Post-OCR Document Correction with large Ensembles of Character Sequence-to-Sequence Models

TL;DR

This paper introduces a novel ensemble-based character sequence-to-sequence approach for post-OCR document correction, effectively handling long strings and achieving state-of-the-art results across multiple languages.

Contribution

It presents strategies for processing long OCR texts efficiently using ensemble models and voting schemes, advancing post-OCR correction methods.

Findings

Achieved state-of-the-art results in five languages from ICDAR 2019.

Developed a voting scheme for ensemble correction of long strings.

Demonstrated resource-efficient processing of long documents.

Abstract

In this paper, we propose a novel method based on character sequence-to-sequence models to correct documents already processed with Optical Character Recognition (OCR) systems. The main contribution of this paper is a set of strategies to accurately process strings much longer than the ones used to train the sequence model while being sample- and resource-efficient, supported by thorough experimentation. The strategy with the best performance involves splitting the input document in character n-grams and combining their individual corrections into the final output using a voting scheme that is equivalent to an ensemble of a large number of sequence models. We further investigate how to weigh the contributions from each one of the members of this ensemble. We test our method on nine languages of the ICDAR 2019 competition on post-OCR text correction and achieve a new state-of-the-art performance in five of them. Our code for post-OCR correction is shared at https://github.com/jarobyte91/post_ocr_correction.