Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2602.13905 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914331102281728 |
|---|---|
| author | Clérice, Thibault Bawden, Rachel Glaise, Anthony Pinche, Ariane Smith, David |
| author_facet | Clérice, Thibault Bawden, Rachel Glaise, Anthony Pinche, Ariane Smith, David |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_13905 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Pre-Editorial Normalization for Automatically Transcribed Medieval Manuscripts in Old French and Latin Clérice, Thibault Bawden, Rachel Glaise, Anthony Pinche, Ariane Smith, David Computation and Language 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. |
| title | Pre-Editorial Normalization for Automatically Transcribed Medieval Manuscripts in Old French and Latin |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2602.13905 |