Accéder directement au contenu Accéder directement à la navigation
Communication dans un congrès

What is best for Spoken Language Understanding: Small but Task-dependant Embeddings or Huge but Out-of-domain Embeddings?

Abstract : Word embeddings are shown to be a great asset for several Natural Language and Speech Processing tasks. While they are already evaluated on various NLP tasks, their evaluation on spoken or natural language understanding (SLU) is less studied. The goal of this study is two-fold: firstly, it focuses on semantic evaluation of common word embeddings ap- proaches for SLU task; secondly, it investigates the use of two different data sets to train the embeddings: small and task-dependent corpus or huge and out-of-domain corpus. Experiments are carried out on 5 benchmark corpora (ATIS, SNIPS, SNIPS70, M2M, MEDIA), on which a relevance ranking was proposed in the literature. Interestingly, the per- formance of the embeddings is independent of the difficulty of the corpora. Moreover, the embeddings trained on huge and out-of-domain corpus yields to better results than the ones trained on small and task-dependent corpus.
Type de document :
Communication dans un congrès
Liste complète des métadonnées

Littérature citée [25 références]  Voir  Masquer  Télécharger

https://hal.archives-ouvertes.fr/hal-02503694
Contributeur : Limsi Publications <>
Soumis le : mardi 10 mars 2020 - 10:53:07
Dernière modification le : mercredi 14 octobre 2020 - 04:20:39
Archivage à long terme le : : jeudi 11 juin 2020 - 14:27:11

Fichier

isSLUEmb-6.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-02503694, version 1

Citation

Sahar Ghannay, Antoine Neuraz, Sophie Rosset. What is best for Spoken Language Understanding: Small but Task-dependant Embeddings or Huge but Out-of-domain Embeddings?. IEEE International Conference on Acoustics, Speech, and Signal Processing, May 2020, Barcelone, Spain. ⟨hal-02503694⟩

Partager

Métriques

Consultations de la notice

106

Téléchargements de fichiers

229