基于语义引导的LLM历史亚美尼亚报纸阅读顺序重建
Semantic-Guided Reading Order Reconstruction in Historical Armenian Newspapers with LLMs
AI总结：
针对历史亚美尼亚报纸复杂版面和低资源问题，提出混合方法结合语义区域检测与生成式LLM，排序错误率较几何基线降低76%。
摘要：
本文研究了历史亚美尼亚报纸中的阅读顺序重建问题，这些报纸结合了复杂的布局和有限的语言资源。我们引入了一个包含66页的新注释数据集，并比较了几何启发式方法、基于YOLO的布局解析、端到端文档模型ECLAIR，以及一种结合语义区域检测与生成式LLM的混合方法。我们的混合方法在所有评估方法中实现了最低的错误率，相比最强的几何基线，排序错误减少了高达76%，并且在多页设置和噪声OCR下保持鲁棒性。该方法并非面向生产，而是设计为一种数据引导策略，能够在高度资源匮乏的场景中实现快速注释。除了数据集，我们还发布了一个专门用于历史亚美尼亚印刷品的Tesseract OCR模型。
英文摘要：
This paper addresses reading order reconstruction in historical Armenian newspapers, which combine complex layouts with limited language resources. We introduce a new annotated dataset of 66 pages and compare geometric heuristics, YOLO-based layout parsing, an end-to-end document model ECLAIR, and a hybrid method combining semantic zone detection with a generative LLM. Our hybrid method achieves the lowest error rates of all evaluated approaches, reducing ordering errors by up to 76% over the strongest geometric baseline, and remains robust in multi-page settings and under noisy OCR. Rather than targeting production the method is designed as a data bootstrapping strategy enabling rapid annotation in highly under-resourced scenarios. Alongside the dataset, we release a specialized Tesseract OCR model for historical Armenian print.
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。
