Research

Paper

AI LLM March 10, 2026

The Patrologia Graeca Corpus: OCR, Annotation, and Open Release of Noisy Nineteenth-Century Polytonic Greek Editions

Authors

Chahan Vidal-Gorène, Bastien Kindt

Abstract

We present the Patrologia Graeca Corpus, the first large-scale open OCR and linguistic resource for nineteenthcentury editions of Ancient Greek. The collection covers the remaining undigitized volumes of the Patrologia Graeca (PG), printed in complex bilingual (Greek-Latin) layouts and characterized by highly degraded polytonic Greek typography. Through a dedicated pipeline combining YOLO-based layout detection and CRNN-based text recognition, we achieve a character error rate (CER) of 1.05% and a word error rate (WER) of 4.69%, largely outperforming existing OCR systems for polytonic Greek. The resulting corpus contains around six million lemmatized and part-of-speech tagged tokens, aligned with full OCR and layout annotations. Beyond its philological value, this corpus establishes a new benchmark for OCR on noisy polytonic Greek and provides training material for future models, including LLMs.

Metadata

arXiv ID: 2603.09470
Provider: ARXIV
Primary Category: cs.CV
Published: 2026-03-10
Fetched: 2026-03-11 06:02

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.09470v1</id>\n    <title>The Patrologia Graeca Corpus: OCR, Annotation, and Open Release of Noisy Nineteenth-Century Polytonic Greek Editions</title>\n    <updated>2026-03-10T10:21:54Z</updated>\n    <link href='https://arxiv.org/abs/2603.09470v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.09470v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>We present the Patrologia Graeca Corpus, the first large-scale open OCR and linguistic resource for nineteenthcentury editions of Ancient Greek. The collection covers the remaining undigitized volumes of the Patrologia Graeca (PG), printed in complex bilingual (Greek-Latin) layouts and characterized by highly degraded polytonic Greek typography. Through a dedicated pipeline combining YOLO-based layout detection and CRNN-based text recognition, we achieve a character error rate (CER) of 1.05% and a word error rate (WER) of 4.69%, largely outperforming existing OCR systems for polytonic Greek. The resulting corpus contains around six million lemmatized and part-of-speech tagged tokens, aligned with full OCR and layout annotations. Beyond its philological value, this corpus establishes a new benchmark for OCR on noisy polytonic Greek and provides training material for future models, including LLMs.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.CV'/>\n    <published>2026-03-10T10:21:54Z</published>\n    <arxiv:primary_category term='cs.CV'/>\n    <arxiv:journal_ref>Language Resources and Evaluation Conference, May 2026, Palma De Majorque, Spain</arxiv:journal_ref>\n    <author>\n      <name>Chahan Vidal-Gorène</name>\n      <arxiv:affiliation>CJM, LIPN</arxiv:affiliation>\n    </author>\n    <author>\n      <name>Bastien Kindt</name>\n    </author>\n  </entry>"
}