TAT-R1: Terminology-Aware Translation with Reinforcement Learning and Word Alignment

• URL: http://arxiv.org/abs/2505.21172v1
• Date: Tue, 27 May 2025 13:26:02 GMT
• Title: TAT-R1: Terminology-Aware Translation with Reinforcement Learning and Word Alignment
• Authors: Zheng Li, Mao Zheng, Mingyang Song, Wenjie Yang,
• Abstract summary: We propose textbfTAT-R1, a terminology-aware translation model trained with reinforcement learning and word alignment.<n>Our model significantly improves terminology translation accuracy compared to the baseline models.
• Score: 18.162673576513836
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recently, deep reasoning large language models(LLMs) like DeepSeek-R1 have made significant progress in tasks such as mathematics and coding. Inspired by this, several studies have employed reinforcement learning(RL) to enhance models' deep reasoning capabilities and improve machine translation(MT) quality. However, the terminology translation, an essential task in MT, remains unexplored in deep reasoning LLMs. In this paper, we propose \textbf{TAT-R1}, a terminology-aware translation model trained with reinforcement learning and word alignment. Specifically, we first extract the keyword translation pairs using a word alignment model. Then we carefully design three types of rule-based alignment rewards with the extracted alignment relationships. With those alignment rewards, the RL-trained translation model can learn to focus on the accurate translation of key information, including terminology in the source text. Experimental results show the effectiveness of TAT-R1. Our model significantly improves terminology translation accuracy compared to the baseline models while maintaining comparable performance on general translation tasks. In addition, we conduct detailed ablation studies of the DeepSeek-R1-like training paradigm for machine translation and reveal several key findings.

Related papers

• ExTrans: Multilingual Deep Reasoning Translation via Exemplar-Enhanced Reinforcement Learning [77.41383117199227]
  We design a new reward modeling method that compares the translation results of the policy MT model with a strong LRM.<n>Using Qwen2.5-7B-Instruct as the backbone, the trained model achieves the new state-of-the-art performance in literary translation.<n>We extend our method to the multilingual settings with 11 languages.
  arXiv  Detail & Related papers  (2025-05-19T11:34:47Z)
• Deep Reasoning Translation via Reinforcement Learning [77.41383117199227]
  We introduce DeepTrans, a deep reasoning translation model that learns free translation via reinforcement learning.<n>Given the source sentences, the reward model teaches the deep translation model how to think and free-translate them during reinforcement learning.<n> Experimental results show that DeepTrans improves performance by 16.3% in literature translation.
  arXiv  Detail & Related papers  (2025-04-14T12:40:39Z)
• R1-T1: Fully Incentivizing Translation Capability in LLMs via Reasoning Learning [23.721573333602677]
  This paper introduces R1-Translator (R1-T1), a novel framework to achieve inference-time reasoning for general machine translation (MT) via reinforcement learning (RL)<n>Our approach pioneers three innovations: (1) extending reasoning-based translation to broader MT scenarios (e.g., multilingual MT, domain MT) unseen in the training phase; (2) formalizing six expert-curated CoT templates that mirror hybrid human strategies like context-aware paraphrasing and back translation; and (3) enabling self-evolving CoT discovery through RL.
  arXiv  Detail & Related papers  (2025-02-27T03:57:00Z)
• Efficient Technical Term Translation: A Knowledge Distillation Approach for Parenthetical Terminology Translation [0.0]
  This paper addresses the challenge of accurately translating technical terms, which are crucial for clear communication in specialized fields. We introduce the Parenthetical Terminology Translation (PTT) task, designed to mitigate potential inaccuracies by displaying the original term in parentheses alongside its translation. We developed a novel evaluation metric to assess both overall translation accuracy and the correct parenthetical presentation of terms.
  arXiv  Detail & Related papers  (2024-10-01T13:40:28Z)
• Rethinking Human-like Translation Strategy: Integrating Drift-Diffusion Model with Large Language Models for Machine Translation [15.333148705267012]
  We propose Thinker with the Drift-Diffusion Model to emulate human translators' dynamic decision-making under constrained resources. We conduct experiments under the high-resource, low-resource, and commonsense translation settings using the WMT22 and CommonMT datasets. We also perform additional analysis and evaluation on commonsense translation to illustrate the high effectiveness and efficacy of the proposed method.
  arXiv  Detail & Related papers  (2024-02-16T14:00:56Z)
• Learning to Generalize to More: Continuous Semantic Augmentation for Neural Machine Translation [50.54059385277964]
  We present a novel data augmentation paradigm termed Continuous Semantic Augmentation (CsaNMT) CsaNMT augments each training instance with an adjacency region that could cover adequate variants of literal expression under the same meaning.
  arXiv  Detail & Related papers  (2022-04-14T08:16:28Z)
• DEEP: DEnoising Entity Pre-training for Neural Machine Translation [123.6686940355937]
  It has been shown that machine translation models usually generate poor translations for named entities that are infrequent in the training corpus. We propose DEEP, a DEnoising Entity Pre-training method that leverages large amounts of monolingual data and a knowledge base to improve named entity translation accuracy within sentences.
  arXiv  Detail & Related papers  (2021-11-14T17:28:09Z)
• Exploring Unsupervised Pretraining Objectives for Machine Translation [99.5441395624651]
  Unsupervised cross-lingual pretraining has achieved strong results in neural machine translation (NMT) Most approaches adapt masked-language modeling (MLM) to sequence-to-sequence architectures, by masking parts of the input and reconstructing them in the decoder. We compare masking with alternative objectives that produce inputs resembling real (full) sentences, by reordering and replacing words based on their context.
  arXiv  Detail & Related papers  (2021-06-10T10:18:23Z)
• Pre-training Multilingual Neural Machine Translation by Leveraging Alignment Information [72.2412707779571]
  mRASP is an approach to pre-train a universal multilingual neural machine translation model. We carry out experiments on 42 translation directions across a diverse setting, including low, medium, rich resource, and as well as transferring to exotic language pairs.
  arXiv  Detail & Related papers  (2020-10-07T03:57:54Z)
• Learning Source Phrase Representations for Neural Machine Translation [65.94387047871648]
  We propose an attentive phrase representation generation mechanism which is able to generate phrase representations from corresponding token representations. In our experiments, we obtain significant improvements on the WMT 14 English-German and English-French tasks on top of the strong Transformer baseline.
  arXiv  Detail & Related papers  (2020-06-25T13:43:11Z)

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.