# An Evaluation of Neural Machine Translation Models on Historical Spelling Normalization

arXiv: https://arxiv.org/abs/1806.05210 · HTML: https://mlsanity.com/paper/1806.05210/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Jun 2018.

## Built on by (most cited first, 5 of 5)

- [Restoring and Mining the Records of the Joseon Dynasty via Neural Language Modeling and Machine Translation](https://mlsanity.com/paper/2104.05964/) (2021)
- [Text normalization for low-resource languages: the case of Ligurian](https://mlsanity.com/paper/2206.07861/) (2022)
- [Historical German Text Normalization Using Type- and Token-Based Language Modeling](https://mlsanity.com/paper/2409.02841/) (2024)
- [Two Spelling Normalization Approaches Based on Large Language Models](https://mlsanity.com/paper/2506.23288/) (2025)
- [Leveraging External Knowledge for Historical Document Restoration via Retrieval-Augmented Large Language Models](https://mlsanity.com/paper/2607.21936/) (2026)

## Abstract (arXiv)

In this paper, we apply different NMT models to the problem of historical spelling normalization for five languages: English, German, Hungarian, Icelandic, and Swedish. The NMT models are at different levels, have different attention mechanisms, and different neural network architectures. Our results show that NMT models are much better than SMT models in terms of character error rate. The vanilla RNNs are competitive to GRUs/LSTMs in historical spelling normalization. Transformer models perform better only when provided with more training data. We also find that subword-level models with a small subword vocabulary are better than character-level models for low-resource languages. In addition, we propose a hybrid method which further improves the performance of historical spelling normalization.