POMP: Probability-driven Meta-graph Prompter for LLMs in Low-resource Unsupervised Neural Machine Translation

Anonymous

Abstract: Low-resource languages (LRLs) face challenges in supervised neural machine translation (NMT) due to limited parallel data, prompting research in unsupervised NMT.Unsupervised NMT (UNMT), without requiring ground truth, provides solutions for LRL translations using synthetic pseudo-parallel data and parallel data from auxiliary language pairs. However, they usually encounter linguistic noises, such as errors in synthetic data and biases in auxiliary language pairs.We argue that large language models (LLMs) mitigate UNMT's linguistic noises by dynamically organizing auxiliary languages in prompts to improve LRL translations. In this paper, we propose PrObability-driven Meta-graph Prompter (POMP), an approach employing a dynamic graph to organize multiple auxiliary languages, to prompt LLMs in LRL translations. POMP proposes a language-specific meta-graph that dynamically samples multiple translation paths to organize auxiliary languages in constructing prompts. Following the path, POMP prompts LLMs with a mixture of auxiliary languages to translate. We achieve the meta-graph's evolution by back-propagating evaluation scores to update probabilities on the graph.Our experimental improvements show POMP's effectiveness on LRLs' translation.

Paper Type: long

Research Area: Machine Translation

Contribution Types: Approaches to low-resource settings

Languages Studied: English, Gujarati, Kazakh, Nepail, Sinhala, German, Spanish, Finish, Hindi, Russian, Chinese