并非双关：结合对比学习与音义嵌入的多智能体双关语翻译方法，用于CLEF JOKER 2025任务2
Pun Intended: Multi-Agent Translation of Wordplay with Contrastive Learning and Phonetic-Semantic Embeddings for CLEF JOKER 2025 Task 2
- Georgia Institute of Technology（佐治亚理工学院）
- Peoples' Friendship University of Russia (RUDN University)（俄罗斯人民友谊大学）
- Joint Institute for Nuclear Research（联合核子研究中心）
- Vrije Universiteit Amsterdam（阿姆斯特丹自由大学）
- University of Skövde（斯德哥尔摩大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本研究针对跨语言双关语翻译难题，提出结合对比学习、音义嵌入与多智能体生成器-判别器框架的三阶段方法，在CLEF JOKER 2025任务2竞赛中获第一、第二名，推动了双关语翻译研究。
AI中文摘要：
跨语言双关语翻译面临独特挑战，长期困扰专业人工翻译与机器翻译系统。本研究提出从英语到法语的双关语翻译新方法，结合最先进的大语言模型与双关语生成专用技术，采用三阶段方案：第一阶段，基于新构建的对比学习数据集，结合反馈建立多个前沿大语言模型的基线；第二阶段，实施结合音义嵌入的引导式思维链流程；第三阶段，实施多智能体生成器-判别器框架，通过反馈评估并重新生成双关语。该方法超越字面翻译的局限，核心目标是捕捉源文本双关语的语言创造性与幽默，而非仅复制其词汇。本研究的最优运行结果在CLEF JOKER 2025任务2竞赛中获第一、第二名，由法语母语专家人工评估。本研究通过实施语言学导向的双关语翻译技术，填补翻译研究与计算语言学间的空白，深化对如何利用语言模型处理语义歧义、语音相似性及成功幽默所需的隐性文化与语言意识间复杂互动的理解。
英文摘要：
Translating wordplay across languages presents unique challenges that have long confounded both professional human translators and machine translation systems. This research proposes a novel approach for translating puns from English to French by combining state-of-the-art large language models with specialized techniques for wordplay generation. Our methodology employs a three-stage approach. First, we establish a baseline using multiple frontier large language models with feedback based on a new contrastive learning dataset. Second, we implement a guided chain-of-thought pipeline with combined phonetic-semantic embeddings. Third, we implement a multi-agent generator-discriminator framework for evaluating and regenerating puns with feedback. Moving beyond the limitations of literal translation, our methodology's primary objective is to capture the linguistic creativity and humor of the source text wordplay, rather than simply duplicating its vocabulary. Our best runs earned first and second place in the CLEF JOKER 2025 Task 2 competition where they were evaluated manually by expert native French speakers. This research addresses a gap between translation studies and computational linguistics by implementing linguistically-informed techniques for wordplay translation, advancing our understanding of how language models can be leveraged to handle the complex interplay between semantic ambiguity, phonetic similarity, and the implicit cultural and linguistic awareness needed for successful humor.
