Machine translation focuses mainly on high-resource languages (HRLs), while low-resource languages (LRLs) like Taiwanese Hokkien are relatively under-explored. The study aims to address this gap by developing a dual translation model between Taiwanese Hokkien and both Traditional Mandarin Chinese and English. We employ a pre-trained LLaMA 2-7B model specialized in Traditional Mandarin Chinese to leverage the orthographic similarities between Taiwanese Hokkien Han and Traditional Mandarin Chinese. Our comprehensive experiments involve translation tasks across various writing systems of Taiwanese Hokkien as well as between Taiwanese Hokkien and other HRLs. We find that the use of a limited monolingual corpus still further improves the model's Taiwanese Hokkien capabilities. We then utilize our translation model to standardize all Taiwanese Hokkien writing systems into Hokkien Han, resulting in further performance improvements. Additionally, we introduce an evaluation method incorporating back-translation and GPT-4 to ensure reliable translation quality assessment even for LRLs. The study contributes to narrowing the resource gap for Taiwanese Hokkien and empirically investigates the advantages and limitations of pre-training and fine-tuning based on LLaMA 2.

翻译：機器翻譯主要聚焦於高資源語言（HRLs），而臺灣閩南語等低資源語言（LRLs）相對較少被探討。本研究旨在彌補此缺口，開發臺灣閩南語與繁體中文及英文之間的雙向翻譯模型。我們採用預訓練的LLaMA 2-7B模型（專精於繁體中文）以利用臺灣閩南語漢字與繁體中文之間的字形相似性。全面的實驗涵蓋臺灣閩南語各種書寫系統間的翻譯任務，以及臺灣閩南語與其他高資源語言間的翻譯。我們發現，使用有限單語語料庫仍能進一步提升模型對臺灣閩南語的能力。接著，我們利用翻譯模型將所有臺灣閩南語書寫系統標準化為臺語漢字，從而帶來進一步的性能提升。此外，我們引入一種結合反向翻譯與GPT-4的評估方法，確保即使是低資源語言的翻譯品質評估也具有可靠性。本研究有助於縮小臺灣閩南語的資源差距，並基於LLaMA 2實證探討預訓練與微調的優點與限制。