Skip to Main content Skip to Navigation
New interface
Conference papers

Is it time to switch to Word Embedding and Recurrent Neural Networks for Spoken Language Understanding?

Vedran Vukotić 1 Christian Raymond 1 Guillaume Gravier 1 
1 LinkMedia - Creating and exploiting explicit links between multimedia fragments
Inria Rennes – Bretagne Atlantique , IRISA-D6 - MEDIA ET INTERACTIONS
Abstract : Recently, word embedding representations have been investigated for slot filling in Spoken Language Understanding, along with the use of Neural Networks as classifiers. Neural Networks , especially Recurrent Neural Networks, that are specifically adapted to sequence labeling problems, have been applied successfully on the popular ATIS database. In this work, we make a comparison of this kind of models with the previously state-of-the-art Conditional Random Fields (CRF) classifier on a more challenging SLU database. We show that, despite efficient word representations used within these Neural Networks, their ability to process sequences is still significantly lower than for CRF, while also having a drawback of higher computational costs, and that the ability of CRF to model output label dependencies is crucial for SLU.
Document type :
Conference papers
Complete list of metadata

Cited literature [19 references]  Display  Hide  Download
Contributor : Christian Raymond Connect in order to contact the contributor
Submitted on : Thursday, September 10, 2015 - 3:58:19 PM
Last modification on : Thursday, January 20, 2022 - 5:33:20 PM
Long-term archiving on: : Tuesday, December 29, 2015 - 12:06:16 AM


Files produced by the author(s)


  • HAL Id : hal-01196915, version 1


Vedran Vukotić, Christian Raymond, Guillaume Gravier. Is it time to switch to Word Embedding and Recurrent Neural Networks for Spoken Language Understanding?. InterSpeech, Sep 2015, Dresde, Germany. ⟨hal-01196915⟩



Record views


Files downloads