paper-with-me

홈 › Papers

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

2026-01-09 · Ishika Agarwal, Zhenlin He, Dhruva Patil, Dilek Hakkani-Tür arxiv

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.

📄 PDF Abstract BibTeX arXiv:2601.06307

Code (0)

등록된 구현이 없습니다.

Tasks

Machine Translation

Similar Papers 제목 키워드 기반

When More Parameters Hurt: Foundation Model Priors Amplify Worst-Client Disparity Under Extreme Federated Heterogeneity

2026-05-09 · Kiran Naseer, Umar Shoaib arxiv

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 Learning

MTQE.en-he: Machine Translation Quality Estimation for English-Hebrew

2026-02-06 · Andy Rosenbaum, Assaf Siani, Ilan Kernerman arxiv

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 Translation

Approximate Supervised Object Distance Estimation on Unmanned Surface Vehicles

2025-01-09 · Benjamin Kiefer, Yitong Quan, Andreas Zell

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 Detection

Does a Rising Tide Lift All Boats? Bias Mitigation for AI-based CMR Segmentation

2025-03-21 · Tiarna Lee, Esther Puyol-Antón, Bram Ruijsink, Miaojing Shi 외

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 Segmentation

Stable Yaw Estimation of Boats from the Viewpoint of UAVs and USVs

2023-06-24 · Benjamin Kiefer, Timon Höfer, Andreas Zell

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