XLM-RoBERTa-Base-Turkish-NER

Introduction

The XLM-RoBERTa-Base-Turkish-NER model is a fine-tuned version of the multilingual "xlm-roberta-base" for performing named entity recognition (NER) in Turkish. It leverages a reviewed Turkish NER dataset to enhance its performance in identifying entities like persons, organizations, and locations within Turkish text.

Architecture

The model is based on the XLM-RoBERTa architecture, which is a multilingual variant of RoBERTa designed to handle various languages. This architecture enables the model to effectively process Turkish text for NER tasks.

Training

The model was fine-tuned with the following 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
Number of Training Epochs: 2
Weight Decay: 0.01

Guide: Running Locally

To run the XLM-RoBERTa-Base-Turkish-NER model locally, follow these steps:

Install Required Libraries: Ensure you have the Hugging Face Transformers library installed:
```
pip install transformers
```

Load the Model and Tokenizer:

from transformers import AutoModelForTokenClassification, AutoTokenizer, pipeline

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")

Run NER on Your Text:

result = ner("<your text here>")
print(result)

Cloud GPU Recommendation: For improved performance, consider using cloud-based GPU services such as AWS EC2, Google Cloud Platform, or Microsoft Azure.

License

The model is available under the MIT License, allowing for wide usage and modification.