[Corpora-List] Introducing FlauBERT (Unsupervised Language Model Pre-training for French)

Didier schwab didier.schwab at imag.fr
Fri Dec 13 11:13:25 CET 2019


Here is FlauBERT: a French LM learnt (with #CNRS J-Zay supercomputer) on a large and heterogeneous corpus. Along with it comes FLUE (evaluation setup for French NLP). FlauBERT was successfully applied to complex tasks (NLI, WSD, Parsing). More on https://github.com/getalp/Flaubert <https://github.com/getalp/Flaubert> More details on this online paper: https://arxiv.org/abs/1912.05372 <https://arxiv.org/abs/1912.05372>

Voici FlauBERT : un modèle de langue en français (appris avec le supercalculateur JZay du #CNRS) sur un grand corpus hétérogène. Le modèle est livré avec une suite de test (FLUE) qui inclut des tâches complexes (NLI, WSD, Parsing). Plus d'informations sur https://github.com/getalp/Flaubert <https://github.com/getalp/Flaubert> Plus de détails sur: https://arxiv.org/abs/1912.05372 <https://arxiv.org/abs/1912.05372>

-- The FlauBERT team -------------- next part -------------- A non-text attachment was scrubbed... Name: not available Type: text/html Size: 2355 bytes Desc: not available URL: <https://mailman.uib.no/public/corpora/attachments/20191213/44a6a775/attachment.txt>



More information about the Corpora mailing list