Model Card for Turkish Named Entity Recognition Model

This model performs Named Entity Recognition (NER) for Turkish text, identifying and classifying entities such as person names, locations, and organizations. Model got 0.9599 F1 on validation set.

Model Details

Model Description

This is a fine-tuned BERT model for Turkish Named Entity Recognition (NER). It is based on the dbmdz/bert-base-turkish-uncased model and has been trained on a custom Turkish NER dataset.

Developed by: Ezel Bayraktar ([email protected])
Model type: Token Classification (Named Entity Recognition)
Language(s) (NLP): Turkish
License: MIT
Finetuned from model: dbmdz/bert-base-turkish-uncased

Direct Use

This model can be used directly for Named Entity Recognition tasks in Turkish text. It identifies and labels entities such as person names (PER), locations (LOC), and organizations (ORG).

Downstream Use [optional]

The model can be integrated into larger natural language processing pipelines for Turkish, such as information extraction systems, question answering, or text summarization.

Out-of-Scope Use

This model should not be used for languages other than Turkish or for tasks beyond Named Entity Recognition. It may not perform well on domain-specific text or newly emerging named entities not present in the training data.

Bias, Risks, and Limitations

The model may inherit biases present in the training data or the pre-trained BERT model it was fine-tuned from. It may not perform consistently across different domains or types of Turkish text.

Recommendations

Users should evaluate the model's performance on their specific domain and use case. For critical applications, human review of the model's outputs is recommended.

How to Get Started with the Model

Use the code below to get started with the model.

from transformers import pipeline

nert = pipeline('ner', model='TerminatorPower/nerT', tokenizer='TerminatorPower/nerT')
answer = nert("Mustafa Kemal Atatürk, 19 Mayıs 1919'da Samsun'a çıktı.")
print(answer)