LLM-Assisted Rule Based Machine Translation for Low/No-Resource Languages

TL;DR

This paper introduces LLM-RBMT, a novel machine translation paradigm that leverages large language models to enable translation for no-resource languages, demonstrated through a case study on Owens Valley Paiute.

Contribution

It presents the first LLM-assisted rule-based translation system tailored for critically endangered languages with no available data.

Findings

Successful development of an OVP-English translation system

Detailed evaluation of translation components and their effectiveness

Discussion of limitations and future research directions

Abstract

We propose a new paradigm for machine translation that is particularly useful for no-resource languages (those without any publicly available bilingual or monolingual corpora): LLM-RBMT (LLM-Assisted Rule Based Machine Translation). Using the LLM-RBMT paradigm, we design the first language education/revitalization-oriented machine translator for Owens Valley Paiute (OVP), a critically endangered Indigenous American language for which there is virtually no publicly available data. We present a detailed evaluation of the translator's components: a rule-based sentence builder, an OVP to English translator, and an English to OVP translator. We also discuss the potential of the paradigm, its limitations, and the many avenues for future research that it opens up.