Creative and Context-Aware Translation of East Asian Idioms with GPT-4
Kenan Tang, Peiyang Song, Yao Qin, Xifeng Yan
Abstract
As a type of figurative language, an East Asian idiom condenses rich cultural background into only 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 candidate 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 high-quality translations per idiom than the human baseline. We open-source all code and data to facilitate further research.
BibTeX
@inproceedings{tang-etal-2024-creative,
title = "Creative and Context-Aware Translation of {E}ast {A}sian Idioms with {GPT}-4",
author = "Tang, Kenan and
Song, Peiyang and
Qin, Yao and
Yan, Xifeng",
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-emnlp.544/",
doi = "10.18653/v1/2024.findings-emnlp.544",
pages = "9285--9305"
}