# Pre-Editorial Normalization for Automatically Transcribed Medieval Manuscripts in Old French and Latin

arXiv: https://arxiv.org/abs/2602.13905 · HTML: https://mlsanity.com/paper/2602.13905/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 78 references that are in the map.
- First posted on arXiv 14 Feb 2026.

## Builds on (most cited first, 12 of 12)

- [ByT5: Towards a token-free future with pre-trained byte-to-byte models](https://mlsanity.com/paper/2105.13626/) (2021)
- [Synthetic and Natural Noise Both Break Neural Machine Translation](https://mlsanity.com/paper/1711.02173/) (2017)
- [MTNT: A Testbed for Machine Translation of Noisy Text](https://mlsanity.com/paper/1809.00388/) (2018)
- [Exploring Document-Level Literary Machine Translation with Parallel Paragraphs from World Literature](https://mlsanity.com/paper/2210.14250/) (2022)
- [Improving Robustness of Machine Translation with Synthetic Noise](https://mlsanity.com/paper/1902.09508/) (2019)
- [Did Translation Models Get More Robust Without Anyone Even Noticing?](https://mlsanity.com/paper/2403.03923/) (2024)
- [Utilizing Character and Word Embeddings for Text Normalization with Sequence-to-Sequence Models](https://mlsanity.com/paper/1809.01534/) (2018)
- [Adversarial Subword Regularization for Robust Neural Machine Translation](https://mlsanity.com/paper/2004.14109/) (2020)
- [Normalization of Transliterated Words in Code-Mixed Data Using Seq2Seq Model & Levenshtein Distance](https://mlsanity.com/paper/1805.08701/) (2018)
- [GNAT: A General Narrative Alignment Tool](https://mlsanity.com/paper/2311.03627/) (2023)
- [Normalized vs Diplomatic Annotation: A Case Study of Automatic Information Extraction from Handwritten Uruguayan Birth Certificates](https://mlsanity.com/paper/2507.08636/) (2025)
- [Transcribing Spanish Texts from the Past: Experiments with Transkribus, Tesseract and Granite](https://mlsanity.com/paper/2507.04878/) (2025)

## Abstract (arXiv)

Recent advances in Automatic Text Recognition (ATR) have improved access to historical archives, yet a methodological divide persists between palaeographic transcriptions and normalized digital editions. While ATR models trained on more palaeographically-oriented datasets such as CATMuS have shown greater generalizability, their raw outputs remain poorly compatible with most readers and downstream NLP tools, thus creating a usability gap. On the other hand, ATR models trained to produce normalized outputs have been shown to struggle to adapt to new domains and tend to over-normalize and hallucinate. We introduce the task of Pre-Editorial Normalization (PEN), which consists in normalizing graphemic ATR output according to editorial conventions, which has the advantage of keeping an intermediate step with palaeographic fidelity while providing a normalized version for practical usability. We present a new dataset derived from the CoMMA corpus and aligned with digitized Old French and Latin editions using passim. We also produce a manually corrected gold-standard evaluation set. We benchmark this resource using ByT5-based sequence-to-sequence models on normalization and pre-annotation tasks. Our contributions include the formal definition of PEN, a 4.66M-sample silver training corpus, a 1.8k-sample gold evaluation set, and a normalization model achieving a 6.7% CER, substantially outperforming previous models for this task.