camembert-base-squadFR-fquad-piaf

模型描述

基于法语问答任务的模型，使用基础版CamemBERT在三个法语问答数据集上微调而成：

1. PIAFv1.1
2. FQuADv1.0
3. SQuAD-FR (法译版SQuAD数据集)

训练超参数

python run_squad.py \
--model_type camembert \
--model_name_or_path camembert-base \
--do_train --do_eval \
--train_file data/SQuAD+fquad+piaf.json \
--predict_file data/fquad_valid.json \
--per_gpu_train_batch_size 12 \ 
--learning_rate 3e-5 \ 
--num_train_epochs 4 \  
--max_seq_length 384 \ 
--doc_stride 128 \
--save_steps 10000 

评估结果

FQuAD v1.0 评估

{"f1": 79.81, "exact_match": 55.14}

SQuAD-FR 评估

{"f1": 80.61, "exact_match": 59.54}

使用方式

from transformers import pipeline

nlp = pipeline('question-answering', model='etalab-ia/camembert-base-squadFR-fquad-piaf', tokenizer='etalab-ia/camembert-base-squadFR-fquad-piaf')

nlp({
    'question': "克劳德·莫奈是谁？",
    'context': "克劳德·莫奈，1840年11月14日生于巴黎，1926年12月5日卒于吉维尼，是法国画家，印象派创始人之一。"
})

致谢

本工作使用了GENCI–IDRIS提供的高性能计算资源（资助编号2020-AD011011224）。

引用文献

PIAF

@inproceedings{KeraronLBAMSSS20,
  author    = {Rachel Keraron and
               Guillaume Lancrenon and
               Mathilde Bras and
               Fr{\'{e}}d{\'{e}}ric Allary and
               Gilles Moyse and
               Thomas Scialom and
               Edmundo{-}Pavel Soriano{-}Morales and
               Jacopo Staiano},
  title     = {Project {PIAF:} Building a Native French Question-Answering Dataset},
  booktitle = {{LREC}},
  pages     = {5481--5490},
  publisher = {European Language Resources Association},
  year      = {2020}
}

FQuAD

@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}
}

SQuAD-FR

 @MISC{kabbadj2018,
   author =       "Kabbadj, Ali",
   title =        "法语文本挖掘与信息提取新突破（通用聊天机器人）：最大规模法语问答训练数据集（110,000+条）",
   editor =       "linkedin.com",
   month =        "11月",
   year =         "2018",
   url =          "\url{https://www.linkedin.com/pulse/something-new-french-text-mining-information-chatbot-largest-kabbadj/}",
   note =         "[在线资源；发布于2018年11月11日]",
 }

CamemBERT

HF模型卡片：https://huggingface.co/camembert-base

@inproceedings{martin2020camembert,
  title={CamemBERT: 美味的法语语言模型},
  author={Martin, Louis and Muller, Benjamin and Su{\'a}rez, Pedro Javier Ortiz and Dupont, Yoann and Romary, Laurent and de la Clergerie, {\'E}ric Villemonte and Seddah, Djam{\'e} and Sagot, Beno{\^\i}t},
  booktitle={第58届计算语言学协会年会论文集},
  year={2020}
}