北京大学学报（自然科学版）2026，Vol.62Issue(5)：950-962,中插1-中插2,15.DOI:10.13209/j.0479-8023.2026.009
基于检索增强的两阶段跨文化机器翻译方法
A Retrieval-Augmented Two-Stage Approach for Cross-Cultural Machine Translation
摘要
Abstract
Traditional machine translation systems mainly focus on linguistic and semantic consistency but struggle to handle the ambiguity and context sensitivity inherent in cultural content.To address this,we propose a retrieval-augmented two-stage translation framework R2-MT to improve the accuracy and cultural relevance of translating culture-specific items.In the first stage,knowledge base retrieval is performed based on label similarity and description semantics to disambiguate culture-specific items and generate culturally adapted translations.In the second stage,generated translations as hard constraints are injected into the translation prompt to ensure semantic precision and cultural conformity.To support this process,we constructed a multilingual culture-specific item knowledge base covering 15 language variants and approximately 1.9 million entities,providing a foundation for entity retrieval and disambiguation.Additionally,we designed an instruction fine-tuning dataset covering 10 languages and containing 160000 samples,and jointly trained a large language model on two tasks:entity translation generation and constrained name translation,thereby enhancing the model's ability to translate culture-specific items.Experimental results demonstrate that R2-MT significantly outperforms strong baselines on multiple cross-cultural translation benchmarks in terms of BLEU,COMET,and cultural relevance metrics.Ablation studies and human evaluations further confirm the effectiveness and complementary advantages of the two-stage mechanism in improving the translation accuracy of culture-specific items and maintaining overall translation quality.关键词
大语言模型/跨文化机器翻译/文化专有项(CSIs)Key words
large language models/cross-cultural machine translation/culture-specific items(CSIs)引用本文复制引用
王英奇,杨雅婷,董瑞,马博,吐尔洪·吾司曼,鲁凯文,王磊,周喜..基于检索增强的两阶段跨文化机器翻译方法[J].北京大学学报（自然科学版）,2026,62(5):950-962,中插1-中插2,15.基金项目
新疆维吾尔自治区"天山英才"培养计划(2022TSYCCX0059,2023TSYCCX0041,2023TSYCCX0044)、新疆维吾尔自治区自然科学基金重点基金(2022D01D04,2022D01D81)、新疆维吾尔自治区上海合作组织科技伙伴计划及国际科技合作计划(2023E01019)、新疆维吾尔自治区重点研发任务专项(2023B03024,2024B03026)和中国科学院青年创新促进会优秀会员项目(Y2021112,Y2023118,2021436)资助 （2022TSYCCX0059,2023TSYCCX0041,2023TSYCCX0044）
