Linguistically informed ChatGPT prompts to enhance Japanese-Chinese machine translation: A case study on attributive clauses

In the field of Japanese-Chinese translation linguistics, the issue of correctly translating attributive clauses has persistently proven to be challenging. Present-day machine translation tools often fail to accurately translate attributive clauses from Japanese to Chinese. In light of this, this paper investigates the linguistic problem underlying such difficulties, namely how does the semantic role of the modified noun affect the selection of translation patterns for attributive clauses, from a linguistic perspective. Through the analysis of numerous examples, the study develops a novel three-step prompt chaining strategy, which was tested using ChatGPT. The experimental results demonstrate that this approach significantly improves translation quality, with an average score increase of over 43%. These findings highlight the effectiveness and potential of linguistically informed prompt design in enhancing the translation accuracy of complex sentence structures. This study not only offers a new perspective on the integration of linguistics theory and machine translation technologies, but also provides valuable insights for optimizing large language models prompt and improving language education tools.