English

An Augmentation Strategy for Visually Rich Documents

Computation and Language 2022-12-23 v2

Abstract

Many business workflows require extracting important fields from form-like documents (e.g. bank statements, bills of lading, purchase orders, etc.). Recent techniques for automating this task work well only when trained with large datasets. In this work we propose a novel data augmentation technique to improve performance when training data is scarce, e.g. 10-250 documents. Our technique, which we call FieldSwap, works by swapping out the key phrases of a source field with the key phrases of a target field to generate new synthetic examples of the target field for use in training. We demonstrate that this approach can yield 1-7 F1 point improvements in extraction performance.

Keywords

Cite

@article{arxiv.2212.10047,
  title  = {An Augmentation Strategy for Visually Rich Documents},
  author = {Jing Xie and James B. Wendt and Yichao Zhou and Seth Ebner and Sandeep Tata},
  journal= {arXiv preprint arXiv:2212.10047},
  year   = {2022}
}

Comments

9 pages, 6 figures, 3 tables

R2 v1 2026-06-28T07:43:57.075Z