Neural Machine Translation for Coptic-French: Strategies for Low-Resource Ancient Languages

Nasma Chaoui, Richard Khoury


Abstract
This paper presents the first systematic study of strategies for translating Coptic into French. Our comprehensive pipeline systematically evaluates: pivot versus direct translation, the impact of pre-training, the benefits of multi-version fine-tuning, and model robustness to noise. Utilizing aligned biblical corpora, we demonstrate that fine-tuning with a stylistically-varied and noise-aware training corpus significantly enhances translation quality. Our findings provide crucial practical insights for developing translation tools for historical languages in general.
Anthology ID:
2026.lt4hala-1.50
Volume:
Proceedings of the Fourth Workshop on Language Technologies for Historical and Ancient Languages (LT4HALA 2026) @ LREC 2026
Month:
May
Year:
2026
Address:
Palma, Mallorca (Spain)
Editors:
Rachele Sprugnoli, Marco Passarotti
Venues:
LT4HALA | WS
SIG:
Publisher:
ELRA Language Resources Association (ELRA)
Note:
Pages:
482–490
Language:
External URL:
https://lrec.elra.info/lrec2026-ws-lt4hala-50
DOI:
10.63317/5asa4khfm6hq
Bibkey:
Cite (ACL):
Nasma Chaoui and Richard Khoury. 2026. Neural Machine Translation for Coptic-French: Strategies for Low-Resource Ancient Languages. In Proceedings of the Fourth Workshop on Language Technologies for Historical and Ancient Languages (LT4HALA 2026) @ LREC 2026, pages 482–490, Palma, Mallorca (Spain). ELRA Language Resources Association (ELRA).
Cite (Informal):
Neural Machine Translation for Coptic-French: Strategies for Low-Resource Ancient Languages (Chaoui & Khoury, LT4HALA 2026)
Copy Citation: