Sahar Ghannay

According to our database, Sahar Ghannay authored at least 44 papers between 2014 and 2024.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2024

A dual task learning approach to fine-tune a multilingual semantic speech encoder for Spoken Language Understanding.

Gaëlle Laperrière, Sahar Ghannay, Bassam Jabaian, Yannick Estève

CoRR, 2024

Les petits modèles sont bons : une étude empirique de classification dans un contexte zero-shot.

Pierre Lepagnol, Thomas Gerald, Sahar Ghannay, Christophe Servan, Sophie Rosset

Proceedings of the Actes de la 31ème Conférence sur le Traitement Automatique des Langues Naturelles, 2024

Utiliser l'explicabilité des modèles pour mettre en évidence les expressions genrées dans la parole.

François Buet, Camille Guinaudeau, Cyril Grouin, Sahar Ghannay, Shin'ichi Satoh

Proceedings of the Actes de la 31ème Conférence sur le Traitement Automatique des Langues Naturelles, 2024

Nouvelle tâche sémantique pour le corpus de compréhension de parole en français MEDIA.

Nadège Alavoine, Gaëlle Laperrière, Christophe Servan, Sahar Ghannay, Sophie Rosset

Proceedings of the Actes des 35èmes Journées d'Études sur la Parole, 2024

Multi-Level Information Retrieval Augmented Generation for Knowledge-based Visual Question Answering.

Omar Adjali, Olivier Ferret, Sahar Ghannay, Hervé Le Borgne

Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, 2024

mALBERT: Is a Compact Multilingual BERT Model Still Worth It?

Christophe Servan, Sahar Ghannay, Sophie Rosset

Proceedings of the 2024 Joint International Conference on Computational Linguistics, 2024

Small Language Models Are Good Too: An Empirical Study of Zero-Shot Classification.

Pierre Lepagnol, Thomas Gerald, Sahar Ghannay, Christophe Servan, Sophie Rosset

Proceedings of the 2024 Joint International Conference on Computational Linguistics, 2024

New Semantic Task for the French Spoken Language Understanding MEDIA Benchmark.

Nadège Alavoine, Gaëlle Laperrière, Christophe Servan, Sahar Ghannay, Sophie Rosset

Proceedings of the 2024 Joint International Conference on Computational Linguistics, 2024

2023

Explicit Knowledge Integration for Knowledge-Aware Visual Question Answering about Named Entities.

Omar Adjali, Paul Grimal, Olivier Ferret, Sahar Ghannay, Hervé Le Borgne

Proceedings of the 2023 ACM International Conference on Multimedia Retrieval, 2023

Semantic Enrichment Towards Efficient Speech Representations.

Gaëlle Laperrière, Ha Nguyen, Sahar Ghannay, Bassam Jabaian, Yannick Estève

Proceedings of the 24th Annual Conference of the International Speech Communication Association, 2023

Specialized Semantic Enrichment of Speech Representations.

Gaëlle Laperrière, Ha Nguyen, Sahar Ghannay, Bassam Jabaian, Yannick Estève

Proceedings of the IEEE International Conference on Acoustics, 2023

2022

Continual Self-Supervised Domain Adaptation for End-to-End Speaker Diarization.

Juan Manuel Coria, Hervé Bredin, Sahar Ghannay, Sophie Rosset

Proceedings of the IEEE Spoken Language Technology Workshop, 2022

Impact Analysis of the Use of Speech and Language Models Pretrained by Self-Supersivion for Spoken Language Understanding.

Salima Mdhaffar, Valentin Pelloin, Antoine Caubrière, Gaëlle Laperrière, Sahar Ghannay, Bassam Jabaian, Nathalie Camelin, Yannick Estève

Proceedings of the Thirteenth Language Resources and Evaluation Conference, 2022

The Spoken Language Understanding MEDIA Benchmark Dataset in the Era of Deep Learning: data updates, training and evaluation tools.

