Low-Resource Machine Translation through Retrieval-Augmented LLM Prompting: A Study on the Mambai Language

arXiv:2404.04809v1 Announce Type: new
Abstract: This study explores the use of large language models (LLMs) for translating English into Mambai, a low-resource Austronesian language spoken in Timor-Leste, with approximately 200,000 native speakers. Leveraging a novel corpus derived from a Mambai language manual and additional sentences translated by a native speaker, we examine the efficacy of few-shot LLM prompting for machine translation (MT) in this low-resource context. Our methodology involves the strategic selection of parallel sentences and dictionary entries for prompting, …

abstract arxiv cs.cl english language language models large language large language models llm llms low machine machine translation novel prompting retrieval retrieval-augmented speakers spoken study through translated translation type