AI-assisted cultural heritage dissemination: Comparing NMT and glossary-augmented LLM translation in rock art documents

Vicent Briva-Iglesias, María Ferre Fernández


Abstract
Cultural heritage institutions increasingly disseminate research and interpretive materials globally, but multilingual dissemination is constrained by limited budgets and staffing. In terminology-dense domains such as rock art, translation quality depends on accurate, consistent specialised terms, and small lexical errors can mislead non-specialists and reduce reuse. We compare three English MT setups for a Spanish academic rock art text: (1) DeepL as a strong NMT baseline, (2) Gemini-Simple (LLM with a basic prompt), and (3) Gemini-RAG (the same LLM with glossary-augmented prompting via lightweight retrieval of term pairs). Using PEARMUT, we conduct a human evaluation via (i) multi-way Direct Assessment (0–100) on 91 segments (1,743 Spanish words) and (ii) targeted terminology auditing with a restricted MQM taxonomy. Gemini-RAG yields the highest exact-match terminology accuracy (81.4%), versus Gemini-Simple (69.1%) and DeepL (64.4%), while preserving overall quality (mean DA 85.3 Gemini-RAG vs. 85.2 Gemini-Simple) and outperforming DeepL (80.3). These results show that glossary-augmented prompting is a low-overhead way to improve terminology control in cultural-heritage translation, provided that institutions maintain minimal terminology resources and lightweight evaluation procedures.
Anthology ID:
2026.eamt-1.49
Volume:
Proceedings of the 26th Annual Conference of the European Association for Machine Translation (Volume 1)
Month:
June
Year:
2026
Address:
Tilburg, The Netherlands
Editors:
Dimitar Shterionov, Eva Vanmassenhove, Mirella De Sisto, Fred Blain, Javad Pourmostafa Roshan Sharami, Lisa Lepp, Chiara Manna, Argentina Anna Rescigno, Alina Karakanta, Ayla Rigouts Terryn, Manuel Lardelli, Natalia Resende, Elena Murgolo, Janiça Hackenbuchner, Anna Zaretskaya, Miquel Esplà-Gomis, Thierry Etchegoyhen, Dagmar Gromann, Rachel Bawden, Barry Haddow, Sara Szoc, Mikel Forcada, Helena Moniz
Venue:
EAMT
SIG:
Publisher:
European Association for Machine Translation
Note:
Pages:
774–786
Language:
URL:
https://aclanthology.org/2026.eamt-1.49/
DOI:
Bibkey:
Cite (ACL):
Vicent Briva-Iglesias and María Ferre Fernández. 2026. AI-assisted cultural heritage dissemination: Comparing NMT and glossary-augmented LLM translation in rock art documents. In Proceedings of the 26th Annual Conference of the European Association for Machine Translation (Volume 1), pages 774–786, Tilburg, The Netherlands. European Association for Machine Translation.
Cite (Informal):
AI-assisted cultural heritage dissemination: Comparing NMT and glossary-augmented LLM translation in rock art documents (Briva-Iglesias & Fernández, EAMT 2026)
Copy Citation:
PDF:
https://aclanthology.org/2026.eamt-1.49.pdf