面向古希腊校勘本的结构感知文本识别
Structure-Aware Text Recognition for Ancient Greek Critical Editions
AI总结：
本文通过构建大规模合成语料库和真实扫描基准，评估了视觉语言模型在结构感知文本识别上的性能，发现Qwen3VL-8B模型在真实扫描上达到1.0%的中位字符错误率。
摘要：
视觉语言模型（VLM）的最新进展已经改变了端到端的文档理解。然而，它们解释历史学术文本复杂布局语义的能力仍然有限。本文研究了面向古希腊校勘本的结构感知文本识别，这些校勘本具有密集的参考层次和广泛的边缘注释。我们引入了两个新资源：（i）从TEI/XML源生成的185,000页图像的大规模合成语料库，具有受控的排版和布局变化，以及（ii）跨越一个多世纪编辑和排版实践的真实扫描校勘本的精选基准。使用这些数据集，我们在零样本和微调设置下评估了三种最先进的VLM。我们的实验揭示了当前VLM架构在面对高度结构化的历史文档时的显著局限性。在零样本设置中，大多数模型的性能明显低于现有的现成软件。尽管如此，Qwen3VL-8B模型达到了最先进的性能，在真实扫描上实现了1.0%的中位字符错误率。这些结果既突显了当前VLM在结构感知识别复杂学术文档方面的不足，也展示了其未来潜力。
英文摘要：
Recent advances in visual language models (VLMs) have transformed end-to-end document understanding. However, their ability to interpret the complex layout semantics of historical scholarly texts remains limited. This paper investigates structure-aware text recognition for Ancient Greek critical editions, which have dense reference hierarchies and extensive marginal annotations. We introduce two novel resources: (i) a large-scale synthetic corpus of 185,000 page images generated from TEI/XML sources with controlled typographic and layout variation, and (ii) a curated benchmark of real scanned editions spanning more than a century of editorial and typographic practices. Using these datasets, we evaluate three state-of-the-art VLMs under both zero-shot and fine-tuning regimes. Our experiments reveal substantial limitations in current VLM architectures when confronted with highly structured historical documents. In zero-shot settings, most models significantly underperform compared to established off-the-shelf software. Nevertheless, the Qwen3VL-8B model achieves state-of-the-art performance, reaching a median Character Error Rate of 1.0\% on real scans. These results highlight both the current shortcomings and the future potential of VLMs for structure-aware recognition of complex scholarly documents.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
