Multidimensional Information Extraction from Digitized Chinese Historical Documents via Relation-Aware Semantic Enhancement
Academic Journal of Applied Sciences · 2026
DOI: 10.54097/5pkh5531 ↗Kurz gefasst
Fachartikel in der Zeitschrift Academic Journal of Applied Sciences, 2026. Verfasst von Lei Zhang und 3 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).
Abstract (Originalsprache)
Complex layouts, rare characters, and irregular reading orders pose challenges to optical character recognition (OCR) and semantic information extraction from Chinese historical documents. To address these challenges, we propose Relation-Guided and Semantics-Enhanced TongGuOCR (RSE-TongGuOCR). A category-aware relation predictor integrates learned reading dependencies into geometry-based block construction, while dynamic programming selects recognition blocks to preserve both local context and character legibility. To promote consistency between layout analysis and text decoding, a cross-branch constraint aligns layout-based relation predictions with decoder-generated transition tokens in a shared spatial transition space. The framework retains rare-character vocabulary expansion and incorporates an ancient Chinese named entity recognition (NER) branch to identify six categories of historical entities in transcribed text. The OCR and NER components are trained in stages using distinct annotation sources and evaluated independently. RSE-TongGuOCR achieves an AR of 94.38 and an RO-ED of 2.86 on M5HisDoc, while its NER branch attains an F1 score of 85.84% on EvaHan2025 Dataset A. These task-specific results support the framework’s effectiveness in document transcription, reading-order recovery, and structured historical information extraction.
Zitieren
APA
Zhang, L., Ren, P., Guo, R., & Zhao, J. (2026). Multidimensional Information Extraction from Digitized Chinese Historical Documents via Relation-Aware Semantic Enhancement. Academic Journal of Applied Sciences. https://doi.org/10.54097/5pkh5531
Vancouver
Zhang L, Ren P, Guo R, Zhao J. Multidimensional Information Extraction from Digitized Chinese Historical Documents via Relation-Aware Semantic Enhancement. Academic Journal of Applied Sciences. 2026. doi:10.54097/5pkh5531
BibTeX
@article{Zhang2026,
author = {Zhang, Lei and Ren, Peng and Guo, Rui and Zhao, Jinjiang},
title = {Multidimensional Information Extraction from Digitized Chinese Historical Documents via Relation-Aware Semantic Enhancement},
journal = {Academic Journal of Applied Sciences},
year = {2026},
doi = {10.54097/5pkh5531}
}
EUVIMED