Gaëlle Laperrière, Valentin Pelloin, Antoine Caubrière, Salima Mdhaffar, Nathalie Camelin, Sahar Ghannay, Bassam Jabaian, Yannick Estève

Proceedings of the Thirteenth Language Resources and Evaluation Conference, 2022

Benchmarking Transformers-based models on French Spoken Language Understanding tasks.

Oralie Cattan, Sahar Ghannay, Christophe Servan, Sophie Rosset

Proceedings of the 23rd Annual Conference of the International Speech Communication Association, 2022

2021

Where Are We in Semantic Concept Extraction for Spoken Language Understanding?

Sahar Ghannay, Antoine Caubrière, Salima Mdhaffar, Gaëlle Laperrière, Bassam Jabaian, Yannick Estève

Proceedings of the Speech and Computer - 23rd International Conference, 2021

Evaluating the carbon footprint of NLP methods: a survey and analysis of existing tools.

Nesrine Bannour, Sahar Ghannay, Aurélie Névéol, Anne-Laure Ligozat

Proceedings of the Second Workshop on Simple and Efficient Natural Language Processing, 2021

Overlap-Aware Low-Latency Online Speaker Diarization Based on End-to-End Local Segmentation.

Juan Manuel Coria, Hervé Bredin, Sahar Ghannay, Sophie Rosset

Proceedings of the IEEE Automatic Speech Recognition and Understanding Workshop, 2021

2020

A study of continuous space word and sentence representations applied to ASR error detection.

Sahar Ghannay, Yannick Estève, Nathalie Camelin

Speech Commun., 2020

A Comparison of Metric Learning Loss Functions for End-To-End Speaker Verification.

Juan Manuel Coria, Hervé Bredin, Sahar Ghannay, Sophie Rosset

Proceedings of the Statistical Language and Speech Processing, 2020

LIMSI_UPV at SemEval-2020 Task 9: Recurrent Convolutional Neural Network for Code-mixed Sentiment Analysis.

Somnath Banerjee, Sahar Ghannay, Sophie Rosset, Anne Vilnat, Paolo Rosso

Proceedings of the Fourteenth Workshop on Semantic Evaluation, 2020

A Metric Learning Approach to Misogyny Categorization.

Juan Manuel Coria, Sahar Ghannay, Sophie Rosset, Hervé Bredin

Proceedings of the 5th Workshop on Representation Learning for NLP, 2020

A Cooking Knowledge Graph and Benchmark for Question Answering Evaluation in Lifelong Learning Scenarios.

Mathilde Veron, Anselmo Peñas, Guillermo Echegoyen, Somnath Banerjee, Sahar Ghannay, Sophie Rosset

Proceedings of the Natural Language Processing and Information Systems, 2020

What is best for spoken language understanding: small but task-dependant embeddings or huge but out-of-domain embeddings?

Sahar Ghannay, Antoine Neuraz, Sophie Rosset

Proceedings of the 2020 IEEE International Conference on Acoustics, 2020

Error Analysis Applied to End-to-End Spoken Language Understanding.

Antoine Caubrière, Sahar Ghannay, Natalia A. Tomashenko, Renato De Mori, Antoine Laurent, Emmanuel Morin, Yannick Estève

Proceedings of the 2020 IEEE International Conference on Acoustics, 2020

Neural Networks approaches focused on French Spoken Language Understanding: application to the MEDIA Evaluation Task.

Sahar Ghannay, Christophe Servan, Sophie Rosset

Proceedings of the 28th International Conference on Computational Linguistics, 2020

Experiments from LIMSI at the French Named Entity Recognition Coarse-grained Task.

Sahar Ghannay, Cyril Grouin, Thomas Lavergne

Proceedings of the Working Notes of CLEF 2020, 2020

2019

Lifelong Learning and Task-Oriented Dialogue System: What Does It Mean?

Mathilde Veron, Sahar Ghannay, Anne-Laure Ligozat, Sophie Rosset

Proceedings of the Increasing Naturalness and Flexibility in Spoken Dialogue Interaction, 2019

2018

End-to-end named entity extraction from speech.

