French MEDIA spoken-dialog corpus.
Type de document :
Communication dans un congrès
SIGDIAL - 14th annual SIGdial Meeting on Discourse and Dialogue - 2013, Aug 2013, Metz, France. pp.12-20, 2013
Liste complète des métadonnées

Littérature citée [18 références]  Voir  Masquer  Télécharger

https://hal.archives-ouvertes.fr/hal-00911017
Contributeur : Christophe Cerisara <>
Soumis le : jeudi 28 novembre 2013 - 15:58:46
Dernière modification le : mardi 24 avril 2018 - 13:36:30
Document(s) archivé(s) le : lundi 3 mars 2014 - 18:16:34

Fichier

sigdial2013.pdf
Fichiers éditeurs autorisés sur une archive ouverte

Identifiants

  • HAL Id : hal-00911017, version 1

Collections

Citation

Alejandra Lorenzo, Lina Rojas-Barahona, Christophe Cerisara. Unsupervised structured semantic inference for spoken dialog reservation tasks. SIGDIAL - 14th annual SIGdial Meeting on Discourse and Dialogue - 2013, Aug 2013, Metz, France. pp.12-20, 2013. 〈hal-00911017〉

Partager

Métriques

Consultations de la notice

223

Téléchargements de fichiers

404