Psychology-Driven Enhancement of Humour Translation

TL;DR

This paper introduces a psychology-inspired mechanism for improving humour translation in large language models, significantly enhancing humor, fluency, and coherence in translated texts by mimicking human thought processes.

Contribution

It proposes a novel Humour Decomposition Mechanism (HDM) utilizing Chain-of-Thought and humour theory to better translate humor across languages, addressing linguistic interference issues.

Findings

7.75% improvement in humour quality

2.81% increase in fluency

6.13% enhancement in coherence

Abstract

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.