tner/deberta-v3-large-ontonotes5

该模型是在数据集 tner/ontonotes5 上对 microsoft/deberta-v3-large 进行微调得到的。模型微调是通过 T-NER 的超参数搜索完成的（详见存储库以获取更多细节）。它在测试集上取得了以下结果：

• F1（微平均）：0.9069623608411381
• 精确率（微平均）：0.902100360312857
• 召回率（微平均）：0.9118770542773386
• F1（宏平均）：0.834586960779896
• 精确率（宏平均）：0.8237351069457466
• 召回率（宏平均）：0.8475169311172334

测试集上F1分数的实体细分如下：

• cardinal_number：0.853475935828877
• date：0.8815545959284392
• event：0.8030303030303031
• facility：0.7896678966789669
• geopolitical_area：0.9650033867690223
• group：0.9337209302325581
• language：0.8372093023255814
• law：0.6756756756756757
• location：0.7624020887728459
• money：0.8818897637795275
• ordinal_number：0.8635235732009926
• organization：0.914952751528627
• percent：0.9
• person：0.9609866599546942
• product：0.7901234567901234
• quantity：0.8161434977578474
• time：0.674364896073903
• work_of_art：0.7188405797101449

对于F1分数，通过自助法获得置信区间，如下所示：

• F1（微平均）：
  • 90%：[0.9019409960743083, 0.911751130722053]
  • 95%：[0.9010822890967028, 0.9125611412371442]
• F1（宏平均）：
  • 90%：[0.9019409960743083, 0.911751130722053]
  • 95%：[0.9010822890967028, 0.9125611412371442]

完整的评估结果可以在 metric file of NER 和 metric file of entity span 中找到。

用法

该模型可以通过 tner library 来使用。通过pip安装库

pip install tner

并进行如下操作以激活模型。

from tner import TransformersNER
model = TransformersNER("tner/deberta-v3-large-ontonotes5")
model.predict(["Jacob Collier is a Grammy awarded English artist from London"])

它可以通过transformers库使用，但目前不建议这样做，因为不支持CRF层。

训练超参数

训练过程中使用了以下超参数：

• 数据集：['tner/ontonotes5']
• 数据集切分：train
• 数据集名称：None
• 本地数据集：None
• 模型：microsoft/deberta-v3-large
• CRF：True
• 最大长度：128
• 训练轮数：15
• 批量大小：16
• 学习率：1e-05
• 随机种子：42
• 梯度累积步数：4
• 权重衰减：1e-07
• 学习率预热步数比例：0.1
• 最大梯度范数：10.0

完整的配置信息可以在 fine-tuning parameter file 中找到。

参考文献

如果您使用了T-NER的任何资源，请考虑引用我们的 paper 。

@inproceedings{ushio-camacho-collados-2021-ner,
    title = "{T}-{NER}: An All-Round Python Library for Transformer-based Named Entity Recognition",
    author = "Ushio, Asahi  and
      Camacho-Collados, Jose",
    booktitle = "Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations",
    month = apr,
    year = "2021",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2021.eacl-demos.7",
    doi = "10.18653/v1/2021.eacl-demos.7",
    pages = "53--62",
    abstract = "Language model (LM) pretraining has led to consistent improvements in many NLP downstream tasks, including named entity recognition (NER). In this paper, we present T-NER (Transformer-based Named Entity Recognition), a Python library for NER LM finetuning. In addition to its practical utility, T-NER facilitates the study and investigation of the cross-domain and cross-lingual generalization ability of LMs finetuned on NER. Our library also provides a web app where users can get model predictions interactively for arbitrary text, which facilitates qualitative model evaluation for non-expert programmers. We show the potential of the library by compiling nine public NER datasets into a unified format and evaluating the cross-domain and cross- lingual performance across the datasets. The results from our initial experiments show that in-domain performance is generally competitive across datasets. However, cross-domain generalization is challenging even with a large pretrained LM, which has nevertheless capacity to learn domain-specific features if fine- tuned on a combined dataset. To facilitate future research, we also release all our LM checkpoints via the Hugging Face model hub.",
}