Paper ID: 2210.16391

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

Yichao Zhou, James B. Wendt, Navneet Potti, Jing Xie, Sandeep Tata

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 $10\times$ with a negligible loss in accuracy.

Submitted: Oct 28, 2022