POMP：面向低资源无监督神经机器翻译中大语言模型的概率驱动元图提示器
POMP: Probability-driven Meta-graph Prompter for LLMs in Low-resource Unsupervised Neural Machine Translation
AI总结：
本文提出POMP方法，通过构建多辅助语言的有向无环元图并动态采样路径来提示大语言模型，以概率驱动方式缓解语言噪声，从而提升低资源语言的无监督神经机器翻译质量。
摘要：
低资源语言（LRLs）由于平行数据有限，在有监督神经机器翻译中面临挑战，这促使人们研究无监督方法。无监督神经机器翻译（UNMT）方法，包括回译、迁移学习和基于枢轴的翻译，为低资源语言翻译提供了实用的解决方案，但它们受到合成数据噪声、语言偏差和错误传播等问题的阻碍，而这些问题有可能通过大语言模型（LLMs）得到缓解。LLMs 已通过上下文学习（ICL）和有监督微调方法推进了神经机器翻译（NMT），但训练数据不足导致其在低资源语言中表现不佳。我们认为，LLMs 可以利用辅助语言来减轻语言噪声，从而改善低资源语言的翻译。在本文中，我们提出了概率驱动元图提示器（POMP），这是一种新颖的方法，采用基于采样的多辅助语言动态图来增强 LLMs 对低资源语言的翻译能力。POMP 涉及为每种源语言构建一个有向无环元图，我们从中动态采样多条路径来提示 LLMs，以在训练过程中减轻语言噪声并改善翻译。我们使用 BLEURT 指标评估翻译质量，并反向传播由分数估计的奖励，以更新路径中辅助语言的概率。我们的实验表明，三种低资源语言的翻译质量有显著提升，证明了我们方法的有效性。
英文摘要：
Low-resource languages (LRLs) face challenges in supervised neural machine translation due to limited parallel data, prompting research into unsupervised methods. Unsupervised neural machine translation (UNMT) methods, including back-translation, transfer learning, and pivot-based translation, offer practical solutions for LRL translation, but they are hindered by issues like synthetic data noise, language bias, and error propagation, which can potentially be mitigated by Large Language Models (LLMs). LLMs have advanced NMT with in-context learning (ICL) and supervised fine-tuning methods, but insufficient training data results in poor performance in LRLs. We argue that LLMs can mitigate the linguistic noise with auxiliary languages to improve translations in LRLs. In this paper, we propose Probability-driven Meta-graph Prompter (POMP), a novel approach employing a dynamic, sampling-based graph of multiple auxiliary languages to enhance LLMs' translation capabilities for LRLs. POMP involves constructing a directed acyclic meta-graph for each source language, from which we dynamically sample multiple paths to prompt LLMs to mitigate the linguistic noise and improve translations during training. We use the BLEURT metric to evaluate the translations and back-propagate rewards, estimated by scores, to update the probabilities of auxiliary languages in the paths. Our experiments show significant improvements in the translation quality of three LRLs, demonstrating the effectiveness of our approach.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
