A Rising Tide Lifts All Boats: MTQE Rewards for Idioms Improve General Translation Quality
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Machine TranslationSimilar Papers 제목 키워드 기반
When More Parameters Hurt: Foundation Model Priors Amplify Worst-Client Disparity Under Extreme Federated Heterogeneity
Federated learning (FL) is increasingly used to fine-tune foundation models (FMs) on distributed private data. The community largely assumes that large-scale pretraining serves as a 'rising tide that lifts all boats' in …
Text ClassificationFederated LearningMTQE.en-he: Machine Translation Quality Estimation for English-Hebrew
We release MTQE.en-he: to our knowledge, the first publicly available English-Hebrew benchmark for Machine Translation Quality Estimation. MTQE.en-he contains 959 English segments from WMT24++, each paired with a machine…
Machine TranslationApproximate Supervised Object Distance Estimation on Unmanned Surface Vehicles
Unmanned surface vehicles (USVs) and boats are increasingly important in maritime operations, yet their deployment is limited due to costly sensors and complexity. LiDAR, radar, and depth cameras are either costly, yield…
object-detectionObject DetectionDoes a Rising Tide Lift All Boats? Bias Mitigation for AI-based CMR Segmentation
Artificial intelligence (AI) is increasingly being used for medical imaging tasks. However, there can be biases in the resulting models, particularly when they were trained using imbalanced training datasets. One such ex…
AllImage SegmentationSemantic SegmentationStable Yaw Estimation of Boats from the Viewpoint of UAVs and USVs
Yaw estimation of boats from the viewpoint of unmanned aerial vehicles (UAVs) and unmanned surface vehicles (USVs) or boats is a crucial task in various applications such as 3D scene rendering, trajectory prediction, and…
Trajectory Prediction