arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2507.09259cs.CL
收藏

幽默翻译的心理学驱动增强

Psychology-Driven Enhancement of Humour Translation

School of Computer Science, University of Auckland, New Zealand(奥克兰大学计算机科学学院);Singapore University of Technology and Design(新加坡科技设计大学);School of Electronic Engineering and Computer Science, Queen Mary University of London(伦敦玛丽女王大学电子工程与计算机科学学院)

Yuchen Su, Yonghua Zhu, Yang Chen, Diana Benavides-Prado, Michael Witbrock

AI总结:

针对大型语言模型在幽默翻译中存在的语言干扰和幽默感缺失问题,提出受心理学启发的幽默分解机制(HDM),结合思维链与幽默理论优化译文,在开源数据集上显著提升了翻译的幽默度、流畅性和连贯性。

摘要:

幽默翻译作为不同文化之间的桥梁,在促进理解与沟通方面发挥着重要作用。尽管大多数现有的大型语言模型(LLMs)能够胜任一般翻译任务,但这些模型在幽默翻译上仍面临困难,这尤其体现在语言干扰以及译文中缺乏幽默感。在本文中,我们提出了一种受心理学启发的幽默分解机制(HDM),该机制利用思维链(CoT)来模仿人类思维过程的能力,激发LLMs优化翻译幽默文本的可读性。此外,我们在HDM中整合了幽默理论,以进一步增强译文中的幽默元素。我们在开源幽默数据集上进行的自动评估实验表明,我们的方法显著提升了幽默翻译的质量,在生成文本的幽默度、流畅性和连贯性方面分别取得了7.75%、2.81%和6.13%的平均提升。

英文摘要:

Humour translation plays a vital role as a bridge between different cultures, fostering understanding and communication. Although most existing Large Language Models (LLMs) are capable of general translation tasks, these models still struggle with humour translation, which is especially reflected through linguistic interference and lacking humour in translated text. In this paper, we propose a psychology-inspired Humour Decomposition Mechanism (HDM) that utilises Chain-of-Thought (CoT) to imitate the ability of the human thought process, stimulating LLMs to optimise the readability of translated humorous texts. Moreover, we integrate humour theory in HDM to further enhance the humorous elements in the translated text. Our automatic evaluation experiments on open-source humour datasets demonstrate that our method significantly improves the quality of humour translation, yielding average gains of 7.75\% in humour, 2.81\% in fluency, and 6.13\% in coherence of the generated text.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