# Estimating Post-OCR Denoising Complexity on Numerical Texts

arXiv: https://arxiv.org/abs/2307.01020 · HTML: https://mlsanity.com/paper/2307.01020/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 29 references that are in the map.
- First posted on arXiv 3 Jul 2023.

## Builds on (most cited first, 9 of 9)

- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [ByT5: Towards a token-free future with pre-trained byte-to-byte models](https://mlsanity.com/paper/2105.13626/) (2021)
- [FUNSD: A Dataset for Form Understanding in Noisy Scanned Documents](https://mlsanity.com/paper/1905.13538/) (2019)
- [ICDAR2019 Competition on Scanned Receipt OCR and Information Extraction](https://mlsanity.com/paper/2103.10213/) (2021)
- [OpenNMT: Open-source Toolkit for Neural Machine Translation](https://mlsanity.com/paper/1709.03815/) (2017)
- [Representing Numbers in NLP: a Survey and a Vision](https://mlsanity.com/paper/2103.13136/) (2021)
- [Kleister: A novel task for Information Extraction involving Long Documents with Complex Layout](https://mlsanity.com/paper/2003.02356/) (2020)
- [Post-OCR Document Correction with large Ensembles of Character Sequence-to-Sequence Models](https://mlsanity.com/paper/2109.06264/) (2021)

## Built on by (most cited first, 1 of 1)

- [Confidence-Aware Document OCR Error Detection](https://mlsanity.com/paper/2409.04117/) (2024)

## Abstract (arXiv)

Post-OCR processing has significantly improved over the past few years. However, these have been primarily beneficial for texts consisting of natural, alphabetical words, as opposed to documents of numerical nature such as invoices, payslips, medical certificates, etc. To evaluate the OCR post-processing difficulty of these datasets, we propose a method to estimate the denoising complexity of a text and evaluate it on several datasets of varying nature, and show that texts of numerical nature have a significant disadvantage. We evaluate the estimated complexity ranking with respect to the error rates of modern-day denoising approaches to show the validity of our estimator.