A step beyond local observations with a dialog aware bidirectional GRU network for Spoken Language Understanding - Archive ouverte HAL Access content directly
Conference Papers Year :

A step beyond local observations with a dialog aware bidirectional GRU network for Spoken Language Understanding

(1) , (2) , (1)
1
2

Abstract

Architectures of Recurrent Neural Networks (RNN) recently become a very popular choice for Spoken Language Understanding (SLU) problems; however, they represent a big family of different architectures that can furthermore be combined to form more complex neural networks. In this work, we compare different recurrent networks, such as simple Recurrent Neural Networks (RNN), Long Short-Term Memory (LSTM) networks, Gated Memory Units (GRU) and their bidirectional versions, on the popular ATIS dataset and on MEDIA, a more complex French dataset. Additionally, we propose a novel method where information about the presence of relevant word classes in the dialog history is combined with a bidirectional GRU, and we show that combining relevant word classes from the dialog history improves the performance over recurrent networks that work by solely analyzing the current sentence.
Fichier principal
Vignette du fichier
Vukotic_Interspeech_2016.pdf (1.2 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01351733 , version 1 (04-08-2016)

Identifiers

  • HAL Id : hal-01351733 , version 1

Cite

Vedran Vukotić, Christian Raymond, Guillaume Gravier. A step beyond local observations with a dialog aware bidirectional GRU network for Spoken Language Understanding. Interspeech, Sep 2016, San Francisco, United States. ⟨hal-01351733⟩
943 View
626 Download

Share

Gmail Facebook Twitter LinkedIn More