🚀 bert-portuguese-ner
本模型是基于 neuralmind/bert-base-portuguese-cased 的微调版本,可用于解决葡萄牙语档案文档中的命名实体识别(NER)问题,在评估集上有出色的表现。
🚀 快速开始
本模型在评估集上取得了以下结果:
- 损失值:0.1140
- 精确率:0.9147
- 召回率:0.9483
- F1值:0.9312
- 准确率:0.9700
✨ 主要特性
- 基于预训练的葡萄牙语 BERT 模型进行微调,适用于葡萄牙语档案文档的命名实体识别任务。
- 标注的标签包括:日期、职业、人物、地点、组织,能满足多种信息抽取需求。
📚 详细文档
模型描述
该模型在葡萄牙语档案文档的标记分类任务(NER)上进行了微调。标注的标签有:日期、职业、人物、地点、组织。
数据集
所有训练和评估数据可在以下链接获取:http://ner.epl.di.uminho.pt/
训练超参数
训练过程中使用了以下超参数:
- 学习率:2e-05
- 训练批次大小:16
- 评估批次大小:16
- 随机种子:42
- 优化器:Adam(β1=0.9,β2=0.999,ε=1e-08)
- 学习率调度器类型:线性
- 训练轮数:4
训练结果
训练损失 |
轮数 |
步数 |
验证损失 |
精确率 |
召回率 |
F1值 |
准确率 |
无记录 |
1.0 |
192 |
0.1438 |
0.8917 |
0.9392 |
0.9148 |
0.9633 |
0.2454 |
2.0 |
384 |
0.1222 |
0.8985 |
0.9417 |
0.9196 |
0.9671 |
0.0526 |
3.0 |
576 |
0.1098 |
0.9150 |
0.9481 |
0.9312 |
0.9698 |
0.0372 |
4.0 |
768 |
0.1140 |
0.9147 |
0.9483 |
0.9312 |
0.9700 |
框架版本
- Transformers 4.10.0.dev0
- Pytorch 1.9.0+cu111
- Datasets 1.10.2
- Tokenizers 0.10.3
引用信息
@Article{make4010003,
AUTHOR = {Cunha, Luís Filipe and Ramalho, José Carlos},
TITLE = {NER in Archival Finding Aids: Extended},
JOURNAL = {Machine Learning and Knowledge Extraction},
VOLUME = {4},
YEAR = {2022},
NUMBER = {1},
PAGES = {42--65},
URL = {https://www.mdpi.com/2504-4990/4/1/3},
ISSN = {2504-4990},
ABSTRACT = {The amount of information preserved in Portuguese archives has increased over the years. These documents represent a national heritage of high importance, as they portray the country’s history. Currently, most Portuguese archives have made their finding aids available to the public in digital format, however, these data do not have any annotation, so it is not always easy to analyze their content. In this work, Named Entity Recognition solutions were created that allow the identification and classification of several named entities from the archival finding aids. These named entities translate into crucial information about their context and, with high confidence results, they can be used for several purposes, for example, the creation of smart browsing tools by using entity linking and record linking techniques. In order to achieve high result scores, we annotated several corpora to train our own Machine Learning algorithms in this context domain. We also used different architectures, such as CNNs, LSTMs, and Maximum Entropy models. Finally, all the created datasets and ML models were made available to the public with a developed web platform, NER@DI.},
DOI = {10.3390/make4010003}
}
📄 许可证
本项目采用 MIT 许可证。