Visually Rich Documents (VRDs), comprising elements such as charts, tables, and paragraphs, convey complex information across diverse domains. However, extracting key information from these documents remains labour-intensive, particularly for scanned formats with inconsistent layouts and domain-specific requirements. Despite advances in pretrained models for VRD understanding, their dependence on large annotated datasets for fine-tuning hinders scalability. This paper proposes \textbf{SynJAC} (Synthetic-data-driven Joint-granular Adaptation and Calibration), a method for key information extraction in scanned documents. SynJAC leverages synthetic, machine-generated data for domain adaptation and employs calibration on a small, manually annotated dataset to mitigate noise. By integrating fine-grained and coarse-grained document representation learning, SynJAC significantly reduces the need for extensive manual labelling while achieving competitive performance. Extensive experiments demonstrate its effectiveness in domain-specific and scanned VRD scenarios.
@article{arxiv.2410.01609,
title = {SynJAC: Synthetic-data-driven Joint-granular Adaptation and Calibration for Domain Specific Scanned Document Key Information Extraction},
author = {Yihao Ding and Soyeon Caren Han and Zechuan Li and Hyunsuk Chung},
journal= {arXiv preprint arXiv:2410.01609},
year = {2025}
}