Historical Document Processing

Overview

The field develops methods for turning historical scans into usable text and structured evidence, from OCR and handwriting recognition to page classification, layout detection, and reading-order reconstruction. Common approaches combine CNNs and Transformers with domain adaptation, synthetic training data, language or vision-language models, and human review; downstream tasks include entity and relation extraction, geocoding, retrieval, and knowledge-graph construction. Work spans multilingual manuscripts, newspapers, books, inscriptions, maps, and specialized records, with benchmarks testing recognition, layout, and information extraction across collections and time periods. A central challenge is generalizing across scripts, layouts, degradation, and OCR noise while avoiding over-correction or unsupported model-generated content, and evaluations often need to measure structural fidelity and downstream usefulness as well as transcription accuracy.

Latest papers

CardsList

80 papers7 papers in the last four weeks, down 36% on the four weeks before. 0.1% of all new papers.

  1. Rewrite, Then Veto: Rewriter-Agnostic Edit Gating for LLM-Based Post-OCR Correction

    Nov 3, 2026Jorge Ramón Fonseca CachoOCR Post-ProcessingHistorical Document Processing

  2. HERIT: Enabling Global Access to Hanja-to-English Historical Translation by Mitigating Temporal Bias

    Nov 3, 2026Dayeon Jeong, Kyeongpil KangMachine TranslationHistorical Document Processing

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

    Oct 27, 2026Tamas Kovacs, Daniel LugerHistorical Document ProcessingForced Alignment

  4. Reading Beyond OCR Noise: Robust Cross-Lingual RAG for Legislative Archives

    Oct 26, 2026Radha Krishna Deshpande, Ajoy Mondal, Akash Manna +1Multilingual RAGHistorical Document Processing

  5. Reading the Registers of Honorius III without Manual Line Transcription: Forced-Aligned HTR, End to End, Modular or Hybrid

    Oct 26, 2026Tamas Kovacs, Daniel LugerHistorical Document ProcessingConformer

  6. Automated, auditable dating of the Babylonian Astronomical Diaries with language models and astronomical tools

    Oct 25, 2026Lucas Carrit Delgado Pinheiro, Yuan-Sen Ting, Jon Clindaniel +3Historical Document AnalysisHistorical Document Processing

  7. TableVision: Recovering Verified Structure from Historical Tables

    Oct 12, 2026Todd Y. Zhou, James M. SnyderTable Structure RecognitionHistorical Document Processing

  8. DDVR-Net: Degradation-Aware Decoupling and Visibility-Guided Restoration for Historical Document Recognition

    Oct 12, 2026Jiu Sha, Yu Weng, Mengxiao ZhuOptical Character RecognitionHistorical Document Processing

  9. Automated Detection and Encoding of Cartographic Signs in Historical Maps

    Oct 9, 2026Remi PetitpierreHistorical Document ProcessingGeospatial Representation Learning

  10. Entity-Aware Evaluation of OCR Systems for Historical Document Transcription

    Oct 7, 2026Camilo Mariño, Diego Belzarena, Marina Gardella +3Optical Character RecognitionHistorical Document Processing

  11. InscriptionOCR: A Dataset and Method for Understanding Inscriptions

    Oct 7, 2026Jaidev Sanjay Khalane, Akbar Ali, V. N. Prabhakar +1Historical Document ProcessingOptical Character Recognition

  12. Which papyrus HTR is good enough? Character-error-rate tolerance of four papyrological tasks on Greek texts

    Sep 29, 2026Anton Repushko, Elena ChepelAutomated EvaluationOptical Character Recognition

  13. Beyond Pixel Reconstruction: Retrieval-Guided Glyph-Aware Restoration for Low-Resource Manchu Historical Documents

    Sep 29, 2026Ting Huang, Dongdong Wang, Mingqiu Liang +1Image RestorationHistorical Document Processing

  14. Think Before You Restore: Risk-Aware Manchu Manuscript Restoration with Stroke-Guided Attention

    Sep 28, 2026Mingqiu Liang, Dongdong Wang, Siyang Lu +2Image RestorationHistorical Document Processing

  15. HPMD: A Historical Persian Manuscript Dataset for Word Spotting with Line-Level Annotation

    Sep 28, 2026Saeid Firouzi Daghigh, Majid Iranpour MobarakehOptical Character RecognitionHistorical Document Processing

  16. A Visual Classification Dataset and Model Evaluation for Historical Manuscript Illustrations

    Sep 27, 2026Yoav Evron, Michal Bar-Asher Siegal, Michael FireVLM EvaluationHistorical Document Analysis

  17. TRACE: Accountable Agentic Retrieval for Source Discovery in Digital Archives

    Sep 17, 2026Donghan Bian, Marie Puren, Florian CafieroData ProvenanceAgentic Retrieval

  18. OCR-Based Field Extraction for Archaeological Pottery Metadata: The CENTURIA Dataset

    Aug 31, 2026Gissu Valentina Naghavi, Dominik Hagmann, Martin Kampel +1Document Information ExtractionOptical Character Recognition

  19. Lot Machine: Multimodal Lot Extraction from Auction Catalogs

    Aug 31, 2026Mathias Zinnen, Alisha Mund, Sabine Lang +3VLM EvaluationDocument Image Understanding

  20. Text Restoration of Ancient Documents with Language Models

    Aug 28, 2026Shibingfeng Zhang, Edoardo Caraffa, Annafelicia Zuffrano +2Historical Document ProcessingText Generation

  21. AraMS-28k: The Largest Publicly Released Line-Level Dataset of Historical Arabic Manuscripts with Margin and Insertion-Anchor Annotations

    Aug 27, 2026Mohamed Guechaoui, Mohamed Diaa Zellagui, Souleyman Chaib +1Historical Document ProcessingOptical Character Recognition

  22. Beyond Recognition: Compact Multi-Domain Arabic Manuscript HTR with Candidate-Selection Analysis and Evidence-Preserving Review

    Aug 19, 2026Abdullah Ahmed Ali, Mohammed Thamer Abdulhadi, Ali Haider Safaa +1OCR Post-ProcessingHistorical Document Processing

  23. Institutional Books - Enriched Text: A customizable multilingual open-source pipeline for denoising, deduplicating, and annotating OCR text at scale

    Aug 19, 2026David Lowry-Duda, Matteo Cargnelutti, Catherine Brobston +4Library and Information ScienceHistorical Document Processing

  24. Institutional Newspapers Pipeline: Deriving billions of high quality tokens from historical newspapers

    Aug 19, 2026Matteo Cargnelutti, Catherine Brobston, Eben English +6Historical Document ProcessingDocument Information Extraction