Xlm Roberta Base Turkish Ner

🚀 Turkish Named Entity Recognition (NER) Model

This model is a fine - tuned version of "xlm - roberta - base", a multilingual RoBERTa, using a reviewed Turkish NER dataset. It can effectively perform named entity recognition tasks in Turkish.

🚀 Quick Start

This Turkish NER model is a fine - tuned version of "xlm - roberta - base". It uses a reviewed version of a well - known Turkish NER dataset from here.

✨ Features

• Based on the "xlm - roberta - base" model, which is a multilingual version of RoBERTa.
• Fine - tuned on a specific Turkish NER dataset for better performance in Turkish NER tasks.

📦 Installation

No specific installation steps are provided in the original document. However, to use the model, you need to have the necessary Python libraries installed, such as transformers. You can install it using pip install transformers.

💻 Usage Examples

Basic Usage

model = AutoModelForTokenClassification.from_pretrained("akdeniz27/xlm-roberta-base-turkish-ner")
tokenizer = AutoTokenizer.from_pretrained("akdeniz27/xlm-roberta-base-turkish-ner")
ner = pipeline('ner', model=model, tokenizer=tokenizer, aggregation_strategy="simple")
ner("<your text here>")

Advanced Usage

Please refer to this link for entity grouping with the aggregation_strategy parameter.

🔧 Technical Details

Fine - tuning parameters

task = "ner"
model_checkpoint = "xlm-roberta-base"
batch_size = 8 
label_list = ['O', 'B-PER', 'I-PER', 'B-ORG', 'I-ORG', 'B-LOC', 'I-LOC']
max_length = 512 
learning_rate = 2e-5 
num_train_epochs = 2 
weight_decay = 0.01 

📄 License

This project is licensed under the MIT license.

📊 Reference test results

• Accuracy: 0.9919343118732742
• F1: 0.9492100796448622
• Precision: 0.9407349896480332
• Recall: 0.9578392621870883