← Back to all news
Hugging Face Trending Papers

Mining the Nineteenth Century for the Thirteenth: Register-Scale Forced Alignment and HTR Bootstrapping via Legacy Regesta and Antiquarian Editions

The paper investigates how nineteenth‑century scholarship—specifically Pressutti’s regesta and partial editions—can aid handwritten text recognition (HTR) for the registers of Pope Honorius III, which lack modern expert transcriptions beyond regnal years 1‑2. By comparing legacy layers to audited transcriptions, the authors identify a three‑tier division of labor: at the orthographic tier, projecting legacy editions onto curial spelling with replay reduces word‑error rate by 1.5 points; at the lexical tier, a legacy lexicon covers 82.2 % of out‑of‑vocabulary words and improves NER performance; and at the topological tier, regesta data help locate entry starts with 73.9 % coverage and estimate a character‑error rate of 7.80 % beyond folio 203. The study shows that while antiquarian scholarship cannot replace modern transcription, it can effectively steer, verify, and segment HTR across untranscribed registers.

Related stories

arXiv Computation and Language
Oct 28

Mining the Nineteenth Century for the Thirteenth: Register-Scale Forced Alignment and HTR Bootstrapping via Legacy Regesta and Antiquarian Editions

The study evaluates how nineteenth‑century scholarship—specifically Pressutti’s regesta and partial editions—can aid handwritten text recognition (HTR) of Pope Honorius III’s registers beyond the limited modern expert transcriptions available for regnal years 1‑2. By aligning legacy layers with modern source lines, the authors demonstrate that projection onto curial spelling with replay reduces word‑error rate by 1.50 points, that a legacy lexicon covers 82.2 % of out‑of‑vocabulary words and flags errors with 66.7 % precision, and that a distilled medieval NER model achieves an F1 of 82.1 % on a validated benchmark. Additionally, Pressutti’s regesta and related topological data recover 73.9 % of entry starts and suggest a character‑error rate of 7.80 % beyond folio 203, indicating that antiquarian scholarship can steer, check, and segment HTR rather than replace modern transcription.

By Tamas Kovacs, Daniel Luger
benchmarkssafety
More like this →
arXiv Computation and Language
Oct 9

Wieszcz-XIX: A 3.1-Billion-Word Corpus of Pre-1918 Polish and Temporally Bounded Language Models Trained From Scratch

Wieszcz‑XIX is a 6.75‑billion‑token corpus of Polish texts from 1800‑1918, comprising 3.1 billion words across 294,369 documents, assembled from Wolne Lektury and the Internet Archive. The pipeline filters, deduplicates, audits for post‑1918 leakage, and splits at the document level, yielding a training set with only 0.04–0.38 % post‑1918 residue. From this corpus the authors train decoder‑only language models ranging from 47 M to 349 M parameters, demonstrating that larger models better preserve period spelling and exhibit temporal boundedness compared to modern Polish baselines.

By Szymon Kocur
llms
More like this →
arXiv Computation and Language
Aug 28

Pair-Level Essay-Scale Republication and Reuse from Fragmented Historical Text Reuse: A Workflow Study on Eighteenth-Century Books and Newspapers

This study tackles the challenge of identifying essay‑scale republication and reuse from fragmented text evidence, focusing on David Hume essays in eighteenth‑century books and newspapers. It compares a staged rule‑based workflow, baseline decision‑tree and LLM approaches, and automated rule adaptation, finding that pair‑level feature aggregation achieves high F1 scores and that the final workflow offers the best precision‑recall balance. Manual audits confirm all predicted positives as genuine republications, demonstrating the method’s effectiveness in producing compact, auditable candidate sets for historical analysis.

By Ke Shu, Kira Hinderks, Eetu M\"akel\"a, Mikko Tolonen
llms
More like this →
arXiv AI
Aug 26

Auditing the Synthetic Memoir: Measuring Scene-Level Confabulation in LLM-Generated Autobiography Against the Documented Record of the Life It Describes

The paper audits a 366‑day autobiographical book generated by a large language model (LLM) against an independent verification corpus. Using a four‑level rubric, 354 of the 366 days (96.7%) failed verification, with only 12 days containing corroborated scenes and 19 days containing actively contradicted claims. Regenerating the same days with current models yielded 100% verification failure, while grounding the generation in the subject’s own corpus improved the rate to 83.3% but still left substantial residual failure.

By Heather Renze
llms
More like this →
arXiv AI
2d ago

One Scale, Four Texts: Gaps, Overlaps and Silent Repairs in Published Grading Schemes

The paper investigates how different published texts for diabetic retinopathy grading—specifically four versions of an international scale and an Italian guideline—lead to gaps, overlaps, and silent repairs when interpreted literally. By transcribing these texts into a unified rule language and exhaustively enumerating over 1.4 billion finding profiles, the authors show that each text leaves some eyes uncategorized, that the 2017 tabulation contains an empty proliferative class and a macular gap absent in the 2003 text, and that English and Italian texts can order the same eyes differently. Experiments on annotated photographs and language‑model responses further reveal significant disagreements in referral decisions and persistent silent repairs even when models are instructed to read literally.

By Elisa Rovai, Fabio Rovai
llms
More like this →