# Advancing Post-OCR Correction: A Comparative Study of Synthetic Data

arXiv: https://arxiv.org/abs/2408.02253 · HTML: https://mlsanity.com/paper/2408.02253/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 68 references that are in the map.
- First posted on arXiv 5 Aug 2024.

## Builds on (most cited first, 26 of 26)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [Unsupervised Cross-lingual Representation Learning at Scale](https://mlsanity.com/paper/1911.02116/) (2019)
- [Sparks of Artificial General Intelligence: Early experiments with GPT-4](https://mlsanity.com/paper/2303.12712/) (2023)
- [SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing](https://mlsanity.com/paper/1808.06226/) (2018)
- [mT5: A massively multilingual pre-trained text-to-text transformer](https://mlsanity.com/paper/2010.11934/) (2020)
- [Improving Neural Machine Translation Models with Monolingual Data](https://mlsanity.com/paper/1511.06709/) (2015)
- [ByT5: Towards a token-free future with pre-trained byte-to-byte models](https://mlsanity.com/paper/2105.13626/) (2021)
- [Multilingual Translation with Extensible Multilingual Pretraining and Finetuning](https://mlsanity.com/paper/2008.00401/) (2020)
- [Synthetic Data and Artificial Neural Networks for Natural Scene Text Recognition](https://mlsanity.com/paper/1406.2227/) (2014)
- [Training Question Answering Models From Synthetic Data](https://mlsanity.com/paper/2002.09599/) (2020)
- [DataPerf: Benchmarks for Data-Centric AI Development](https://mlsanity.com/paper/2207.10062/) (2022)
- [Data Augmentation Approaches in Natural Language Processing: A Survey](https://mlsanity.com/paper/2110.01852/) (2021)
- [CharBERT: Character-aware Pre-trained Language Model](https://mlsanity.com/paper/2011.01513/) (2020)
- [Sequence-to-Label Script Identification for Multilingual OCR](https://mlsanity.com/paper/1708.04671/) (2017)
- [A Benchmark and Dataset for Post-OCR text correction in Sanskrit](https://mlsanity.com/paper/2211.07980/) (2022)
- [Post-OCR Document Correction with large Ensembles of Character Sequence-to-Sequence Models](https://mlsanity.com/paper/2109.06264/) (2021)
- [Upcycle Your OCR: Reusing OCRs for Post-OCR Text Correction in Romanised Sanskrit](https://mlsanity.com/paper/1809.02147/) (2018)
- [DMOps: Data Management Operation and Recipes](https://mlsanity.com/paper/2301.01228/) (2023)
- [PALI: A Language Identification Benchmark for Perso-Arabic Scripts](https://mlsanity.com/paper/2304.01322/) (2023)
- [Byte-Level Grammatical Error Correction Using Synthetic and Curated Corpora](https://mlsanity.com/paper/2305.17906/) (2023)
- [Enhancing OCR Performance through Post-OCR Models: Adopting Glyph Embedding for Improved Correction](https://mlsanity.com/paper/2308.15262/) (2023)
- [Data Generation for Post-OCR correction of Cyrillic handwriting](https://mlsanity.com/paper/2311.15896/) (2023)

## Built on by (most cited first, 8 of 8)

- [LLaVA Steering: Visual Instruction Tuning with 500x Fewer Parameters through Modality Linear Representation-Steering](https://mlsanity.com/paper/2412.12359/) (2024)
- [PreP-OCR: A Complete Pipeline for Document Image Restoration and Enhanced OCR Accuracy](https://mlsanity.com/paper/2505.20429/) (2025)
- [RoundTripOCR: A Data Generation Technique for Enhancing Post-OCR Error Correction in Low-Resource Devanagari Languages](https://mlsanity.com/paper/2412.15248/) (2024)
- [OCR-EDR: Rendering-Aware Diagnosis and Repair for Closed-Loop OCR Improvement](https://mlsanity.com/paper/2609.03445/) (2026)
- [PsOCR: Benchmarking Large Multimodal Models for Optical Character Recognition in Low-resource Pashto Language](https://mlsanity.com/paper/2505.10055/) (2025)
- [KazakhOCR: A Synthetic Benchmark for Evaluating Multimodal Models in Low-Resource Kazakh Script OCR](https://mlsanity.com/paper/2603.13238/) (2026)
- [DocRevive: A Unified Pipeline for Document Text Restoration](https://mlsanity.com/paper/2604.10077/) (2026)
- [Evaluating In-Context Learning and Retrieval Strategies for Devanagari Post-OCR Correction](https://mlsanity.com/paper/2609.21595/) (2026)

## Abstract (arXiv)

This paper explores the application of synthetic data in the post-OCR domain on multiple fronts by conducting experiments to assess the impact of data volume, augmentation, and synthetic data generation methods on model performance. Furthermore, we introduce a novel algorithm that leverages computer vision feature detection algorithms to calculate glyph similarity for constructing post-OCR synthetic data. Through experiments conducted across a variety of languages, including several low-resource ones, we demonstrate that models like ByT5 can significantly reduce Character Error Rates (CER) without the need for manually annotated data, and our proposed synthetic data generation method shows advantages over traditional methods, particularly in low-resource languages.