Transcending Language Boundaries: Harnessing LLMs for Low-Resource Language Translation
It addresses the challenge of linguistic barriers for minority communities by improving translation into low-resource languages, though it appears incremental as it builds on existing retrieval techniques.
This paper tackles the problem of low-resource language translation by introducing a retrieval-based method that improves translation quality for languages like Cherokee, Tibetan, and Manchu, showing promise in enhancing word-level accuracy and semantic understanding compared to zero-shot LLMs like GPT-4o and LLaMA 3.1 405B.
Large Language Models (LLMs) have demonstrated remarkable success across a wide range of tasks and domains. However, their performance in low-resource language translation, particularly when translating into these languages, remains underexplored. This gap poses significant challenges, as linguistic barriers hinder the cultural preservation and development of minority communities. To address this issue, this paper introduces a novel retrieval-based method that enhances translation quality for low-resource languages by focusing on key terms, which involves translating keywords and retrieving corresponding examples from existing data. To evaluate the effectiveness of this method, we conducted experiments translating from English into three low-resource languages: Cherokee, a critically endangered indigenous language of North America; Tibetan, a historically and culturally significant language in Asia; and Manchu, a language with few remaining speakers. Our comparison with the zero-shot performance of GPT-4o and LLaMA 3.1 405B, highlights the significant challenges these models face when translating into low-resource languages. In contrast, our retrieval-based method shows promise in improving both word-level accuracy and overall semantic understanding by leveraging existing resources more effectively.