Alert button
Picture for Djamé Seddah

Djamé Seddah

Alert button

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

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

Multilingual Auxiliary Tasks Training: Bridging the Gap between Languages for Zero-Shot Transfer of Hate Speech Detection Models

Oct 25, 2022
Syrielle Montariol, Arij Riabi, Djamé Seddah

Figure 1 for Multilingual Auxiliary Tasks Training: Bridging the Gap between Languages for Zero-Shot Transfer of Hate Speech Detection Models
Figure 2 for Multilingual Auxiliary Tasks Training: Bridging the Gap between Languages for Zero-Shot Transfer of Hate Speech Detection Models
Figure 3 for Multilingual Auxiliary Tasks Training: Bridging the Gap between Languages for Zero-Shot Transfer of Hate Speech Detection Models
Figure 4 for Multilingual Auxiliary Tasks Training: Bridging the Gap between Languages for Zero-Shot Transfer of Hate Speech Detection Models
Viaarxiv icon

Towards Unsupervised Content Disentanglement in Sentence Representations via Syntactic Roles

Jun 22, 2022
Ghazi Felhi, Joseph Le Roux, Djamé Seddah

Figure 1 for Towards Unsupervised Content Disentanglement in Sentence Representations via Syntactic Roles
Figure 2 for Towards Unsupervised Content Disentanglement in Sentence Representations via Syntactic Roles
Figure 3 for Towards Unsupervised Content Disentanglement in Sentence Representations via Syntactic Roles
Figure 4 for Towards Unsupervised Content Disentanglement in Sentence Representations via Syntactic Roles
Viaarxiv icon

Exploiting Inductive Bias in Transformers for Unsupervised Disentanglement of Syntax and Semantics with VAEs

May 19, 2022
Ghazi Felhi, Joseph Le Roux, Djamé Seddah

Figure 1 for Exploiting Inductive Bias in Transformers for Unsupervised Disentanglement of Syntax and Semantics with VAEs
Figure 2 for Exploiting Inductive Bias in Transformers for Unsupervised Disentanglement of Syntax and Semantics with VAEs
Figure 3 for Exploiting Inductive Bias in Transformers for Unsupervised Disentanglement of Syntax and Semantics with VAEs
Figure 4 for Exploiting Inductive Bias in Transformers for Unsupervised Disentanglement of Syntax and Semantics with VAEs
Viaarxiv icon

Simple, Interpretable and Stable Method for Detecting Words with Usage Change across Corpora

Dec 28, 2021
Hila Gonen, Ganesh Jawahar, Djamé Seddah, Yoav Goldberg

Figure 1 for Simple, Interpretable and Stable Method for Detecting Words with Usage Change across Corpora
Figure 2 for Simple, Interpretable and Stable Method for Detecting Words with Usage Change across Corpora
Figure 3 for Simple, Interpretable and Stable Method for Detecting Words with Usage Change across Corpora
Figure 4 for Simple, Interpretable and Stable Method for Detecting Words with Usage Change across Corpora
Viaarxiv icon

Can Character-based Language Models Improve Downstream Task Performance in Low-Resource and Noisy Language Scenarios?

Oct 26, 2021
Arij Riabi, Benoît Sagot, Djamé Seddah

Figure 1 for Can Character-based Language Models Improve Downstream Task Performance in Low-Resource and Noisy Language Scenarios?
Figure 2 for Can Character-based Language Models Improve Downstream Task Performance in Low-Resource and Noisy Language Scenarios?
Figure 3 for Can Character-based Language Models Improve Downstream Task Performance in Low-Resource and Noisy Language Scenarios?
Figure 4 for Can Character-based Language Models Improve Downstream Task Performance in Low-Resource and Noisy Language Scenarios?
Viaarxiv icon

Noisy UGC Translation at the Character Level: Revisiting Open-Vocabulary Capabilities and Robustness of Char-Based Models

Oct 24, 2021
José Carlos Rosales Núñez, Guillaume Wisniewski, Djamé Seddah

Figure 1 for Noisy UGC Translation at the Character Level: Revisiting Open-Vocabulary Capabilities and Robustness of Char-Based Models
Figure 2 for Noisy UGC Translation at the Character Level: Revisiting Open-Vocabulary Capabilities and Robustness of Char-Based Models
Figure 3 for Noisy UGC Translation at the Character Level: Revisiting Open-Vocabulary Capabilities and Robustness of Char-Based Models
Figure 4 for Noisy UGC Translation at the Character Level: Revisiting Open-Vocabulary Capabilities and Robustness of Char-Based Models
Viaarxiv icon