no code implementations • LREC 2022 • Gaëlle Laperrière, Valentin Pelloin, Antoine Caubrière, Salima Mdhaffar, Nathalie Camelin, Sahar Ghannay, Bassam Jabaian, Yannick Estève
In this paper, we focus on the French MEDIA SLU dataset, distributed since 2005 and used as a benchmark dataset for a large number of research works.
no code implementations • LREC 2022 • Salima Mdhaffar, Valentin Pelloin, Antoine Caubrière, Gaëlle Laperriere, Sahar Ghannay, Bassam Jabaian, Nathalie Camelin, Yannick Estève
Pretrained models through self-supervised learning have been recently introduced for both acoustic and language modeling.
no code implementations • 3 Jul 2023 • Gaëlle Laperrière, Ha Nguyen, Sahar Ghannay, Bassam Jabaian, Yannick Estève
Over the past few years, self-supervised learned speech representations have emerged as fruitful replacements for conventional surface representations when solving Spoken Language Understanding (SLU) tasks.
no code implementations • 25 Oct 2021 • Matthieu Riou, Bassam Jabaian, Stéphane Huet, Fabrice Lefèvre
The analysis of these experiments gives us some insights, discussed in the paper, into the difficulty for the system's trainers to establish a coherent and constant behavioural strategy to enable a fast and good-quality training phase.
no code implementations • 24 Jun 2021 • Sahar Ghannay, Antoine Caubrière, Salima Mdhaffar, Gaëlle Laperrière, Bassam Jabaian, Yannick Estève
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.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +7
no code implementations • 14 Feb 2020 • Marco Dinarelli, Nikita Kapoor, Bassam Jabaian, Laurent Besacier
For that, in many cases, models are combined with an external language model to enhance their performance.
no code implementations • 1 Oct 2018 • Matthieu Riou, Bassam Jabaian, Stéphane Huet, Fabrice Lefèvre
Several variants of joint learning are investigated and tested with user trials to confirm that the overall on-line learning can be obtained after only a few hundred training dialogues and can overstep an expert-based system.
no code implementations • JEPTALNRECITAL 2017 • Matthieu Riou, Bassam Jabaian, St{\'e}phane Huet, Fabrice Lef{\`e}vre
R{\'e}cemment, de nouveaux mod{\`e}les {\`a} base de r{\'e}seaux de neurones r{\'e}currents ont {\'e}t{\'e} propos{\'e}s pour traiter la g{\'e}n{\'e}ration en langage naturel dans des syst{\`e}mes de dialogue (Wen et al., 2016a).
no code implementations • 21 Feb 2017 • Luis Adrián Cabrera-Diego, Stéphane Huet, Bassam Jabaian, Alejandro Molina, Juan-Manuel Torres-Moreno, Marc El-Bèze, Barthélémy Durette
This year, the DEFT campaign (D\'efi Fouilles de Textes) incorporates a task which aims at identifying the session in which articles of previous TALN conferences were presented.
no code implementations • JEPTALNRECITAL 2016 • Emmanuel Ferreira, Alex Reiffers-Masson, re, Bassam Jabaian, Fabrice Lef{\`e}vre
De nombreux modules de compr{\'e}hension de la parole ont en commun d{'}{\^e}tre probabilistes et bas{\'e}s sur des algorithmes d{'}apprentissage automatique.
no code implementations • LREC 2016 • Elena Manishina, Bassam Jabaian, St{\'e}phane Huet, Fabrice Lef{\`e}vre
As data-driven approaches started to make their way into the Natural Language Generation (NLG) domain, the need for automation of corpus building and extension became apparent.
no code implementations • JEPTALNRECITAL 2015 • Emmanuel Ferreira, Bassam Jabaian, Fabrice Lef{\`e}vre
Cette m{\'e}thode combine une description ontologique minimale de la t{\^a}che vis{\'e}e avec l{'}utilisation d{'}un espace s{\'e}mantique continu appris par des approches {\`a} base de r{\'e}seaux de neurones {\`a} partir de donn{\'e}es g{\'e}n{\'e}riques non-annot{\'e}es.
no code implementations • JEPTALNRECITAL 2014 • Luis Adri{\'a}n Cabrera-Diego, St{\'e}phane Huet, Bassam Jabaian, Alej Molina, ro, Juan-Manuel Torres-Moreno, Marc El-B{\`e}ze, Barth{\'e}l{\'e}my Durette
no code implementations • JEPTALNRECITAL 2012 • Fabrice Lef{\`e}vre, Djamel Mostefa, Laurent Besacier, Yannick Est{\`e}ve, Matthieu Quignard, Nathalie Camelin, Benoit Favre, Bassam Jabaian, Lina Rojas-Barahona
no code implementations • LREC 2012 • Fabrice Lef{\`e}vre, Djamel Mostefa, Laurent Besacier, Yannick Est{\`e}ve, Matthieu Quignard, Nathalie Camelin, Benoit Favre, Bassam Jabaian, Lina M. Rojas-Barahona
The PORTMEDIA project is intended to develop new corpora for the evaluation of spoken language understanding systems.