Artificial Intelligence and the Transcription of Handwritten Documents in Archives: a Proposal for a Procedural Protocol to Ensure Transparency, Traceability, and Scientific Validation
DOI:
https://doi.org/10.60923/issn.2532-8816/24856Keywords:
artificial intelligence, archives, Handwritten Text Recognition (HTR), methodological protocol, metadataAbstract
The introduction of artificial intelligence (AI) into archives, particularly in handwritten text recognition (HTR) systems, offers new opportunities to improve access to and search capabilities within documentary sources. However, these technologies operate primarily at the level of graphic form and risk reducing the document to mere text to be decoded, thereby neglecting its context of creation and archival relationships. Since transcription always involves interpretive choices, the use of artificial intelligence must be understood as a support to archival work and not as a replacement for it. Despite good levels of accuracy, these systems don’t understand the context of the text and therefore require constant human intervention during the training, review, and validation phases. This paper proposes the adoption of a standardized and transparent methodological approach for AI-assisted transcription processes, based on the documentation of computational stages, codified procedures for human review, and tools for the quantitative evaluation of transcriptions, clearly distinguishing between automated and human stages. Furthermore, integrating this information into the metadata of digital documents makes the transcription process explicit, traceable, and verifiable. In this context, the archivist maintains a central role as a mediator between the documentary heritage and computational tools.
References
AlKendi, Wissam, Franck Gechter, Laurent Heyberger, et al.. 2024. “Advancements and Challenges in Handwritten Text Recognition: A Comprehensive Survey”. Journal of Imaging 10 (1), 18: 1-30. https://doi.org/10.3390/jimaging10010018.
Capurro, Carlotta, Vera Provatorova, and Evangelos Kanoulas. 2023. “Experimenting with Training a Neural Network in Transkribus to Recognise Text in a Multilingual and Multi-Authored Manuscript Collection”, Heritage, 6(12), 7482–7494. https://doi.org/10.3390/heritage6120392.
Ciula, Arianna, and Øyvind Eide. 2014. “Reflections on cultural heritage and digital humanities: modelling in practice and theory”. In DATeCH ‘14: Proceedings of the First International Conference on Digital Access to Textual Cultural Heritage: 35-41. https://doi.org/10.1145/2595188.2595207.
Cummings, James, and Diane Jakacki. 2024. “Preserving Abbreviations and Tagging: Retaining Intellectual Content in HTR to TEI Workflows in the Evolving Hands project.” Proceedings of the Digital Humanities Congress 2024.
Garrido-Munoz, Carlos, Antonio Rios-Vila, and Jorge Calvo-Zaragoza. 2025. “Handwritten Text Recognition: A Survey”. IEEE Transactions on Pattern Analysis and Machine Intelligence 48 (4): 4367-4387. https://doi.org/10.1109/TPAMI.2025.3646002.
Huskey, Samuel J., 2024. “Committing to reproducibility and explainability: using Git as a research journal”. International Journal of Digital Humanities 6: 9-21. https://doi.org/10.1007/s42803-023-00076-9.
Kiessling, Benjamin. 2025 “Kraken - A Universal Text Recognizer for the Humanities”. Digital Humanities 2019: 1-7. https://hal.science/hal-04936936v1.
Lebo, Timothy, Satya Sahoo, Deborah McGuinness, et al. 2013. “PROV-O: The PROV Ontology.” W3C Recommendation, 30 April 2013. https://www.w3.org/TR/2013/REC-prov-o-20130430/.
Maness, J. M., and K. Pham. 2022. “Just Because We Can Doesn”t Mean We Should: On Knowing and Protecting Data Produced by the Jewish Consumptives” Relief Society”, Humanist Studies & the Digital Age, 7(1), 1–14. https://doi.org/10.5399/uo/hsda/7.1.8.
Momtaz, Yahya, Lorenza Laccetti, and Guido Russo. 2025. “Modular pipeline for text recognition in early printed books using Kraken and ByT5”. Electronics 14 (3083): 1-16. https://doi.org/10.3390/electronics14153083.
Nockels, Joe, Paul Gooding, Sarah Ames, and Melissa Terras. 2022. “Understanding the application of handwritten text recognition technology in heritage contexts: a systematic review of Transkribus in published research”. Archival Science 22: 367-392. https://doi.org/10.1007/s10502-022-09397-0.
Peer, Marco, Anna Scius-Bertrand, and Andreas Fischer. 2025. “CTC Transcription Alignment of the Bullinger Letters: Automatic Improvement of Annotation Quality”, Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) Workshops, 7616–7625. https://doi.org/10.1109/ICCVW69036.2025.00783.
Rakesh, Salakapuri, Kushal Reddy Patlolla, Prashanth Venkat, et al. 2024. “Handwritten text recognition using deep learning techniques: A survey”. MATEC Web of Conferences, 392 (01126): 1-8. https://doi.org/10.1051/matecconf/202439201126.
Reul, Christian, Stefan Tomasek, Florian Langhanki, and Uwe Springmann. 2022. “Open Source Handwritten Text Recognition on Medieval Manuscripts using Mixed Models and Document-Specific Finetuning”. In International Workshop on Document Analysis Systems, Springer: 1-30. https://doi.org/10.48550/arXiv.2201.07661.
Romein, Annemieke, Achim Rabus, Gundram Leifert, et al. 2025. “Assessing advanced handwritten text recognition engines for digitizing historical documents”. International Journal of Digital Humanities 7: 115-134. https://doi.org/10.1007/s42803-025-00100-0.
Ströbel, Phillip Benjamin, Simon Clematide, and Martin Volk. 2020. “How Much Data Do You Need? About the Creation of a Ground Truth for Black Letter and the Effectiveness of Neural OCR.” Proceedings of LREC 2020, 3551–3559. Marseille: European Language Resources Association. https://aclanthology.org/2020.lrec-1.436/.
Švītiņa, Laura. 2024. “From Manuscripts to Machine-Readable Texts: Developing AI Model for Latvian Autobiographic Heritage”, Baltic Journal of Modern Computing, 12(4), 628–635. https://doi.org/10.22364/bjmc.2024.12.4.22.
Torres Aguilar, Sergio, and Vincent Jolivet. 2023. “Handwritten Text Recognition for Documentary Medieval Manuscripts”, Journal of Data Mining and Digital Humanities: 1-11 https://doi.org/10.46298/jdmdh.10484.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Stefania Conte

This work is licensed under a Creative Commons Attribution 4.0 International License.