Wu-Dao Yang

Semi-Supervised Marginal Likelihood Training with Curriculum-Guided Rewriting for Low-Resource Machine Translation

Large language models continue to face challenges in translating low-resource languages with scarce parallel data. This study investigates how to fine-tune them effectively using target-side monolingual data. Existing approaches—dominated by back-translation and recent LLM-based rewriting—remain limited by noisy synthe...