用强化学习提升术语翻译准确率，兼顾通用翻译质量
TAT-R1: Terminology-Aware Translation with Reinforcement Learning and Word Alignment
- 通过词对齐提取关键词翻译对，构建规则奖励机制
- 术语翻译准确率显著优于基线模型，通用翻译性能相当
- 验证了大模型训练范式在机器翻译中的有效性
近年来，如 DeepSeek-R1 的深度推理大语言模型在数学和编程任务上取得显著进展。受此启发，一些研究采用强化学习（RL）提升模型的深度推理能力并改进机器翻译（MT）质量。然而，术语翻译这一关键任务在深度推理大模型中尚未被探索。本文提出 TAT-R1，一种基于强化学习与词对齐的术语感知翻译模型。首先，利用词对齐模型提取关键词翻译对；随后，基于提取的对齐关系设计三种规则化对齐奖励。这些奖励使 RL 训练的翻译模型能聚焦于源文本中关键信息的准确翻译，包括术语。实验结果表明，TAT-R1 在术语翻译准确率上显著优于基线模型，同时在通用翻译任务上保持相当性能。此外，我们还对 DeepSeek-R1 类训练范式在机器翻译中的应用进行了详细消融研究，揭示多个关键发现。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。