通过跨语言转移和LoRA适配器合并实现低资源阿拉伯语脚本语言的生物医学机器翻译
Biomedical Machine Translation for Low-Resource Arabic-Script Languages via Cross-Lingual Transfer and LoRA Adapter Merging
浏览论文内容
中文总结 AI 辅助
研究针对阿拉伯语脚本低资源语言生物医学翻译稀缺问题，利用阿拉伯语和波斯语作枢纽，通过LoRA微调训练特定领域适配器，评估少样本学习、最小监督适应及零数据LoRA适配器合并三种策略，展现不同策略效果及跨语言转移局限性。
中文摘要 AI 辅助
我们对医疗领域的跨语言转移进行了系统研究，以解决阿拉伯语脚本语言生物医学神经机器翻译资源稀缺的问题。我们使用阿拉伯语和波斯语作为高资源枢纽，以改善四种严重低资源目标语言的翻译：达里语（阿富汗波斯语，波斯语的一种标准化变体）、普什图语、索拉尼库尔德语（库尔德语的主要标准化变体）和乌尔都语（与印地语密切相关）。我们在仅含解码器的小型语言模型上使用LoRA微调，训练特定领域的枢纽适配器，并评估三种转移策略：少样本上下文学习、最小监督适应，以及据我们所知在此设置下首次使用的零数据LoRA适配器合并。仅用500个句子进行监督适应，达里语（CHrF++ 41.01）就能达到接近枢纽语言的质量，乌尔都语也有显著提升（28.88），而适配器合并在不增加额外成本的情况下，使达里语与监督适应的差距缩小到3.5 CHrF++以内。普什图语和索拉尼库尔德语在高风险临床部署中仍不足，这暴露了与枢纽语言结构距离过大时跨语言转移的局限性。LoRA适配器合并对密切相关的语言效果惊人，即使没有目标语言的生物医学数据。
英文摘要
We present a systematic study of healthcare-domain cross-lingual transfer to address the scarcity of biomedical NMT resources for Arabic-script languages. We use Arabic and Persian as higher-resource pivots to improve translation for \textbf{four severely low-resource} targets: Dari (Afghan Persian, a standardised variety of Persian), Pashto, Sorani Kurdish (Central Kurdish, a major standardized variety of Kurdish), and Urdu (closely related to Hindi). Using LoRA fine-tuning on small decoder-only LLMs, we train \textit{domain-specific pivot adapters} and evaluate \textbf{three transfer strategies}: few-shot in-context learning, minimal supervised adaptation, and, to the best of our knowledge, for the first time in this setting, zero-data LoRA adapter merging. Supervised adaptation with just 500 sentences achieves near pivot-language quality for Dari (CHrF++ 41.01) and meaningful gains for Urdu (28.88), while adapter merging reaches within 3.5 CHrF++ of supervised adaptation for Dari at zero additional cost. Pashto and Sorani Kurdish remain insufficient for high-stakes clinical deployment exposing the limits of cross-lingual transfer when structural distance from the pivots is too great. LoRA adapter merging works surprisingly well for closely related languages, even without target-language biomedical data.
