Bert Base Arabic Camelbert Mix Poetry

🚀 CAMeLBERT - Mix诗歌分类模型

CAMeLBERT - Mix诗歌分类模型是一个用于诗歌分类的模型，它通过微调CAMeLBERT Mix模型构建而成。该模型能有效对阿拉伯语诗歌进行分类，为相关研究和应用提供了有力支持。

🚀 快速开始

你可以将CAMeLBERT - Mix诗歌分类模型作为transformers管道的一部分来使用。该模型不久后也将在CAMeL Tools中可用。

✨ 主要特性

• 基于微调的CAMeLBERT Mix模型构建，具有良好的性能基础。
• 使用APCD数据集进行微调，数据来源可靠。
• 微调过程和超参数在论文 "The Interplay of Variant, Size, and Task Type in Arabic Pre - trained Language Models" 中有详细说明。

📦 安装指南

要下载我们的模型，你需要transformers>=3.5.0。否则，你可以手动下载模型。

💻 使用示例

基础用法

>>> from transformers import pipeline
>>> poetry = pipeline('text-classification', model='CAMeL-Lab/bert-base-arabic-camelbert-mix-poetry')
>>> # A list of verses where each verse consists of two parts.
>>> verses = [
        ['الخيل والليل والبيداء تعرفني' ,'والسيف والرمح والقرطاس والقلم'],
        ['قم للمعلم وفه التبجيلا' ,'كاد المعلم ان يكون رسولا']
    ]
>>> # A function that concatenates the halves of each verse by using the [SEP] token.
>>> join_verse = lambda half: ' [SEP] '.join(half)
>>> # Apply this to all the verses in the list.
>>> verses = [join_verse(verse) for verse in verses]
>>> poetry(sentences)
[{'label': 'البسيط', 'score': 0.9937475919723511},
 {'label': 'الكامل', 'score': 0.971284031867981}]

📚 详细文档

模型描述

CAMeLBERT - Mix诗歌分类模型 是一个诗歌分类模型，它通过微调CAMeLBERT Mix模型构建而成。在微调过程中，我们使用了APCD数据集。我们的微调过程和所使用的超参数可以在我们的论文 "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这里找到。

预期用途

你可以将CAMeLBERT - Mix诗歌分类模型作为transformers管道的一部分来使用。该模型不久后也将在CAMeL Tools中可用。

📄 许可证

本项目采用Apache - 2.0许可证。

🔖 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.",
}