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

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.
Document type :
Conference papers
Complete list of metadatas

Cited literature [19 references]  Display  Hide  Download

https://hal.inria.fr/hal-01351733
Contributor : Vedran Vukotić <>
Submitted on : Thursday, August 4, 2016 - 4:09:52 PM
Last modification on : Friday, March 22, 2019 - 11:34:07 AM
Long-term archiving on : Tuesday, November 8, 2016 - 8:36:15 PM

File

Vukotic_Interspeech_2016.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01351733, version 1

Citation

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⟩

Share

Metrics

Record views

1540

Files downloads

601