Creative and Context-Aware Translation of East Asian Idioms with GPT-4

ACL ARR 2024 June Submission40 Authors

Abstract: East Asian idioms are a type of figurative language, each condensing its rich cultural background into a few characters. Translating such idioms is challenging for human translators, who often resort to choosing a context-aware translation from an existing list of candidates. However, compiling a dictionary of translations demands much time and creativity even for expert translators. To alleviate such burden, we evaluate if GPT-4 can help generate high-quality translations. Based on automatic evaluations of faithfulness and creativity, we first identify Pareto-optimal prompting strategies that can outperform translation engines from Google and DeepL. Then, at a low cost, our context-aware translations can achieve far more and higher-quality translations per idiom than the human baseline. We open-source our code and data to facilitate further research.

Paper Type: Short

Research Area: Machine Translation

Research Area Keywords: automatic evaluation, few-shot/zero-shot MT, interactive MT

Contribution Types: NLP engineering experiment, Data resources, Data analysis

Languages Studied: English, Chinese, Japanese, Korean

Submission Number: 40