tner/roberta-large-mit-restaurant

该模型是在 roberta-large 数据集上通过 T-NER 的超参数搜索进行微调的版本。模型在测试集上取得了以下结果：

• F1（微平均）：0.8164676304211189
• Precision（微平均）：0.8085901027077498
• Recall（微平均）：0.8245001586797842
• F1（宏平均）：0.8081522050756316
• Precision（宏平均）：0.7974927131040113
• Recall（宏平均）：0.8199029986502094

测试集中F1得分的实体细分如下：

• amenity：0.7140221402214022
• cuisine：0.8558052434456929
• dish：0.829103214890017
• location：0.8611793611793611
• money：0.8579710144927537
• rating：0.8
• restaurant：0.8713375796178344
• time：0.6757990867579908

F1得分的置信区间通过自助法获得：

• F1（微平均）：
  • 90%：[0.8050039870241192, 0.8289531287254172]
  • 95%：[0.8030897272187587, 0.8312785732455824]
• F1（宏平均）：
  • 90%：[0.8050039870241192, 0.8289531287254172]
  • 95%：[0.8030897272187587, 0.8312785732455824]

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

可以通过 tner library 库使用该模型。通过pip安装库：

pip install tner

并按照以下方式激活模型。

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

也可以使用transformers库，但是目前不建议使用，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/mit_restaurant']
• 数据集拆分：train
• 数据集名称：None
• 本地数据集：None
• 模型：roberta-large
• CRF：True
• 最大长度：128
• epoch：15
• 批量大小：64
• 学习率：1e-05
• 随机种子：42
• 梯度累积步数：1
• 权重衰减：None
• 学习率预热步数比例：0.1
• 最大梯度范数：10.0

完整配置可以在 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.",
}