水涨船高：成语MTQE奖励机制提升整体翻译质量

A Rising Tide Lifts All Boats: MTQE Rewards for Idioms Improve General Translation Quality

January 9, 2026

作者: Ishika Agarwal, Zhenlin He, Dhruva Patil, Dilek Hakkani-Tür

cs.AI

摘要

非组合式表达（如习语、谚语和隐喻）对神经机器翻译系统构成重大挑战，因为其含义无法仅从单个词汇推导得出。这类表达承载着丰富的文化内涵，兼具比喻义与字面义，导致准确翻译极为困难。鉴于现有模型在组合式文本翻译上表现良好，我们研究采用基于机器翻译质量评估模型的GRPO式微调方法，将其作为奖励函数来训练模型提升习语翻译能力。通过中印习语数据集的实验发现：习语翻译能力提升约14个百分点，普通非习语翻译能力隐性提升约8个百分点，跨语言翻译能力（单语言训练，多语言评估）提升约6个百分点。本研究首次量化了非组合式表达的翻译差距，为开发具有更强跨文化及比喻语言理解能力的大语言模型提供了新思路。

English

Non-compositional expressions (e.g., idioms, proverbs, and metaphors) pose significant challenges for neural machine translation systems because their meanings cannot be derived from individual words alone. These expressions encode rich, cultural meaning, and have both figurative and literal meanings, making accurate translation difficult. Because models are fairly good at translating compositional text, we investigate GRPO-style fine-tuning using Machine Translation Quality Estimation (MTQE) models as reward functions to train models to better translate idioms. Using Chinese and Hindi idiom datasets, we find that idiom translation abilities improve by ~14 points, general, non-idiomatic translation implicitly improves by ~8 points, and cross-lingual translation abilities (trained on one language, evaluated on another) improves by ~6 points. Overall, our work quantifies the non-compositional translation gap and offers insights for developing LLMs with stronger cross-cultural and figurative language understanding.