# An Unsupervised method for OCR Post-Correction and Spelling Normalisation for Finnish

arXiv: https://arxiv.org/abs/2011.03502 · HTML: https://mlsanity.com/paper/2011.03502/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Nov 2020.

## Built on by (most cited first, 9 of 9)

- [OCR-free Document Understanding Transformer](https://mlsanity.com/paper/2111.15664/) (2021)
- [Multimodal LLMs for OCR, OCR Post-Correction, and Named Entity Recognition in Historical Documents](https://mlsanity.com/paper/2504.00414/) (2025)
- [OCR Error Post-Correction with LLMs in Historical Documents: No Free Lunches](https://mlsanity.com/paper/2502.01205/) (2025)
- [Lemmatization of Historical Old Literary Finnish Texts in Modern Orthography](https://mlsanity.com/paper/2107.03266/) (2021)
- [The Current State of Finnish NLP](https://mlsanity.com/paper/2109.11326/) (2021)
- [From Plenipotentiary to Puddingless: Users and Uses of New Words in Early English Letters](https://mlsanity.com/paper/2103.09926/) (2021)
- [TransDocAnalyser: A Framework for Offline Semi-structured Handwritten Document Analysis in the Legal Domain](https://mlsanity.com/paper/2306.02142/) (2023)
- [Comparative analysis of optical character recognition methods for S'ami texts from the National Library of Norway](https://mlsanity.com/paper/2501.07300/) (2025)
- [TFW2V: An Enhanced Document Similarity Method for the Morphologically Rich Finnish Language](https://mlsanity.com/paper/2112.12489/) (2021)

## Abstract (arXiv)

Historical corpora are known to contain errors introduced by OCR (optical character recognition) methods used in the digitization process, often said to be degrading the performance of NLP systems. Correcting these errors manually is a time-consuming process and a great part of the automatic approaches have been relying on rules or supervised machine learning. We build on previous work on fully automatic unsupervised extraction of parallel data to train a character-based sequence-to-sequence NMT (neural machine translation) model to conduct OCR error correction designed for English, and adapt it to Finnish by proposing solutions that take the rich morphology of the language into account. Our new method shows increased performance while remaining fully unsupervised, with the added benefit of spelling normalisation. The source code and models are available on GitHub and Zenodo.