中文RoBERTa-Base文本分类模型

模型描述

这是由 UER-py 细调的5个中文RoBERTa-Base分类模型。您可以从以下链接中的 UER-py Modelzoo page （以UER-py格式）下载5个中文RoBERTa-Base分类模型，或通过HuggingFace下载：

如何使用

您可以直接在文本分类的管道中使用此模型（以roberta-base-finetuned-chinanews-chinese为例）：

>>> from transformers import AutoModelForSequenceClassification,AutoTokenizer,pipeline
>>> model = AutoModelForSequenceClassification.from_pretrained('uer/roberta-base-finetuned-chinanews-chinese')
>>> tokenizer = AutoTokenizer.from_pretrained('uer/roberta-base-finetuned-chinanews-chinese')
>>> text_classification = pipeline('sentiment-analysis', model=model, tokenizer=tokenizer)
>>> text_classification("北京上个月召开了两会")
    [{'label': 'mainland China politics', 'score': 0.7211663722991943}]

训练数据

使用了5个中文文本分类数据集。JD full，JD binary和Dianping数据集包含不同情感极性的用户评论。Ifeng和Chinanews包含不同主题类别的新闻文章的第一段。它们由 Glyph 项目收集，更多细节在相应的 paper 中讨论。

训练过程

模型由 UER-py 在 Tencent Cloud 上进行了微调。我们在512个序列长度上进行了三个时期的微调，基于预训练模型 chinese_roberta_L-12_H-768 。在每个时期结束时，当在开发集上获得最佳性能时，保存模型。我们在不同的模型上使用相同的超参数。

以roberta-base-finetuned-chinanews-chinese为例

python3 run_classifier.py --pretrained_model_path models/cluecorpussmall_roberta_base_seq512_model.bin-250000 \
                          --vocab_path models/google_zh_vocab.txt \
                          --train_path datasets/glyph/chinanews/train.tsv \
                          --dev_path datasets/glyph/chinanews/dev.tsv \
                          --output_model_path models/chinanews_classifier_model.bin \
                          --learning_rate 3e-5 --epochs_num 3 --batch_size 32 --seq_length 512

最后，我们将预训练模型转换为Huggingface的格式：

python3 scripts/convert_bert_text_classification_from_uer_to_huggingface.py --input_model_path models/chinanews_classifier_model.bin \
                                                                            --output_model_path pytorch_model.bin \
                                                                            --layers_num 12

BibTeX参考文献和引用信息

@article{devlin2018bert,
  title={BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding},
  author={Devlin, Jacob and Chang, Ming-Wei and Lee, Kenton and Toutanova, Kristina},
  journal={arXiv preprint arXiv:1810.04805},
  year={2018}
}

@article{liu2019roberta,
  title={Roberta: A robustly optimized bert pretraining approach},
  author={Liu, Yinhan and Ott, Myle and Goyal, Naman and Du, Jingfei and Joshi, Mandar and Chen, Danqi and Levy, Omer and Lewis, Mike and Zettlemoyer, Luke and Stoyanov, Veselin},
  journal={arXiv preprint arXiv:1907.11692},
  year={2019}
}

@article{zhang2017encoding,
  title={Which encoding is the best for text classification in chinese, english, japanese and korean?},
  author={Zhang, Xiang and LeCun, Yann},
  journal={arXiv preprint arXiv:1708.02657},
  year={2017}
}

@article{zhao2019uer,
  title={UER: An Open-Source Toolkit for Pre-training Models},
  author={Zhao, Zhe and Chen, Hui and Zhang, Jinbin and Zhao, Xin and Liu, Tao and Lu, Wei and Chen, Xi and Deng, Haotang and Ju, Qi and Du, Xiaoyong},
  journal={EMNLP-IJCNLP 2019},
  pages={241},
  year={2019}
}