language, tags, license, datasets
| language | tags | license | datasets | |||
|---|---|---|---|---|---|---|
| fr |
|
gpl-3.0 |
|
camembert-large-fquad
Description
A native French Question Answering model CamemBERT-large fine-tuned on FQuAD.
FQuAD Leaderboard and evaluation scores
The results of Camembert-large-fquad can be compared with other state-of-the-art models of the FQuAD Leaderboard.
On the test set the model scores,
{"f1": 91.5, "exact_match": 82.0}
On the development set the model scores,
{"f1": 91.0, "exact_match": 81.2}
Note : You can also explore the results of the model on FQuAD-Explorer !
Usage
from transformers import pipeline
nlp = pipeline('question-answering', model='illuin/camembert-large-fquad', tokenizer='illuin/camembert-large-fquad')
nlp({
'question': "Qui est Claude Monet?",
'context': "Claude Monet, né le 14 novembre 1840 à Paris et mort le 5 décembre 1926 à Giverny, est un peintre français et l’un des fondateurs de l'impressionnisme."
})
Citation
If you use our work, please cite:
@article{dHoffschmidt2020FQuADFQ,
title={FQuAD: French Question Answering Dataset},
author={Martin d'Hoffschmidt and Maxime Vidal and Wacim Belblidia and Tom Brendl'e and Quentin Heinrich},
journal={ArXiv},
year={2020},
volume={abs/2002.06071}
}