SOURCE-LINKED INTELLIGENCE

Combining Synthetic and Real Data for Low-Resource Historical OCR: A Manchu Case Study

arXiv · AI, language, vision and robotics · article · Sep 10, 2026 · UTC

Manchu, now critically endangered, was one of the principal languages of the Qing empire (1636-1912), and its extensive archival record is increasingly digitized but remains difficult to search and analyze at scale. Previous work showed that vision-language models (VLMs) trained only on synthetic Manchu word images can reach 87.4% word accuracy on real Qing manuscripts and prints, leaving a substantial synthetic-to-real gap. This study examines how synthetic and real historical training data should be combined for low-resource OCR. Using 60,000 synthetic and 20,306 real historical word images,

Read original source ↗ Open in workspace

recordType

paper

region

Global