Can I read Radically Lower Data-Labeling Costs for Visually Rich Document Extraction Models on EtoBox?

Radically Lower Data-Labeling Costs for Visually Rich Document Extraction Models by Zhou, Yichao; Wendt, James B.; Potti, Navneet; Xie, Jing; Tata, Sandeep is a scholarly article available to read on EtoBox.

What is Radically Lower Data-Labeling Costs for Visually Rich Document Extraction Models about?

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.

Author

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

Published

2022

Language

EN