并非双关：基于对比学习与音义嵌入的多智能体文字游戏翻译

中文摘要 AI 辅助

跨语言文字游戏翻译长期以来一直困扰着专业翻译人员和机器翻译系统。我们结合大型语言模型与文字游戏生成的语言约束，研究了三种将英语双关语翻译成法语的方法。我们的基线方法是使用大型语言模型，并通过提示包含法语正例和反例的判别器提供反馈；我们的引导推理流水线使用结合音义嵌入来检索用于生成文字游戏的词汇候选；最后，我们的多智能体框架利用专门的反馈迭代评估并重新生成候选翻译。我们的目标超越了字面翻译，在于保留源语文本文字游戏的语言创造性、歧义性和幽默感，而非简单复制其词汇。在CLEF JOKER 2025任务2竞赛的专家人工评估中，多智能体系统和引导式思维链系统分别排名第一和第二，尽管BLEU和BERTScore仅取得适度提升。这些发现表明，明确的音义指导和迭代多智能体评估均可改善基于大型语言模型的文字游戏翻译，相较于直接的判别器引导生成，尤其在平衡语义保真度、语音相似性和自然目标语言表达方面表现突出。

英文摘要

Translating wordplay across languages has long challenged both professional translators and machine translation systems. We investigate three approaches to translating puns from English to French by combining large language models with linguistic constraints for wordplay generation. Our baseline uses a large language model with feedback from a discriminator prompted with positive and negative French examples. Our guided reasoning pipeline uses combined phonetic-semantic embeddings to retrieve lexical candidates for wordplay generation. Finally, our multi-agent framework iteratively evaluates and regenerates candidate translations using specialized feedback. Moving beyond literal translation, our objective is to preserve the linguistic creativity, ambiguity, and humor of the source-text wordplay rather than simply reproduce its vocabulary. The multi-agent and guided chain-of-thought systems ranked first and second, respectively, in the CLEF JOKER 2025 Task 2 competition under expert human evaluation, despite only modest improvements in BLEU and BERTScore. These findings suggest that both explicit phonetic-semantic guidance and iterative multi-agent evaluation can improve LLM-based wordplay translation relative to direct discriminator-guided generation, particularly when balancing semantic fidelity, phonetic similarity, and natural target-language expression

发表机构

• Georgia Institute of Technology（佐治亚理工学院）

机构由 AI 辅助整理，请以论文原文为准。