Dehatebert Mono Indonesian

🚀 Indonesian Hate Speech Detection Mono Model

This model is designed to detect hatespeech in the Indonesian language. The "mono" in its name indicates a monolingual setting, where the model is trained solely on Arabic language data. It is a fine - tuned version of a multilingual BERT model.

🚀 Quick Start

This model can be used to detect hatespeech in Indonesian text. For training details, the code can be found at this url.

✨ Features

• Monolingual Focus: Trained specifically for detecting hatespeech in the Indonesian language.
• Fine - Tuned on BERT: Leverages the power of a pre - trained multilingual BERT model.
• Optimized Learning Rate: Achieved a best validation score of 0.844494 with a learning rate of 2e - 5.

📚 Documentation

Training Details

The model is trained with different learning rates, and the best validation score of 0.844494 is achieved when the learning rate is set to 2e - 5.

Paper Reference

Sai Saketh Aluru, Binny Mathew, Punyajoy Saha and Animesh Mukherjee. "Deep Learning Models for Multilingual Hate Speech Detection". Accepted at ECML - PKDD 2020.

⚠️ Important Note

Please cite our paper in any published work that uses any of these resources.

Citation

@article{aluru2020deep,
  title={Deep Learning Models for Multilingual Hate Speech Detection},
  author={Aluru, Sai Saket and Mathew, Binny and Saha, Punyajoy and Mukherjee, Animesh},
  journal={arXiv preprint arXiv:2004.06465},
  year={2020}
}