Weakly supervised information extraction from inscrutable handwritten document images

TL;DR

This paper presents a weakly supervised method for extracting medicine names from handwritten prescriptions, overcoming OCR errors and limited annotations by identifying relevant regions and using a domain-specific language model trained on synthetic data.

Contribution

It introduces a novel weakly supervised approach that combines region identification with synthetic data-trained language models for handwritten medicine extraction.

Findings

>2.5x improvement over state-of-the-art methods

Effective extraction with only weak labels

Domain-specific language model enhances accuracy

Abstract

State-of-the-art information extraction methods are limited by OCR errors. They work well for printed text in form-like documents, but unstructured, handwritten documents still remain a challenge. Adapting existing models to domain-specific training data is quite expensive, because of two factors, 1) limited availability of the domain-specific documents (such as handwritten prescriptions, lab notes, etc.), and 2) annotations become even more challenging as one needs domain-specific knowledge to decode inscrutable handwritten document images. In this work, we focus on the complex problem of extracting medicine names from handwritten prescriptions using only weakly labeled data. The data consists of images along with the list of medicine names in it, but not their location in the image. We solve the problem by first identifying the regions of interest, i.e., medicine lines from just weak labels and then injecting a domain-specific medicine language model learned using only synthetically generated data. Compared to off-the-shelf state-of-the-art methods, our approach performs >2.5x better in medicine names extraction from prescriptions.