A Novel Machine Learning Based Approach for Post-OCR Error Detection

Shafqat Mumtaz Virk, Dana Dannélls, Azam Sheikh Muhammad


Abstract
Post processing is the most conventional approach for correcting errors that are caused by Optical Character Recognition(OCR) systems. Two steps are usually taken to correct OCR errors: detection and corrections. For the first task, supervised machine learning methods have shown state-of-the-art performances. Previously proposed approaches have focused most prominently on combining lexical, contextual and statistical features for detecting errors. In this study, we report a novel system to error detection which is based merely on the n-gram counts of a candidate token. In addition to being simple and computationally less expensive, our proposed system beats previous systems reported in the ICDAR2019 competition on OCR-error detection with notable margins. We achieved state-of-the-art F1-scores for eight out of the ten involved European languages. The maximum improvement is for Spanish which improved from 0.69 to 0.90, and the minimum for Polish from 0.82 to 0.84.
Anthology ID:
2021.ranlp-1.164
Volume:
Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021)
Month:
September
Year:
2021
Address:
Held Online
Editors:
Ruslan Mitkov, Galia Angelova
Venue:
RANLP
SIG:
Publisher:
INCOMA Ltd.
Note:
Pages:
1463–1470
Language:
URL:
https://aclanthology.org/2021.ranlp-1.164
DOI:
Bibkey:
Cite (ACL):
Shafqat Mumtaz Virk, Dana Dannélls, and Azam Sheikh Muhammad. 2021. A Novel Machine Learning Based Approach for Post-OCR Error Detection. In Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2021), pages 1463–1470, Held Online. INCOMA Ltd..
Cite (Informal):
A Novel Machine Learning Based Approach for Post-OCR Error Detection (Virk et al., RANLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.ranlp-1.164.pdf