biomedical-machine-translation-for-low-resource-arabic-script-languages-via-cross-lingual-transfer-and-lora-adapter-merging-077a3d15·1 events·first seen Aliases: Biomedical Machine Translation for Low-Resource Arabic-Script Languages via Cross-Lingual Transfer and LoRA Adapter Merging
Researchers present a systematic study of healthcare-domain neural machine translation for four severely low-resource Arabic-script languages (Dari, Pashto, Sorani Kurdish, Urdu) using Arabic and Persian as higher-resource pivots. Three transfer strategies are evaluated: few-shot in-context learning, minimal supervised adaptation, and zero-data LoRA adapter merging — the last being novel in this setting. Supervised adaptation with just 500 sentences achieves near-pivot quality for Dari, while LoRA adapter merging reaches within 3.5 CHrF++ of supervised adaptation at zero additional data cost. Pashto and Sorani Kurdish remain below clinical deployment thresholds, exposing limits of cross-lingual transfer when structural distance is large.