Where are we in semantic concept extraction for Spoken Language Understanding? ⋆
| Autor: | Gaëlle Laperrière, Salima Mdhaffar, Sahar Ghannay, Bassam Jabaian, Antoine Caubrière, Yannick Estève |
|---|---|
| Přispěvatelé: | Laboratoire Interdisciplinaire des Sciences du Numérique (LISN), Institut National de Recherche en Informatique et en Automatique (Inria)-CentraleSupélec-Université Paris-Saclay-Centre National de la Recherche Scientifique (CNRS), Laboratoire Informatique d'Avignon (LIA), Avignon Université (AU)-Centre d'Enseignement et de Recherche en Informatique - CERI, CentraleSupélec-Université Paris-Saclay-Centre National de la Recherche Scientifique (CNRS) |
| Jazyk: | angličtina |
| Rok vydání: | 2021 |
| Předmět: |
FOS: Computer and information sciences
Sound (cs.SD) Computer science Process (engineering) Word error rate Context (language use) 02 engineering and technology Semantics computer.software_genre 01 natural sciences Computer Science - Sound Spoken language understanding [INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL] Named-entity recognition Audio and Speech Processing (eess.AS) 0103 physical sciences FOS: Electrical engineering electronic engineering information engineering 0202 electrical engineering electronic engineering information engineering 010301 acoustics Computer Science - Computation and Language business.industry SIGNAL (programming language) 020206 networking & telecommunications Self supervised training Task (computing) End-to-end approach Cascade approach Artificial intelligence business Computation and Language (cs.CL) computer Natural language processing Electrical Engineering and Systems Science - Audio and Speech Processing Spoken language |
| Zdroj: | SPECOM 2021 23rd International Conference on Speech and Computer SPECOM 2021 23rd International Conference on Speech and Computer, Sep 2021, Saint Petersburg, Russia Speech and Computer ISBN: 9783030878016 SPECOM |
| Popis: | 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-to-end 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. Accepted in the SPECOM 2021 conference |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|