CAMeLBERT-Mix POS-GLF模型

模型描述

CAMeLBERT-Mix POS-GLF模型是一个海湾阿拉伯语词性标注模型，是通过对 CAMeLBERT-Mix 模型进行微调而构建的。我们使用了 Gumar 数据集进行微调。有关微调过程和使用的超参数的详细信息可以在我们的论文“ The Interplay of Variant, Size, and Task Type in Arabic Pre-trained Language Models ”中找到。我们的微调代码可以在 here 找到。

预期用途

您可以将CAMeLBERT-Mix POS-GLF模型作为transformers pipeline的一部分来使用。该模型也将很快在 CAMeL Tools 中提供。

要在transformers pipeline中使用该模型：

>>> from transformers import pipeline
>>> pos = pipeline('token-classification', model='CAMeL-Lab/bert-base-arabic-camelbert-mix-pos-glf')
>>> text = 'شلونك ؟ شخبارك ؟'
>>> pos(text)
[{'entity': 'pron_interrog', 'score': 0.82657206, 'index': 1, 'word': 'شلون', 'start': 0, 'end': 4}, {'entity': 'prep', 'score': 0.9771731, 'index': 2, 'word': '##ك', 'start': 4, 'end': 5}, {'entity': 'punc', 'score': 0.9999568, 'index': 3, 'word': '؟', 'start': 6, 'end': 7}, {'entity': 'noun', 'score': 0.9977217, 'index': 4, 'word': 'ش', 'start': 8, 'end': 9}, {'entity': 'noun', 'score': 0.99993783, 'index': 5, 'word': '##خبار', 'start': 9, 'end': 13}, {'entity': 'prep', 'score': 0.5309442, 'index': 6, 'word': '##ك', 'start': 13, 'end': 14}, {'entity': 'punc', 'score': 0.9999575, 'index': 7, 'word': '؟', 'start': 15, 'end': 16}]

注意：要下载我们的模型，您需要 transformers>=3.5.0 。否则，您可以手动下载模型。

引用

@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.",
}