Abstract
Neural Machine Translation (NMT) systems face significant challenges when working with low-resource languages, particularly in domain adaptation tasks. These difficulties arise due to limited training data and suboptimal model generalization, As a result, selecting an optimal model for translation is crucial for achieving strong performance on in-domain data, particularly in scenarios where fine-tuning is not feasible or practical. In this paper, we investigate strategies for selecting the most suitable NMT model for a given domain using bandit-based algorithms, including Upper Confidence Bound, Linear UCB, Neural Linear Bandit, and Thompson Sampling. Our method effectively addresses the resource constraints by facilitating optimal model selection with high confidence. We evaluate the approach across three African languages and domains, demonstrating its robustness and effectiveness in both scenarios where target data is available and where it is absent.
Abstract (translated)
神经机器翻译（NMT）系统在处理低资源语言时，特别是在领域适应任务中面临重大挑战。这些困难主要是由于训练数据有限以及模型泛化能力不足所导致的。因此，在没有可行或实际微调的情况下，为特定领域选择最佳翻译模型对于实现强大性能至关重要。 在这篇论文中，我们探讨了使用基于多臂赌博机（bandit-based）算法的选择策略来挑选最适合给定领域的NMT模型，这些算法包括上置信界（Upper Confidence Bound）、线性上置信界（Linear UCB）、神经线性赌博机（Neural Linear Bandit）以及汤普森采样（Thompson Sampling）。我们的方法通过在资源有限的情况下有效进行最佳模型选择，从而高效地解决了这一问题。 我们对三种非洲语言和领域进行了评估，并展示了该方法的鲁棒性和有效性，无论是有目标数据还是无目标数据的情况都能取得良好效果。
URL
https://arxiv.org/abs/2505.15069
