Xlm Roberta Ner Japanese

🚀 xlm-roberta-ner-japanese

This is a model for Japanese named entity recognition, fine - tuned from xlm - roberta - base.

This model is a fine-tuned version of xlm-roberta-base (pre-trained cross-lingual RobertaModel) trained for named entity recognition (NER) token classification.

The model is fine-tuned on the NER dataset provided by Stockmark Inc, where the data is collected from Japanese Wikipedia articles.
See here for the license of this dataset.

Each token is labeled as follows:

🚀 Quick Start

💻 Usage Examples

Basic Usage

from transformers import pipeline

model_name = "tsmatz/xlm-roberta-ner-japanese"
classifier = pipeline("token-classification", model=model_name)
result = classifier("鈴井は4月の陽気の良い日に、鈴をつけて北海道のトムラウシへと登った")
print(result)

📚 Documentation

🔧 Technical Details

Training procedure

You can download the source code for fine-tuning from here.

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 5e-05
• train_batch_size: 12
• eval_batch_size: 12
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 5

Training results

Framework versions

• Transformers 4.23.1
• Pytorch 1.12.1+cu102
• Datasets 2.6.1
• Tokenizers 0.13.1

📄 License

This model is released under the MIT license.