用合成数据+小样本校准，高效提取扫描文档关键信息
SynJAC: Synthetic-data-driven Joint-granular Adaptation and Calibration for Domain Specific Scanned Document Key Information Extraction
- 用机器生成的合成数据做域适应，降低标注依赖
- 在少量人工标注数据上校准，有效抑制噪声影响
- 适合需要快速适配新领域的扫描文档信息提取任务
视觉丰富文档（VRDs）包含图表、表格和段落等元素，跨领域传递复杂信息。然而，从这些文档中提取关键信息仍需大量人力，尤其是对布局不一致且具有领域特性的扫描版文档。尽管预训练模型在VRD理解方面取得进展，但其对大规模标注数据的依赖限制了可扩展性。本文提出SynJAC（合成数据驱动的联合粒度自适应与校准），用于扫描文档中的关键信息提取。SynJAC利用机器生成的合成数据进行域适应，并在少量人工标注数据上进行校准以缓解噪声问题。通过融合细粒度与粗粒度文档表征学习，显著减少对大规模手动标注的需求，同时实现竞争力性能。大量实验验证了其在特定领域和扫描型VRD场景下的有效性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。