Enregistré dans:
Détails bibliographiques
Auteurs principaux: Zhang, Zhonghe, He, Xiaoyu, Iyer, Vivek, Birch, Alexandra
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:https://arxiv.org/abs/2408.13534
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866917757732257792
author Zhang, Zhonghe
He, Xiaoyu
Iyer, Vivek
Birch, Alexandra
author_facet Zhang, Zhonghe
He, Xiaoyu
Iyer, Vivek
Birch, Alexandra
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2408_13534
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Cultural Adaptation of Menus: A Fine-Grained Approach
Zhang, Zhonghe
He, Xiaoyu
Iyer, Vivek
Birch, Alexandra
Computation and Language
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.
title Cultural Adaptation of Menus: A Fine-Grained Approach
topic Computation and Language
url https://arxiv.org/abs/2408.13534