Alert button
Picture for Benoît Sagot

Benoît Sagot

Alert button

Anisotropy Is Inherent to Self-Attention in Transformers

Jan 24, 2024
Nathan Godey, Éric de la Clergerie, Benoît Sagot

Viaarxiv icon

Modular Speech-to-Text Translation for Zero-Shot Cross-Modal Transfer

Oct 05, 2023
Paul-Ambroise Duquenne, Holger Schwenk, Benoît Sagot

Figure 1 for Modular Speech-to-Text Translation for Zero-Shot Cross-Modal Transfer
Figure 2 for Modular Speech-to-Text Translation for Zero-Shot Cross-Modal Transfer
Figure 3 for Modular Speech-to-Text Translation for Zero-Shot Cross-Modal Transfer
Figure 4 for Modular Speech-to-Text Translation for Zero-Shot Cross-Modal Transfer
Viaarxiv icon

From Text to Source: Results in Detecting Large Language Model-Generated Content

Sep 23, 2023
Wissam Antoun, Benoît Sagot, Djamé Seddah

Figure 1 for From Text to Source: Results in Detecting Large Language Model-Generated Content
Figure 2 for From Text to Source: Results in Detecting Large Language Model-Generated Content
Figure 3 for From Text to Source: Results in Detecting Large Language Model-Generated Content
Figure 4 for From Text to Source: Results in Detecting Large Language Model-Generated Content
Viaarxiv icon

Headless Language Models: Learning without Predicting with Contrastive Weight Tying

Sep 15, 2023
Nathan Godey, Éric de la Clergerie, Benoît Sagot

Figure 1 for Headless Language Models: Learning without Predicting with Contrastive Weight Tying
Figure 2 for Headless Language Models: Learning without Predicting with Contrastive Weight Tying
Figure 3 for Headless Language Models: Learning without Predicting with Contrastive Weight Tying
Figure 4 for Headless Language Models: Learning without Predicting with Contrastive Weight Tying
Viaarxiv icon

SONAR: Sentence-Level Multimodal and Language-Agnostic Representations

Aug 23, 2023
Paul-Ambroise Duquenne, Holger Schwenk, Benoît Sagot

Figure 1 for SONAR: Sentence-Level Multimodal and Language-Agnostic Representations
Figure 2 for SONAR: Sentence-Level Multimodal and Language-Agnostic Representations
Figure 3 for SONAR: Sentence-Level Multimodal and Language-Agnostic Representations
Figure 4 for SONAR: Sentence-Level Multimodal and Language-Agnostic Representations
Viaarxiv icon

Is Anisotropy Inherent to Transformers?

Jun 13, 2023
Nathan Godey, Éric de la Clergerie, Benoît Sagot

Figure 1 for Is Anisotropy Inherent to Transformers?
Figure 2 for Is Anisotropy Inherent to Transformers?
Figure 3 for Is Anisotropy Inherent to Transformers?
Figure 4 for Is Anisotropy Inherent to Transformers?
Viaarxiv icon

Towards a Robust Detection of Language Model Generated Text: Is ChatGPT that Easy to Detect?

Jun 09, 2023
Wissam Antoun, Virginie Mouilleron, Benoît Sagot, Djamé Seddah

Figure 1 for Towards a Robust Detection of Language Model Generated Text: Is ChatGPT that Easy to Detect?
Figure 2 for Towards a Robust Detection of Language Model Generated Text: Is ChatGPT that Easy to Detect?
Figure 3 for Towards a Robust Detection of Language Model Generated Text: Is ChatGPT that Easy to Detect?
Viaarxiv icon

Data-Efficient French Language Modeling with CamemBERTa

Jun 02, 2023
Wissam Antoun, Benoît Sagot, Djamé Seddah

Figure 1 for Data-Efficient French Language Modeling with CamemBERTa
Figure 2 for Data-Efficient French Language Modeling with CamemBERTa
Figure 3 for Data-Efficient French Language Modeling with CamemBERTa
Figure 4 for Data-Efficient French Language Modeling with CamemBERTa
Viaarxiv icon

A Simple Method for Unsupervised Bilingual Lexicon Induction for Data-Imbalanced, Closely Related Language Pairs

May 23, 2023
Niyati Bafna, Cristina España-Bonet, Josef van Genabith, Benoît Sagot, Rachel Bawden

Figure 1 for A Simple Method for Unsupervised Bilingual Lexicon Induction for Data-Imbalanced, Closely Related Language Pairs
Figure 2 for A Simple Method for Unsupervised Bilingual Lexicon Induction for Data-Imbalanced, Closely Related Language Pairs
Figure 3 for A Simple Method for Unsupervised Bilingual Lexicon Induction for Data-Imbalanced, Closely Related Language Pairs
Figure 4 for A Simple Method for Unsupervised Bilingual Lexicon Induction for Data-Imbalanced, Closely Related Language Pairs
Viaarxiv icon

Tackling Ambiguity with Images: Improved Multimodal Machine Translation and Contrastive Evaluation

Dec 20, 2022
Matthieu Futeral, Cordelia Schmid, Ivan Laptev, Benoît Sagot, Rachel Bawden

Figure 1 for Tackling Ambiguity with Images: Improved Multimodal Machine Translation and Contrastive Evaluation
Figure 2 for Tackling Ambiguity with Images: Improved Multimodal Machine Translation and Contrastive Evaluation
Figure 3 for Tackling Ambiguity with Images: Improved Multimodal Machine Translation and Contrastive Evaluation
Figure 4 for Tackling Ambiguity with Images: Improved Multimodal Machine Translation and Contrastive Evaluation
Viaarxiv icon