Sahar Ghannay, Antoine Caubrière, Yannick Estève, Antoine Laurent, Emmanuel Morin

CoRR, 2018

TED-LIUM 3: Twice as Much Data and Corpus Repartition for Experiments on Speaker Adaptation.

François Hernandez, Vincent Nguyen, Sahar Ghannay, Natalia A. Tomashenko, Yannick Estève

Proceedings of the Speech and Computer - 20th International Conference, 2018

End-To-End Named Entity And Semantic Concept Extraction From Speech.

Sahar Ghannay, Antoine Caubrière, Yannick Estève, Nathalie Camelin, Edwin Simonnet, Antoine Laurent, Emmanuel Morin

Proceedings of the 2018 IEEE Spoken Language Technology Workshop, 2018

Simulating ASR errors for training SLU systems.

Edwin Simonnet, Sahar Ghannay, Nathalie Camelin, Yannick Estève

Proceedings of the Eleventh International Conference on Language Resources and Evaluation, 2018

Task Specific Sentence Embeddings for ASR Error Detection.

Sahar Ghannay, Yannick Estève, Nathalie Camelin

Proceedings of the 19th Annual Conference of the International Speech Communication Association, 2018

2017

Étude sur les représentations continues de mots appliquées à la détection automatique des erreurs de reconnaissance de la parole. (A study of continuous word representations applied to the automatic detection of speech recognition errors).

Sahar Ghannay

PhD thesis, 2017

Enriching Confusion Networks for Post-processing.

Sahar Ghannay, Yannick Estève, Nathalie Camelin

Proceedings of the Statistical Language and Speech Processing, 2017

ASR Error Management for Improving Spoken Language Understanding.

Edwin Simonnet, Sahar Ghannay, Nathalie Camelin, Yannick Estève, Renato De Mori

Proceedings of the 18th Annual Conference of the International Speech Communication Association, 2017

2016

Utilisation des représentations continues des mots et des paramètres prosodiques pour la détection d'erreurs dans les transcriptions automatiques de la parole (Combining continuous word representation and prosodic features for ASR error detection).

Sahar Ghannay, Yannick Estève, Nathalie Camelin, Camille Dutrey, Fabian Santiago, Martine Adda-Decker

Proceedings of the Actes de la conférence conjointe JEP-TALN-RECITAL 2016. Volume 1 : JEP, 2016

Evaluation of acoustic word embeddings.

Sahar Ghannay, Yannick Estève, Nathalie Camelin, Paul Deléglise

Proceedings of the 1st Workshop on Evaluating Vector-Space Representations for NLP, 2016

Word Embedding Evaluation and Combination.

Sahar Ghannay, Benoît Favre, Yannick Estève, Nathalie Camelin

Proceedings of the Tenth International Conference on Language Resources and Evaluation LREC 2016, 2016

Acoustic Word Embeddings for ASR Error Detection.

Sahar Ghannay, Yannick Estève, Nathalie Camelin, Paul Deléglise

Proceedings of the 17th Annual Conference of the International Speech Communication Association, 2016

Recent Improvements on Error Detection for Automatic Speech Recognition.

Yannick Estève, Sahar Ghannay, Nathalie Camelin

Proceedings of the 1st International Workshop on Multimodal Media Data Analytics co-located with the 22nd European Conference on Artificial Intelligence, 2016

2015

Combining Continuous Word Representation and Prosodic Features for ASR Error Prediction.

Sahar Ghannay, Yannick Estève, Nathalie Camelin, Camille Dutrey, Fabian Santiago, Martine Adda-Decker

Proceedings of the Statistical Language and Speech Processing, 2015

Word embeddings combination and neural networks for robustness in ASR error detection.

Sahar Ghannay, Yannick Estève, Nathalie Camelin

Proceedings of the 23rd European Signal Processing Conference, 2015

2014

Using Hypothesis Selection Based Features for Confusion Network MT System Combination.

Sahar Ghannay, Loïc Barrault

Proceedings of the 3rd Workshop on Hybrid Approaches to Machine Translation, 2014