Effective Spoken Language Labeling with Deep Recurrent Neural Networks - Archive ouverte HAL Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2017

Effective Spoken Language Labeling with Deep Recurrent Neural Networks

Résumé

Understanding spoken language is a highly complex problem, which can be decomposed into several simpler tasks. In this paper, we focus on Spoken Language Understanding (SLU), the module of spoken dialog systems responsible for extracting a semantic interpretation from the user utterance. The task is treated as a labeling problem. In the past, SLU has been performed with a wide variety of probabilistic models. The rise of neural networks , in the last couple of years, has opened new interesting research directions in this domain. Recurrent Neural Networks (RNNs) in particular are able not only to represent several pieces of information as embeddings but also, thanks to their recurrent architecture, to encode as embeddings relatively long contexts. Such long contexts are in general out of reach for models previously used for SLU. In this paper we propose novel RNNs architectures for SLU which outperform previous ones. Starting from a published idea as base block, we design new deep RNNs achieving state-of-the-art results on two widely used corpora for SLU: ATIS (Air Traveling Information System), in English, and MEDIA (Hotel information and reservation in France), in French.
Fichier principal
Vignette du fichier
2017_IJCAI_DeepRNNs.pdf (347.92 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01579227 , version 1 (30-08-2017)

Identifiants

  • HAL Id : hal-01579227 , version 1

Citer

Marco Dinarelli, Yoann Dupont, Isabelle Tellier. Effective Spoken Language Labeling with Deep Recurrent Neural Networks. 2017. ⟨hal-01579227⟩
75 Consultations
108 Téléchargements

Partager

Gmail Facebook X LinkedIn More