1. Learning-From-Mistakes Prompting for Indigenous Language Translation
- Author
-
Liao, You-Cheng, Yu, Chen-Jui, Lin, Chi-Yi, Yun, He-Feng, Wang, Yen-Hsiang, Li, Hsiao-Min, and Fan, Yao-Chung
- Subjects
Computer Science - Computation and Language - Abstract
Using large language models, this paper presents techniques to improve extremely low-resourced indigenous language translations. Our approaches are grounded in the use of (1) the presence of a datastore consisting of a limited number of parallel translation examples, (2) the inherent capabilities of LLMs like GPT-3.5, and (3) a word-level translation dictionary. We harness the potential of LLMs and in-context learning techniques in such a setting for using LLMs as universal translators for extremely low-resourced languages. Our methodology hinges on utilizing LLMs as language compilers for selected language pairs, hypothesizing that they could internalize syntactic structures to facilitate accurate translation. We introduce three techniques: KNNPrompting with Retrieved Prompting Context, Chain-of-Thought Prompting and Learningfrom-Mistakes Prompting, with the last method addressing past errors. The evaluation results suggest that, even with limited corpora, LLMs can effectively translate extremely low-resource languages when paired with proper prompting.
- Published
- 2024