Proverbs Run in Pairs: Evaluating Proverb Translation Capability of Large Language Model
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912197158895616 |
|---|---|
| author | Wang, Minghan Pham, Viet-Thanh Moghimifar, Farhad Vu, Thuy-Trang |
| author_facet | Wang, Minghan Pham, Viet-Thanh Moghimifar, Farhad Vu, Thuy-Trang |
| contents | Despite achieving remarkable performance, machine translation (MT) research remains underexplored in terms of translating cultural elements in languages, such as idioms, proverbs, and colloquial expressions. This paper investigates the capability of state-of-the-art neural machine translation (NMT) and large language models (LLMs) in translating proverbs, which are deeply rooted in cultural contexts. We construct a translation dataset of standalone proverbs and proverbs in conversation for four language pairs. Our experiments show that the studied models can achieve good translation between languages with similar cultural backgrounds, and LLMs generally outperform NMT models in proverb translation. Furthermore, we find that current automatic evaluation metrics such as BLEU, CHRF++ and COMET are inadequate for reliably assessing the quality of proverb translation, highlighting the need for more culturally aware evaluation metrics. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_11953 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Proverbs Run in Pairs: Evaluating Proverb Translation Capability of Large Language Model Wang, Minghan Pham, Viet-Thanh Moghimifar, Farhad Vu, Thuy-Trang Computation and Language Despite achieving remarkable performance, machine translation (MT) research remains underexplored in terms of translating cultural elements in languages, such as idioms, proverbs, and colloquial expressions. This paper investigates the capability of state-of-the-art neural machine translation (NMT) and large language models (LLMs) in translating proverbs, which are deeply rooted in cultural contexts. We construct a translation dataset of standalone proverbs and proverbs in conversation for four language pairs. Our experiments show that the studied models can achieve good translation between languages with similar cultural backgrounds, and LLMs generally outperform NMT models in proverb translation. Furthermore, we find that current automatic evaluation metrics such as BLEU, CHRF++ and COMET are inadequate for reliably assessing the quality of proverb translation, highlighting the need for more culturally aware evaluation metrics. |
| title | Proverbs Run in Pairs: Evaluating Proverb Translation Capability of Large Language Model |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2501.11953 |