Read it in Two Steps: Translating Extremely Low-Resource Languages with Code-Augmented Grammar Books
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_ | 1866916773019779072 |
|---|---|
| author | Zhang, Chen Lin, Jiuheng Liu, Xiao Zhang, Zekai Feng, Yansong |
| author_facet | Zhang, Chen Lin, Jiuheng Liu, Xiao Zhang, Zekai Feng, Yansong |
| contents | While large language models (LLMs) have shown promise in translating extremely low-resource languages using resources like dictionaries, the effectiveness of grammar books remains debated. This paper investigates the role of grammar books in translating extremely low-resource languages by decomposing it into two key steps: grammar rule retrieval and application. To facilitate the study, we introduce ZhuangRules, a modularized dataset of grammar rules and their corresponding test sentences. Our analysis reveals that rule retrieval constitutes a primary bottleneck in grammar-based translation. Moreover, although LLMs can apply simple rules for translation when explicitly provided, they encounter difficulties in handling more complex rules. To address these challenges, we propose representing grammar rules as code functions, considering their similarities in structure and the benefit of code in facilitating LLM reasoning. Our experiments show that using code rules significantly boosts both rule retrieval and application, ultimately resulting in a 13.1% BLEU improvement in translation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_01796 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Read it in Two Steps: Translating Extremely Low-Resource Languages with Code-Augmented Grammar Books Zhang, Chen Lin, Jiuheng Liu, Xiao Zhang, Zekai Feng, Yansong Computation and Language While large language models (LLMs) have shown promise in translating extremely low-resource languages using resources like dictionaries, the effectiveness of grammar books remains debated. This paper investigates the role of grammar books in translating extremely low-resource languages by decomposing it into two key steps: grammar rule retrieval and application. To facilitate the study, we introduce ZhuangRules, a modularized dataset of grammar rules and their corresponding test sentences. Our analysis reveals that rule retrieval constitutes a primary bottleneck in grammar-based translation. Moreover, although LLMs can apply simple rules for translation when explicitly provided, they encounter difficulties in handling more complex rules. To address these challenges, we propose representing grammar rules as code functions, considering their similarities in structure and the benefit of code in facilitating LLM reasoning. Our experiments show that using code rules significantly boosts both rule retrieval and application, ultimately resulting in a 13.1% BLEU improvement in translation. |
| title | Read it in Two Steps: Translating Extremely Low-Resource Languages with Code-Augmented Grammar Books |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2506.01796 |