Abstract
Machine Translation of Culture-Specific Items (CSIs) poses significant challenges. Recent work on CSI translation has shown some success using Large Language Models (LLMs) to adapt to different languages and cultures; however, a deeper analysis is needed to examine the benefits and pitfalls of each method. In this paper, we introduce the ChineseMenuCSI dataset, the largest for Chinese-English menu corpora, annotated with CSI vs Non-CSI labels and a fine-grained test set. We define three levels of CSI figurativeness for a more nuanced analysis and develop a novel methodology for automatic CSI identification, which outperforms GPT-based prompts in most categories. Importantly, we are the first to integrate human translation theories into LLM-driven translation processes, significantly improving translation accuracy, with COMET scores increasing by up to 7 points. The code and dataset are available at https://github.com/Henry8772/ChineseMenuCSI.- Anthology ID:
- 2024.wmt-1.120
- Volume:
- Proceedings of the Ninth Conference on Machine Translation
- Month:
- November
- Year:
- 2024
- Address:
- Miami, Florida, USA
- Editors:
- Barry Haddow, Tom Kocmi, Philipp Koehn, Christof Monz
- Venue:
- WMT
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1258–1271
- Language:
- URL:
- https://aclanthology.org/2024.wmt-1.120
- DOI:
- 10.18653/v1/2024.wmt-1.120
- Cite (ACL):
- Zhonghe Zhang, Xiaoyu He, Vivek Iyer, and Alexandra Birch. 2024. Cultural Adaptation of Menus: A Fine-Grained Approach. In Proceedings of the Ninth Conference on Machine Translation, pages 1258–1271, Miami, Florida, USA. Association for Computational Linguistics.
- Cite (Informal):
- Cultural Adaptation of Menus: A Fine-Grained Approach (Zhang et al., WMT 2024)
- PDF:
- https://preview.aclanthology.org/dois-2013-emnlp/2024.wmt-1.120.pdf