tner/deberta-v3-large-btc

这个模型是在 tner/btc 数据集上对 microsoft/deberta-v3-large 进行微调得到的。模型的微调是通过 T-NER 的超参数搜索完成的（详细信息请参阅该存储库）。它在测试集上达到了以下结果：

• F1值（微平均）：0.8399238265934805
• 准确率（微平均）：0.8237749945067018
• 召回率（微平均）：0.8567184643510055
• F1值（宏平均）：0.7921150390682584
• 准确率（宏平均）：0.7766126681668878
• 召回率（宏平均）：0.8103758198218992

测试集上的每个实体的F1分数如下：

• 地点（location）：0.7503949447077408
• 组织（organization）：0.7042372881355932
• 人物（person）：0.9217128843614413

对于F1分数，通过bootstrap方法获取置信区间，结果如下：

• F1值（微平均）：
  • 90%置信区间：[0.8283024935970381, 0.8507400882379221]
  • 95%置信区间：[0.8260021524132041, 0.8526162579659953]
• F1值（宏平均）：
  • 90%置信区间：[0.8283024935970381, 0.8507400882379221]
  • 95%置信区间：[0.8260021524132041, 0.8526162579659953]

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

用法

可以通过 tner library 来使用该模型。通过pip安装该库

pip install tner

并按下面的代码激活模型。

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

可以通过transformers库使用它，但目前不建议使用，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/btc']
• 数据集拆分：train
• 数据集名称：无
• 本地数据集：无
• 模型：microsoft/deberta-v3-large
• CRF层：True
• 最大长度：128
• 迭代轮数：15
• 批次大小：16
• 学习率：1e-05
• 随机种子：42
• 梯度累积步数：8
• 权重衰减：无
• 学习率预热步数比率：0.1
• 最大梯度范数：无

完整的配置可以在 fine-tuning parameter file 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.",
}