no code implementations • JEP/TALN/RECITAL 2021 • Antoine Simoulin, Benoit Crabbé
Ces architectures sont en particulier pré-entraînées sur des tâches auto-supervisées et sont ainsi spécifiques pour une langue donnée.
no code implementations • NAACL (ACL) 2022 • Antoine Simoulin, Benoit Crabbé
As a result, the sentence embedding is computed according to an interpretable linguistic pattern and may be used on any downstream task.
1 code implementation • NeurIPS 2023 • Namyong Park, Ryan Rossi, Xing Wang, Antoine Simoulin, Nesreen Ahmed, Christos Faloutsos
The choice of a graph learning (GL) model (i. e., a GL algorithm and its hyperparameter settings) has a significant impact on the performance of downstream tasks.
1 code implementation • 16 Mar 2024 • Namyong Park, Xing Wang, Antoine Simoulin, Shuai Yang, Grey Yang, Ryan Rossi, Puja Trivedi, Nesreen Ahmed
To address these limitations, the forward-forward algorithm (FF) was recently proposed as an alternative to BP in the image classification domain, which trains NNs by performing two forward passes over positive and negative data.
no code implementations • ACL 2021 • Antoine Simoulin, Benoit Crabb{\'e}
In this study, we investigate the role of the multiple layers in deep transformer models.
no code implementations • EACL 2021 • Antoine Simoulin, Benoit Crabbé
We assume structure is crucial to build consistent representations as we expect sentence meaning to be a function from both syntax and semantic aspects.
no code implementations • 25 Sep 2019 • Antoine Simoulin
We aim to take advantage of this linguist diversity and learn to represent sentences by contrasting these diverse views.
no code implementations • 6 Dec 2017 • Nicolas Thiebaut, Antoine Simoulin, Karl Neuberger, Issam Ibnouhsein, Nicolas Bousquet, Nathalie Reix, Sébastien Molière, Carole Mathelin
With no need for biomedical annotators or pre-defined ontologies, this language-agnostic method reached an good extraction accuracy for several concepts of interest, according to a comparison with a manually structured file, without requiring any existing corpus with local or new notations.