Can AI or Python help us catalogue books we can’t read?
Keywords:
AI, Python, non-English cataloguing, OCR, transliterationAbstract
The potential for using tools like AI and Python to increase the efficiency of library cataloguing is being increasingly recognised. The University of Glasgow Library has a substantial backlog of uncatalogued non-English material, but few staff with the specialist language skills required to tackle it. Recent advances in computerised image analysis and transliteration have made it possible to begin cataloguing this backlog without requiring specialist language skills.
This article discusses a project which started by investigating the viability of using AI tools to help us copy catalogue Russian books. The project found that ChatGPT and Copilot can carry out OCR and transliteration of Russian text quickly and accurately. AI tools, however, come with serious environmental, legal, and ethical drawbacks.
We therefore started developing our own tool written in Python which has similar OCR and transliteration functionality to AI tools but without the associated environmental or ethical costs. The initial results from our Python tool are promising but more development is required.
Our project concluded that both AI and Python can be successfully used to help cataloguers without specialist language skills transliterate non-English texts. To maintain metadata quality, however, cataloguers with language skills must remain an integral part of our workflows.
References
Bashir, N. et al. (2024) 'The Climate and Sustainability Implications of Generative AI', in An MIT Exploration of Generative AI. Available at: https://doi.org/10.21428/e4baedd9.9070dfe7 [Accessed: 18 August 2026]
Carrington, D. and Kassam, A. (2026) 'UK and Switzerland record hottest ever June day as health emergencies surge in Europe', The Guardian, 25 June. Available at: https://web.archive.org/web/20260629171559/https://www.theguardian.com/environment/2026/jun/25/highest-june-minimum-temperature-record-broken-cardiff-savage-heatwave-continues [Accessed: 18 August 2026]
Dover, A. and Grzegorski, J. (2025) 'Artificial Intelligence Through the Lens of the Cataloguing Code of Ethics', Cataloging & Classification Quarterly, 63(6–7), pp. 600–620. Available at: https://doi.org/10.1080/01639374.2025.2544137 [Accessed: 18 August 2026]
Engel, J. Y. et al. (2025) 'Artificial Intelligence in Library Cataloging: A Review of Literature', Journal of Library Metadata, 25(4), pp. 261–276, Available at: https://doi.org/10.1080/19386389.2025.2526913 [Accessed: 18 August 2026]
Farsi, F. et al. (2025) 'ParsiPy: NLP Toolkit for Historical Persian Texts in Python', Second Workshop on Ancient Language Processing, Albuquerque, 3–4 May. Association for Computational Linguistics, pp. 238–250. Available at: https://doi.org/10.18653/v1/2025.alp-1.17 [Accessed: 18 August 2026]
Gamage, R. and Wanigasooriya, P. (2024) 'Using Generative AI for Bibliographic Description: A Study with ChatGPT 4', Journal of the University Librarians Association of Sri Lanka, 27(2), pp. 257–284. Available at: https://doi.org/10.4038/jula.v27i2.8083 [Accessed: 18 August 2026]
Geroimenko, V. (2025) The Essential Guide to Prompt Engineering: Key Principles, Techniques, Challenges, and Security Risks. Springer.
Goodale, I. (2023) Domovyk (Version 1.0.1) [Computer program]. Available at: https://github.com/ian-nai/domovyk [Accessed: 18 August 2026]
Harisanty, D. et al. (2023) 'Is Adopting Artificial Intelligence in Libraries Urgency or a Buzzword? A Systematic Literature Review', Journal of Information Science, 51(2), pp. 511–522. Available at: https://doi.org/10.1177/01655515221141034 [Accessed: 18 August 2026]
Jiang, Y. et al. (2024) 'Exploring the Potential Applications of Generative AI in East Asian Librarianship: Use Cases, Reflections, and Inspirations', Journal of East Asian Libraries, 179, pp. 43–58. Available at: https://scholarsarchive.byu.edu/jeal/vol2024/iss179/5/ [Accessed: 18 August 2026]
Kilić, M. (2025) 'Using AI Tools for Slavic Transliteration to Support Cataloging Workflows: Potential Use Cases and Limitations', Slavic & East European Information Resources, 26(1–2), pp. 80–91. Available at: https://doi.org/10.1080/15228886.2025.2518369 [Accessed: 18 August 2026]
Lee, M. A. (2023) Pytesseract (Version 0.3.13) [Computer program]. Available at: https://github.com/madmaze/pytesseract [Accessed: 18 August 2026]
Library of Congress (2012a) Russian Romanization Table. Available at: https:/www.loc.gov/catdir/cpso/romanization/russian.pdf [Accessed: 3 September 2026]
