{"slug": "letter-lemmatization-one-to-one-and-banded-rnns-for-reversing-character-set-and", "title": "Letter Lemmatization: One-to-one and Banded RNNs for Reversing Character-Set Simplification and Abbreviation in Medieval Text", "summary": "Researchers at arXiv introduced letter lemmatization, using one-to-one and banded RNNs to reverse character-set simplification and expand abbreviations in medieval texts. The method recovers half the character error rate with self-supervision on 20 text lines and achieves significant improvements in handwritten text recognition post-correction. A Python library implementing these techniques was released.", "body_md": "arXiv:2607.09291v1 Announce Type: new\nAbstract: Medieval document transcribers have very different practices; on top of that, heterogeneous digitization policies have resulted in corpora where the character-set must be viewed as fluid. In this paper we address the problem of changing between character-sets in a flexible manner. We focus on one-to-one character mappings and train characterlevel one-to-one RNNs to undo them with self-supervision; recovering half the CER even with 20 text lines. We analyse the use of these one-to-one networks for HTR post-correction and we see that they obtain significant improvements while totally ignoring ins-dels. We then use the exact same networks with character-level alignment groundtruth compiled from parallel corpora in a training and inference mode we call Banded RNNs. We use such networks to successfully expand abbreviations in medieval charter transcriptions. Finally we introduce an elaborate heuristic which takes the characters of two arbitrary character-sets and defines a metric encapsulating what we consider to be semantic similarity of characters. We call the construction of such mappings letter lemmatization and present a rich Python library that efficiently performs all presented methods.", "url": "https://wpnews.pro/news/letter-lemmatization-one-to-one-and-banded-rnns-for-reversing-character-set-and", "canonical_source": "https://arxiv.org/abs/2607.09291", "published_at": "2026-07-13 04:00:00+00:00", "updated_at": "2026-07-13 04:17:26.257063+00:00", "lang": "en", "topics": ["machine-learning", "natural-language-processing", "ai-research"], "entities": ["arXiv"], "alternates": {"html": "https://wpnews.pro/news/letter-lemmatization-one-to-one-and-banded-rnns-for-reversing-character-set-and", "markdown": "https://wpnews.pro/news/letter-lemmatization-one-to-one-and-banded-rnns-for-reversing-character-set-and.md", "text": "https://wpnews.pro/news/letter-lemmatization-one-to-one-and-banded-rnns-for-reversing-character-set-and.txt", "jsonld": "https://wpnews.pro/news/letter-lemmatization-one-to-one-and-banded-rnns-for-reversing-character-set-and.jsonld"}}