CAMeLBERT MSA SA Model

模型描述

CAMeLBERT MSA SA Model 是一个情感分析（SA）模型，通过微调 CAMeLBERT Modern Standard Arabic (MSA) 模型进行构建。我们使用了 ASTD 、 ArSAS 和 SemEval 数据集进行微调。我们在论文 " The Interplay of Variant, Size, and Task Type in Arabic Pre-trained Language Models " 中详细描述了微调过程和所使用的超参数。可以在代码 here 中找到我们的微调代码。

使用目的

您可以将 CAMeLBERT MSA SA 模型直接作为我们提供的 CAMeL Tools SA 组件的一部分使用（建议），也可以作为 transformers pipeline 的一部分使用。

要将模型与 CAMeL Tools SA 组件一起使用：

>>> from camel_tools.sentiment import SentimentAnalyzer
>>> sa = SentimentAnalyzer("CAMeL-Lab/bert-base-arabic-camelbert-msa-sentiment")
>>> sentences = ['أنا بخير', 'أنا لست بخير']
>>> sa.predict(sentences)
>>> ['positive', 'negative']

您还可以直接将 SA 模型与 transformers pipeline 结合使用：

>>> from transformers import pipeline
>>> sa = pipeline('sentiment-analysis', model='CAMeL-Lab/bert-base-arabic-camelbert-msa-sentiment')
>>> sentences = ['أنا بخير', 'أنا لست بخير']
>>> sa(sentences)
[{'label': 'positive', 'score': 0.9616648554801941},
 {'label': 'negative', 'score': 0.9779177904129028}]

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.",
}