bert-base-arabic-camelbert-msa-did-madar-twitter5

CAMeLBERT-MSA DID MADAR Twitter-5 Model

Model description

CAMeLBERT-MSA DID MADAR Twitter-5 Model is a dialect identification (DID) model that was built by fine-tuning the CAMeLBERT-MSA model. For the fine-tuning, we used the MADAR Twitter-5 dataset, which includes 21 labels. Our fine-tuning procedure and the hyperparameters we used can be found in our paper "The Interplay of Variant, Size, and Task Type in Arabic Pre-trained Language Models." Our fine-tuning code can be found here.

Intended uses

You can use the CAMeLBERT-MSA DID MADAR Twitter-5 model as part of the transformers pipeline. This model will also be available in CAMeL Tools soon.

How to use

To use the model with a transformers pipeline:

>>> from transformers import pipeline
>>> did = pipeline('text-classification', model='CAMeL-Lab/bert-base-arabic-camelbert-msa-did-madar-twitter5')
>>> sentences = ['عامل ايه ؟', 'شلونك ؟ شخبارك ؟']
>>> did(sentences)
[{'label': 'Egypt', 'score': 0.5741344094276428},
 {'label': 'Kuwait', 'score': 0.5225679278373718}]

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

Citation

@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.",
}