Automatic readability assessment is relevant to building NLP applications for education, content analysis, and accessibility. However, Arabic readability assessment is a challenging task due to Arabic's morphological richness and limited readability resources. In this paper, we present a set of experimental results on Arabic readability assessment using a diverse range of approaches, from rule-based methods to Arabic pretrained language models. We report our results on a newly created corpus at different textual granularity levels (words and sentence fragments). Our results show that combining different techniques yields the best results, achieving an overall macro F1 score of 86.7 at the word level and 87.9 at the fragment level on a blind test set. We make our code, data, and pretrained models publicly available.

翻译：自动可读性评估对于构建面向教育、内容分析和可访问性的自然语言处理应用具有重要意义。然而，由于阿拉伯语形态丰富且可读性资源有限，阿拉伯语可读性评估是一项具有挑战性的任务。本文通过从基于规则的方法到阿拉伯语预训练语言模型等多种方法，呈现了一系列关于阿拉伯语可读性评估的实验结果。我们在新构建的不同文本粒度级别（单词和句子片段）语料库上报告了实验结果。结果表明，结合不同技术能取得最佳效果，在盲测集上单词级别和片段级别的整体宏观F1分数分别达到86.7和87.9。我们将代码、数据和预训练模型公开提供。