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× with a negligible loss in accuracy.
@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}
}