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

• URL: http://arxiv.org/abs/2601.06307v1
• Date: Fri, 09 Jan 2026 20:55:09 GMT
• Title: A Rising Tide Lifts All Boats: MTQE Rewards for Idioms Improve General Translation Quality
• Authors: Ishika Agarwal, Zhenlin He, Dhruva Patil, Dilek Hakkani-Tür,
• Abstract summary: Non-compositional expressions (e.g., idioms, proverbs, and metaphors) pose significant challenges for neural machine translation systems.<n>We investigate GRPO-style fine-tuning using Machine Translation Quality Estimation (MTQE) models as reward functions to train models to better translate idioms.<n>Using Chinese and Hindi 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 language) improves by 6 points.
• Score: 13.512688251831902
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: 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.

Related papers

• Evaluating LLMs on Chinese Idiom Translation [12.580058582681968]
  Despite recent progress in machine translation, little is known about Chinese idiom translation.<n>We introduceEval, a framework with a comprehensive error taxonomy for Chinese idiom translation.
  arXiv  Detail & Related papers  (2025-08-14T07:52:56Z)
• Graph-Assisted Culturally Adaptable Idiomatic Translation for Indic Languages [3.2498796510544636]
  Translating multi-word expressions (MWEs) and idioms requires a deep understanding of both the source and target languages.<n>Traditional static knowledge graphs (KGs) and prompt-based approaches struggle to capture these complex relationships.<n>We propose an adaptive graph neural network (GNN) based methodology that learns intricate mappings between idiomatic expressions.
  arXiv  Detail & Related papers  (2025-05-28T03:42:16Z)
• DeepTrans: Deep Reasoning Translation via Reinforcement Learning [65.96268429761842]
  We introduce DeepTrans, a deep reasoning translation model that learns free translation via reinforcement learning (RL)<n>Using Qwen2.5-7B as the backbone, DeepTrans improves performance by 16.3% in literature translation.<n>We summarize the failures and interesting findings during our RL exploration.
  arXiv  Detail & Related papers  (2025-04-14T12:40:39Z)
• Lost in Literalism: How Supervised Training Shapes Translationese in LLMs [51.04435855143767]
  Large language models (LLMs) have achieved remarkable success in machine translation.<n>However, translationese, characterized by overly literal and unnatural translations, remains a persistent challenge.<n>We introduce methods to mitigate these biases, including polishing golden references and filtering unnatural training instances.
  arXiv  Detail & Related papers  (2025-03-06T12:14:45Z)
• That was the last straw, we need more: Are Translation Systems Sensitive to Disambiguating Context? [64.38544995251642]
  We study semantic ambiguities that exist in the source (English in this work) itself. We focus on idioms that are open to both literal and figurative interpretations. We find that current MT models consistently translate English idioms literally, even when the context suggests a figurative interpretation.
  arXiv  Detail & Related papers  (2023-10-23T06:38:49Z)
• Crossing the Threshold: Idiomatic Machine Translation through Retrieval Augmentation and Loss Weighting [66.02718577386426]
  We provide a simple characterization of idiomatic translation and related issues. We conduct a synthetic experiment revealing a tipping point at which transformer-based machine translation models correctly default to idiomatic translations. To improve translation of natural idioms, we introduce two straightforward yet effective techniques.
  arXiv  Detail & Related papers  (2023-10-10T23:47:25Z)
• Do GPTs Produce Less Literal Translations? [20.095646048167612]
  Large Language Models (LLMs) have emerged as general-purpose language models capable of addressing many natural language generation or understanding tasks. We find that translations out of English (E-X) from GPTs tend to be less literal, while exhibiting similar or better scores on Machine Translation quality metrics.
  arXiv  Detail & Related papers  (2023-05-26T10:38:31Z)
• The Best of Both Worlds: Combining Human and Machine Translations for Multilingual Semantic Parsing with Active Learning [50.320178219081484]
  We propose an active learning approach that exploits the strengths of both human and machine translations. An ideal utterance selection can significantly reduce the error and bias in the translated data.
  arXiv  Detail & Related papers  (2023-05-22T05:57:47Z)
• Can Transformer be Too Compositional? Analysing Idiom Processing in Neural Machine Translation [55.52888815590317]
  Unlike literal expressions, idioms' meanings do not directly follow from their parts. NMT models are often unable to translate idioms accurately and over-generate compositional, literal translations. We investigate whether the non-compositionality of idioms is reflected in the mechanics of the dominant NMT model, Transformer.
  arXiv  Detail & Related papers  (2022-05-30T17:59:32Z)
• PETCI: A Parallel English Translation Dataset of Chinese Idioms [0.0]
  Current machine translation models perform poorly idiom translation, while idioms are sparse in many translation datasets. We present a parallel English translation dataset of Chinese idioms, aiming to improve translation by both human and machine.
  arXiv  Detail & Related papers  (2022-02-19T03:16:20Z)
• BitextEdit: Automatic Bitext Editing for Improved Low-Resource Machine Translation [53.55009917938002]
  We propose to refine the mined bitexts via automatic editing. Experiments demonstrate that our approach successfully improves the quality of CCMatrix mined bitext for 5 low-resource language-pairs and 10 translation directions by up to 8 BLEU points.
  arXiv  Detail & Related papers  (2021-11-12T16:00:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.