arXiv cs.CL· Ismail El Jamiy, Khadija Msalek, Guillaume Loizelet, Farah Benamara, Nabil Hathout·· 11 小时前AI 评分29
ATHAAR：中世纪科学阿拉伯语手写文本识别数据集
ATHAAR: A Medieval Scientific Arabic Manuscript Dataset for Handwritten Text Recognition
AI 导读
研究者提出首个面向科学阿拉伯语手稿转写的标注指南，并据此构建了人工标注数据集 ATHAAR，覆盖同一文本的不同抄本、书法风格及文字与数字内容。基于 SOTA 视觉语言模型的实验显示，现有系统在跨书写体系、章节和论著迁移时，面对古代科学文本的特殊性仍存在明显局限。
正文 · 原文
Abstract:Despite recent progress in handwritten text recognition, medieval Arabic scientific manuscripts remain an open challenge for current vision-language models (VLMs) due to cursive ligatures, variable diacritization, and more importantly the lack of training data. This paper aims to address this gap, by proposing the first annotation guidelines dedicated to the transcription of scientific Arabic manuscripts inspired by textual criticism, a well-established approach to historical text editing. We then propose, ATHAAR, a new dataset manually annotated following this guideline. Unlike previous resources in the field, ATHAAR varies both witnesses of the same text, calligraphic styles, and content to deal with texts but also numerals. Relying on state-of-the-art VLMs, we finally design a set of experiments to study models transfer across scripts, chapters, and treatises. Our findings highlight the limitations of current systems when faced with the specificities of ancient scientific texts.
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Computation and Language (cs.CL) |
| Cite as: | arXiv:2611.08091 [cs.CV] |
| (or arXiv:2611.08091v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2611.08091 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Ismail El Jamiy [view email]
[v1]
Thu, 5 Nov 2026 14:36:16 UTC (10,098 KB)
来源：arXiv cs.CL · arxiv.org