用多智能体和语音语义嵌入提升双关语翻译的创意与幽默感
Pun Intended: Multi-Agent Translation of Wordplay with Contrastive Learning and Phonetic-Semantic Embeddings
- 通过语音语义嵌入检索候选词，引导双关语生成
- 多智能体框架在人类评估中夺冠，优于单纯模型反馈
- 适合研究自然语言幽默、跨文化翻译的学者与开发者
跨语言双关语翻译长期困扰专业译者与机器翻译系统。本文探索三种将英语双关语译为法语的方法：基线方法使用大语言模型并结合判别器反馈；引导推理流程利用语音-语义嵌入检索词汇候选；多智能体框架则通过专用反馈迭代评估与重生成候选译文。目标不是字面翻译，而是保留源文本的创意性、歧义性和幽默感。在 CLEF JOKER 2025 Task 2 竞赛中，多智能体系统和引导链式思维系统分别在专家人类评估中位列第一和第二，尽管 BLEU 与 BERTScore 提升有限。结果表明，显式语音-语义引导与多智能体迭代评估能有效提升基于大语言模型的双关语翻译表现，尤其在语义保真度、语音相似性和目标语言自然度之间取得更好平衡。
原文摘要 · Abstract (English)
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
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。