Papers by Baptiste Pannier
PAGnol: An Extra-Large French Generative Model (2022.lrec-1)
Copied to clipboard
Julien Launay, E.l. Tommasone, Baptiste Pannier, François Boniface, Amélie Chatelain, Alessandro Cappelli, Iacopo Poli, Djamé Seddah
| Challenge: | a growing number of pre-trained language models are available in many different languages. |
| Approach: | They propose a French-language GPT model with scaling laws to train it efficiently . they evaluate the models on discriminative and generative tasks in French . |
| Outcome: | The proposed model trains with the same computational budget as CamemBERT, a model 13 times smaller. |
Pre-training Is (Almost) All You Need: An Application to Commonsense Reasoning (2020.acl-main)
Copied to clipboard
| Challenge: | Existing methods for solving common NLP tasks rely on fine-tuning of pre-trained transformer models. |
| Approach: | They propose a scoring method that casts a plausibility ranking task in full-text format without fine-tuning . they use masked language modeling head tuned during pre-training phase to exploit this method . |
| Outcome: | The proposed method produces strong baselines comparable to supervised approaches. |