Using AI Tools for Slavic Transliteration to Support Cataloging Workflows: Potential Use Cases and Limitations
Bibliographic record
Abstract
The Library of Congress (LC), in cooperation with the American Library Association (ALA), provides Romanization Tables for the non-Latin script to support the discovery of materials and improved access for users searching in Latin script. With the emergence of AI tools, Cyrillic script can be transliterated quickly and efficiently with the use of Python scripting. Using Microsoft Copilot and the ALA-LC Romanization Tables, Copilot was able to read ALA-LC Tables and generate code to transliterate text into Romanized equivalents based on well-formed prompts. The transliteration code was applied to hundreds of bibliographic records, successfully parsing titles from records, transliterating titles, and exporting new files with improved metadata. This paper describes the process of using generative AI to transliterate Cyrillic script into Latin script; provides an assessment of the quality of transliteration generated by the Copilot code; and highlights potential applications and limitations of AI in transliteration.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.023 | 0.074 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 0.004 |
| Science and technology studies | 0.002 | 0.003 |
| Scholarly communication | 0.008 | 0.010 |
| Open science | 0.004 | 0.004 |
| Research integrity | 0.001 | 0.003 |
| Insufficient payload (model declined to judge) | 0.008 | 0.006 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".