Bert Base Arabic

🚀 Arabic BERT Model

This is a pre - trained BERT base language model designed for the Arabic language, which can effectively handle various natural language processing tasks in Arabic.

🚀 Quick Start

You can use this model by installing torch or tensorflow and Huggingface library transformers. And you can use it directly by initializing it like this:

from transformers import AutoTokenizer, AutoModel

tokenizer = AutoTokenizer.from_pretrained("asafaya/bert-base-arabic")
model = AutoModelForMaskedLM.from_pretrained("asafaya/bert-base-arabic")

✨ Features

• Pretrained on a large - scale Arabic corpus, which can better understand the semantics of Arabic.
• Can be used for various natural language processing tasks such as text classification, named entity recognition, etc.

📦 Installation

To use this model, you need to install torch or tensorflow and the Huggingface library transformers.

💻 Usage Examples

Basic Usage

from transformers import AutoTokenizer, AutoModel

tokenizer = AutoTokenizer.from_pretrained("asafaya/bert-base-arabic")
model = AutoModelForMaskedLM.from_pretrained("asafaya/bert-base-arabic")

📚 Documentation

Pretraining Corpus

The arabic - bert - base model was pretrained on ~8.2 Billion words:

• Arabic version of OSCAR - filtered from Common Crawl
• Recent dump of Arabic Wikipedia

and other Arabic resources which sum up to ~95GB of text.

Notes on training data:

• Our final version of corpus contains some non - Arabic words inlines, which we did not remove from sentences since that would affect some tasks like NER.
• Although non - Arabic characters were lowered as a preprocessing step, since Arabic characters does not have upper or lower case, there is no cased and uncased version of the model.
• The corpus and vocabulary set are not restricted to Modern Standard Arabic, they contain some dialectical Arabic too.

Pretraining details

• This model was trained using Google BERT's github repository on a single TPU v3 - 8 provided for free from TFRC.
• Our pretraining procedure follows training settings of bert with some changes: trained for 3M training steps with batchsize of 128, instead of 1M with batchsize of 256.

Results

For further details on the models performance or any other queries, please refer to [Arabic - BERT](https://github.com/alisafaya/Arabic - BERT)

🔧 Technical Details

• The model is based on the BERT architecture, which is a powerful pre - trained language model architecture.
• The training data comes from multiple Arabic resources, ensuring the diversity and richness of the data.
• The training process was carried out on a TPU v3 - 8, which greatly improved the training efficiency.

📄 License

If you use this model in your work, please cite this paper:

@inproceedings{safaya-etal-2020-kuisail,
    title = "{KUISAIL} at {S}em{E}val-2020 Task 12: {BERT}-{CNN} for Offensive Speech Identification in Social Media",
    author = "Safaya, Ali  and
      Abdullatif, Moutasem  and
      Yuret, Deniz",
    booktitle = "Proceedings of the Fourteenth Workshop on Semantic Evaluation",
    month = dec,
    year = "2020",
    address = "Barcelona (online)",
    publisher = "International Committee for Computational Linguistics",
    url = "https://www.aclweb.org/anthology/2020.semeval-1.271",
    pages = "2054--2059",
}

Acknowledgement

Thanks to Google for providing free TPU for the training process and for Huggingface for hosting this model on their servers 😊