no code implementations • LREC 2016 • Sahar Ghannay, Benoit Favre, Yannick Est{\`e}ve, Nathalie Camelin
Different approaches have been introduced to calculate word embeddings through neural networks.
no code implementations • JEPTALNRECITAL 2016 • Sahar Ghannay, Yannick Est{\`e}ve, Nathalie Camelin, Camille Dutrey, Fabian Santiago, Martine Adda-Decker
Dans cet article, nous proposons d{'}{\'e}tudier leur utilisation dans une architecture neuronale pour la t{\^a}che de d{\'e}tection des erreurs au sein de transcriptions automatiques de la parole.
no code implementations • 26 May 2017 • Edwin Simonnet, Sahar Ghannay, Nathalie Camelin, Yannick Estève, Renato de Mori
This paper addresses the problem of automatic speech recognition (ASR) error detection and their use for improving spoken language understanding (SLU) systems.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +5
3 code implementations • 12 May 2018 • François Hernandez, Vincent Nguyen, Sahar Ghannay, Natalia Tomashenko, Yannick Estève
We present the recent development on Automatic Speech Recognition (ASR) systems in comparison with the two previous releases of the TED-LIUM Corpus from 2012 and 2014.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +1
no code implementations • 30 May 2018 • Sahar Ghannay, Antoine Caubrière, Yannick Estève, Antoine Laurent, Emmanuel Morin
Until now, NER from speech is made through a pipeline process that consists in processing first an automatic speech recognition (ASR) on the audio and then processing a NER on the ASR outputs.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +5
1 code implementation • 31 Mar 2020 • Juan M. Coria, Hervé Bredin, Sahar Ghannay, Sophie Rosset
Despite the growing popularity of metric learning approaches, very little work has attempted to perform a fair comparison of these techniques for speaker verification.
no code implementations • WS 2020 • Juan Manuel Coria, Sahar Ghannay, Sophie Rosset, Herv{\'e} Bredin
The task of automatic misogyny identification and categorization has not received as much attention as other natural language tasks have, even though it is crucial for identifying hate speech in social Internet interactions.
1 code implementation • 30 Aug 2020 • Somnath Banerjee, Sahar Ghannay, Sophie Rosset, Anne Vilnat, Paolo Rosso
This paper describes the participation of LIMSI UPV team in SemEval-2020 Task 9: Sentiment Analysis for Code-Mixed Social Media Text.
no code implementations • SEMEVAL 2020 • Somnath Banerjee, Sahar Ghannay, Sophie Rosset, Anne Vilnat, Paolo Rosso
This paper describes the participation of LIMSI{\_}UPV team in SemEval-2020 Task 9: Sentiment Analysis for Code-Mixed Social Media Text.
1 code implementation • COLING 2020 • Sahar Ghannay, Christophe Servan, Sophie Rosset
In this paper, we present a study on a French Spoken Language Understanding (SLU) task: the MEDIA task.
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
1 code implementation • 14 Sep 2021 • Juan M. Coria, Hervé Bredin, Sahar Ghannay, Sophie Rosset
We propose to address online speaker diarization as a combination of incremental clustering and local diarization applied to a rolling buffer updated every 500ms.
no code implementations • 19 Jul 2022 • Oralie Cattan, Sahar Ghannay, Christophe Servan, Sophie Rosset
In this paper, we propose a unified benchmark, focused on evaluating models quality and their ecological impact on two well-known French spoken language understanding tasks.
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 • 27 Mar 2024 • Christophe Servan, Sahar Ghannay, Sophie Rosset
Within the current trend of Pretained Language Models (PLM), emerge more and more criticisms about the ethical andecological impact of such models.
1 code implementation • 28 Mar 2024 • Nadège Alavoine, Gaëlle Laperriere, Christophe Servan, Sahar Ghannay, Sophie Rosset
A combination ofmultiple datasets, including the MEDIA dataset, was suggested for training this joint model.
no code implementations • 17 Apr 2024 • Pierre Lepagnol, Thomas Gerald, Sahar Ghannay, Christophe Servan, Sophie Rosset
This study is part of the debate on the efficiency of large versus small language models for text classification by prompting. We assess the performance of small language models in zero-shot text classification, challenging the prevailing dominance of large models. Across 15 datasets, our investigation benchmarks language models from 77M to 40B parameters using different architectures and scoring functions.
no code implementations • EMNLP (sustainlp) 2021 • Nesrine Bannour, Sahar Ghannay, Aurélie Névéol, Anne-Laure Ligozat
Modern Natural Language Processing (NLP) makes intensive use of deep learning methods because of the accuracy they offer for a variety of applications.
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.
1 code implementation • MMMPIE (COLING) 2022 • Juan Manuel Coria, Mathilde Veron, Sahar Ghannay, Guillaume Bernard, Hervé Bredin, Olivier Galibert, Sophie Rosset
Knowledge transfer between neural language models is a widely used technique that has proven to improve performance in a multitude of natural language tasks, in particular with the recent rise of large pre-trained language models like BERT.