Word-Level Alignment of Paper Documents with their Electronic Full-Text Counterparts

TL;DR

This paper presents an unsupervised, simple method for automatically aligning words between printed documents and their full-text digital versions, achieving high accuracy and potential for various document processing applications.

Contribution

It introduces a novel, unsupervised approach using standard components for precise word-level alignment between printed and digital documents.

Findings

Achieved an F-score of 85.01 in basic setup

Improved F-score to 86.63 with pre- and post-processing

Applicable to database curation and biomedical OCR tasks

Abstract

We describe a simple procedure for the automatic creation of word-level alignments between printed documents and their respective full-text versions. The procedure is unsupervised, uses standard, off-the-shelf components only, and reaches an F-score of 85.01 in the basic setup and up to 86.63 when using pre- and post-processing. Potential areas of application are manual database curation (incl. document triage) and biomedical expression OCR.