Exploring the use of Attention-Based Recurrent Neural Networks For Spoken Language Understanding - Archive ouverte HAL Access content directly
Conference Papers Year : 2015

Exploring the use of Attention-Based Recurrent Neural Networks For Spoken Language Understanding

Abstract

This study explores the use of a bidirectional recurrent neural network (RNN) encoder/decoder based on a mechanism of attention for a Spoken Language Understanding (SLU) task. First experiments carried on the ATIS corpus confirm the quality of the RNN baseline system used in this paper, by comparing its results on the ATIS corpus to the results recently published in the literature. Additional experiments show that RNN based on a mechanism of attention performs better than RNN architectures recently proposed for a slot filling task. On the French MEDIA corpus, a French state-of-the-art corpus for SLU dedicated to hotel reservation and tourist information, experiments show that a bidirectionnal RNN reaches a f-measure value of 79.51 while the use of a mechanism of attention allows us to reach a f-measure value of 80.27.
Fichier principal
Vignette du fichier
nips15.pdf (189.15 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01433202 , version 1 (09-11-2020)

Identifiers

  • HAL Id : hal-01433202 , version 1

Cite

Edwin Simonnet, Nathalie Camelin, Paul Deléglise, Yannick Estève. Exploring the use of Attention-Based Recurrent Neural Networks For Spoken Language Understanding. Machine Learning for Spoken Language Understanding and Interaction NIPS 2015 workshop (SLUNIPS 2015), 2015, Montreal, Canada. ⟨hal-01433202⟩
510 View
110 Download

Share

Gmail Facebook X LinkedIn More