Library of Congress (2012b) Russian Romanization Table [Source document]. Available at: https://www.loc.gov/catdir/cpso/romanization/russian.doc [Accessed: 3 September 2026]
Michalak, R. and Ellixson, D. (2024) 'Buy Versus Build: Navigating Artificial Intelligence (AI) Tool Adoption in Academic Libraries', Information Services and Use, 44(4), pp. 316–326. Available at: https://doi.org/10.1177/18758789241296755 [Accessed: 18 August 2026]
Moirangthem, G. and Nongmeikapam, K. (2026) 'Optimizing Low-Resource Machine Transliteration: A Case of Script Transition from Manipuri in Bengali Script to Meetei-Mayek', ACM Transactions on Asian and Low-Resource Language Information Processing, 25(5). Available at: https://doi.org/10.1145/3806198 [Accessed: 18 August 2026]
Nam, H. D. (2026) 'The Paradox of Fair Use – A Giant on a Seesaw: Restoring the Balance in Copyright and Media-Specific Issues', GRUR International, 75(7), pp. 605–606. Available at: https://doi.org/10.1093/grurint/ikag001 [Accessed: 18 August 2026]
'The New York Times Company v. Microsoft Corporation' (2023) United States District Court for the Southern District of New York, 1:23-cv-11195. Court Listener. Available at: https://www.courtlistener.com/docket/68117049/the-new-york-times-company-v-microsoft-corporation/#entry-1 [Accessed: 18 August 2026]
Ogungbenro, O. D. et al. (2025) 'Revolutionizing Library Services: The Impact of Artificial Intelligence on Cataloguing and Access to Information in Nigeria Academic Libraries', Journal of Library Metadata, 25(2), pp. 99–118. Available at: https://doi.org/10.1080/19386389.2025.2475418 [Accessed: 18 August 2026]
Oyighan, D. et al. (2024) 'The Role of AI in Transforming Metadata Management: Insights on Challenges, Opportunities, and Emerging Trends', Asian Journal of Information Science and Technology, 14(2), pp. 20–26. Available at: https://doi.org/10.70112/ajist-2024.14.2.4277 [Accessed: 18 August 2026]
PCC Task Group on AI and Machine Learning for Cataloging and Metadata (2025) PCC Task Group on AI and Machine Learning in Cataloging and Metadata: Final Report. Available at: https://web.archive.org/web/20260708094646/https://www.loc.gov/aba/pcc/taskgroup/AI-and-Machine-Learning-TG-final-report.pdf [Accessed: 18 August 2026]
Roy, S. (2025) 'Global Scriptualization of Sanskrit: AI-Assisted OCR, Transliteration, and Translation Across 50+ Languages and Scripts' [Preprint]. Available at: https://doi.org/10.13140/RG.2.2.35119.60326 [Accessed: 18 August 2026]
Shrividya, M. L. et al. (2025) 'Multilingual Digitization of Ancient Manuscripts: OCR-Based Preservation and Translation', 5th International Conference on Emerging Research in Electronics, Computer Science and Technology (ICERECT), Mandya, 12–13 September. IEEE. Available at: https://doi.org/10.1109/ICERECT65215.2025.11377349 [Accessed: 18 August 2026]
Sun, L. (2025) 'Enhancing Cataloging with Generative AI: Converting Wade-Giles to Pinyin', Cataloging & Classification Quarterly, 63(4), pp. 267–283. Available at: https://doi.org/10.1080/01639374.2025.2508956 [Accessed: 18 August 2026]
Sussmeier, S. and Henry, J. A. (2025) 'Mind the Gap!: How Do We Ethically Bridge the Divide Between the Cataloging/Metadata Community and the World of AI?', Journal of Library Metadata, 25(4), pp. 241–259. Available at: https://doi.org/10.1080/19386389.2025.2525720 [Accessed: 18 August 2026]
Togia, A. et al. (2026) 'Artificial Intelligence in Greek Libraries: Perceptions, Challenges, and Readiness for Adoption', Journal of Librarianship and Information Science. Available at: https://doi.org/10.1177/09610006251410240 [Accessed: 18 August 2026]
Tour, E. et al. (2025) 'Potnia: A Python Library for the Conversion of Transliterated Ancient Texts to Unicode', Journal of Open Source Software, 10(108). Available at: https://doi.org/10.21105/joss.07725 [Accessed: 18 August 2026]
United Nations Independent International Scientific Panel on Artificial Intelligence (2026) Preliminary Report of the Independent International Scientific Panel on AI: Evidence-Based Assessment of Opportunities, Risks and Impacts of Artificial Intelligence. United Nations. Available at: https://web.archive.org/web/20260710091141/https://www.un.org/independent-international-scientific-panel-ai/sites/default/files/2026-07/en_Preliminary%20Report_.pdf [Accessed: 18 August 2026]
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Adam Swann, Sally Bell
This work is licensed under a Creative Commons Attribution 4.0 International License.
