Bert Base Arabic Camelbert Mix Pos Msa

🚀 CAMeLBERT-Mix POS-MSA Model

CAMeLBERT-Mix POS-MSA Model is a Modern Standard Arabic (MSA) POS tagging model. It offers accurate part - of - speech tagging for MSA text, which is crucial for various NLP applications in the Arabic language.

🚀 Quick Start

The CAMeLBERT-Mix POS-MSA model can be easily integrated into your NLP projects. It will soon be available in CAMeL Tools for more convenient use.

✨ Features

• Fine - tuned Model: Built by fine - tuning the CAMeLBERT-Mix model, leveraging its pre - trained knowledge for better performance.
• Dataset - Driven: Utilized the PATB dataset for fine - tuning, ensuring high - quality training.
• Research - Backed: The fine - tuning procedure and hyperparameters are detailed in the paper "The Interplay of Variant, Size, and Task Type in Arabic Pre - trained Language Models."

📦 Installation

To use the model, you need transformers>=3.5.0. If you don't have it, you can install it using the following command:

pip install transformers>=3.5.0

💻 Usage Examples

Basic Usage

To use the model with a transformers pipeline:

>>> from transformers import pipeline
>>> pos = pipeline('token-classification', model='CAMeL-Lab/bert-base-arabic-camelbert-mix-pos-msa')
>>> text = 'إمارة أبوظبي هي إحدى إمارات دولة الإمارات العربية المتحدة السبع'
>>> pos(text)
[{'entity': 'noun', 'score': 0.9999592, 'index': 1, 'word': 'إمارة', 'start': 0, 'end': 5}, {'entity': 'noun_prop', 'score': 0.9997877, 'index': 2, 'word': 'أبوظبي', 'start': 6, 'end': 12}, {'entity': 'pron', 'score': 0.9998405, 'index': 3, 'word': 'هي', 'start': 13, 'end': 15}, {'entity': 'noun', 'score': 0.9697179, 'index': 4, 'word': 'إحدى', 'start': 16, 'end': 20}, {'entity': 'noun', 'score': 0.99967164, 'index': 5, 'word': 'إما', 'start': 21, 'end': 24}, {'entity': 'noun', 'score': 0.99980617, 'index': 6, 'word': '##رات', 'start': 24, 'end': 27}, {'entity': 'noun', 'score': 0.99997973, 'index': 7, 'word': 'دولة', 'start': 28, 'end': 32}, {'entity': 'noun', 'score': 0.99995637, 'index': 8, 'word': 'الإمارات', 'start': 33, 'end': 41}, {'entity': 'adj', 'score': 0.9983974, 'index': 9, 'word': 'العربية', 'start': 42, 'end': 49}, {'entity': 'adj', 'score': 0.9999469, 'index': 10, 'word': 'المتحدة', 'start': 50, 'end': 57}, {'entity': 'noun_num', 'score': 0.9993273, 'index': 11, 'word': 'السبع', 'start': 58, 'end': 63}]

Important Note

Note: to download our models, you would need transformers>=3.5.0. Otherwise, you could download the models manually.

📚 Documentation

For more details about the fine - tuning procedure and hyperparameters, please refer to our paper "The Interplay of Variant, Size, and Task Type in Arabic Pre - trained Language Models." Our fine - tuning code can be found here.

📄 License

This project is licensed under the Apache - 2.0 license.

📚 Citation

If you use this model in your research, please cite the following paper:

@inproceedings{inoue-etal-2021-interplay,
    title = "The Interplay of Variant, Size, and Task Type in {A}rabic Pre-trained Language Models",
    author = "Inoue, Go  and
      Alhafni, Bashar  and
      Baimukan, Nurpeiis  and
      Bouamor, Houda  and
      Habash, Nizar",
    booktitle = "Proceedings of the Sixth Arabic Natural Language Processing Workshop",
    month = apr,
    year = "2021",
    address = "Kyiv, Ukraine (Online)",
    publisher = "Association for Computational Linguistics",
    abstract = "In this paper, we explore the effects of language variants, data sizes, and fine-tuning task types in Arabic pre-trained language models. To do so, we build three pre-trained language models across three variants of Arabic: Modern Standard Arabic (MSA), dialectal Arabic, and classical Arabic, in addition to a fourth language model which is pre-trained on a mix of the three. We also examine the importance of pre-training data size by building additional models that are pre-trained on a scaled-down set of the MSA variant. We compare our different models to each other, as well as to eight publicly available models by fine-tuning them on five NLP tasks spanning 12 datasets. Our results suggest that the variant proximity of pre-training data to fine-tuning data is more important than the pre-training data size. We exploit this insight in defining an optimized system selection model for the studied tasks.",
}