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.- Anthology ID:
- 2024.findings-emnlp.544
- Volume:
- Findings of the Association for Computational Linguistics: EMNLP 2024
- Month:
- November
- Year:
- 2024
- Address:
- Miami, Florida, USA
- Editors:
- Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 9285–9305
- Language:
- URL:
- https://preview.aclanthology.org/add_missing_videos/2024.findings-emnlp.544/
- DOI:
- 10.18653/v1/2024.findings-emnlp.544
- Cite (ACL):
- Kenan Tang, Peiyang Song, Yao Qin, and Xifeng Yan. 2024. Creative and Context-Aware Translation of East Asian Idioms with GPT-4. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 9285–9305, Miami, Florida, USA. Association for Computational Linguistics.
- Cite (Informal):
- Creative and Context-Aware Translation of East Asian Idioms with GPT-4 (Tang et al., Findings 2024)
- PDF:
- https://preview.aclanthology.org/add_missing_videos/2024.findings-emnlp.544.pdf