Laughing Across Languages! A Psychological Theory-driven Humour Translation Approach with Large Language Models

ACL ARR 2024 December Submission1831 Authors

Abstract: Humour translation plays a vital role that can serve as a bridge between different cultures, fostering understanding and communication. However, although most existing Large Language Models (LLMs) are capable of general translation tasks, they still struggle with humour translation, especially for linguistic interference and lacking humour in translated text. In this paper, we propose a 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 experimental evaluation involves both automatic and human evaluation on open-source humour datasets, demonstrating that our method effectively enhances the quality of humour translation, showing an average improvement of 7.75\% in humour, 2.81\% in fluency, and 6.13\% in coherency. Finally, we release a new humour Chinese dataset which has been translated from English using HDM.

Paper Type: Long

Research Area: Linguistic theories, Cognitive Modeling and Psycholinguistics

Research Area Keywords: Linguistic Theories, Cognitive Modeling, and Psycholinguistics, Machine Translation

Contribution Types: NLP engineering experiment, Data resources

Languages Studied: English, Chinese, German, Spanish

Submission Number: 1831