English

Radically Lower Data-Labeling Costs for Visually Rich Document Extraction Models

Computation and Language 2022-11-01 v1

Abstract

A key bottleneck in building automatic extraction models for visually rich documents like invoices is the cost of acquiring the several thousand high-quality labeled documents that are needed to train a model with acceptable accuracy. We propose Selective Labeling to simplify the labeling task to provide "yes/no" labels for candidate extractions predicted by a model trained on partially labeled documents. We combine this with a custom active learning strategy to find the predictions that the model is most uncertain about. We show through experiments on document types drawn from 3 different domains that selective labeling can reduce the cost of acquiring labeled data by 10×10\times with a negligible loss in accuracy.

Keywords

Cite

@article{arxiv.2210.16391,
  title  = {Radically Lower Data-Labeling Costs for Visually Rich Document Extraction Models},
  author = {Yichao Zhou and James B. Wendt and Navneet Potti and Jing Xie and Sandeep Tata},
  journal= {arXiv preprint arXiv:2210.16391},
  year   = {2022}
}

Comments

9 pages, 8 figures, 3 tables

R2 v1 2026-06-28T04:44:49.781Z