Where are we in semantic concept extraction for Spoken Language Understanding? ⋆ - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

Where are we in semantic concept extraction for Spoken Language Understanding? ⋆

Résumé

Spoken language understanding (SLU) topic has seen a lot of progress these last three years, with the emergence of end-to-end neural approaches. Spoken language understanding refers to natural language processing tasks related to semantic extraction from speech signal, like named entity recognition from speech or slot filling task in a context of human-machine dialogue. Classically, SLU tasks were processed through a cascade approach that consists in applying, firstly, an automatic speech recognition process, followed by a natural language processing module applied to the automatic transcriptions. These three last years, end-toend neural approaches, based on deep neural networks, have been proposed in order to directly extract the semantics from speech signal, by using a single neural model. More recent works on self-supervised training with unlabeled data open new perspectives in term of performance for automatic speech recognition and natural language processing. In this paper, we present a brief overview of the recent advances on the French MEDIA benchmark dataset for SLU, with or without the use of additional data. We also present our last results that significantly outperform the current state-of-the-art with a Concept Error Rate (CER) of 11.2%, instead of 13.6% for the last state-of-the-art system presented this year.
Fichier principal
Vignette du fichier
2106.13045.pdf (158.05 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03372494 , version 1 (10-10-2021)

Identifiants

  • HAL Id : hal-03372494 , version 1

Citer

Sahar Ghannay, Antoine Caubrière, Salima Mdhaffar, Gaëlle Laperrière, Bassam Jabaian, et al.. Where are we in semantic concept extraction for Spoken Language Understanding? ⋆. SPECOM 2021 23rd International Conference on Speech and Computer, Sep 2021, Saint Petersburg, Russia. ⟨hal-03372494⟩
100 Consultations
191 Téléchargements

Partager

Gmail Facebook X LinkedIn More