Despite the tremendous success of Neural Machine Translation (NMT), its performance on low-resource language pairs still remains subpar, partly due to the limited ability to handle previously unseen inputs, i.e., generalization. In this paper, we propose a method called Joint Dropout, that addresses the challenge of low-resource neural machine translation by substituting phrases with variables, resulting in significant enhancement of compositionality, which is a key aspect of generalization. We observe a substantial improvement in translation quality for language pairs with minimal resources, as seen in BLEU and Direct Assessment scores. Furthermore, we conduct an error analysis, and find Joint Dropout to also enhance generalizability of low-resource NMT in terms of robustness and adaptability across different domains

翻译：尽管神经机器翻译取得了巨大成功，但其在低资源语言对上的性能仍然欠佳，部分原因在于处理未见输入（即泛化）的能力有限。本文提出了一种名为"联合丢失"的方法，通过用变量替换短语来应对低资源神经机器翻译的挑战，从而显著增强组合性——这是泛化的关键方面。从BLEU和直接评估分数来看，我们观察到资源极少的语言对在翻译质量上有了显著提升。此外，我们进行了错误分析，发现联合丢失还能在鲁棒性和跨领域适应性方面增强低资源神经机器翻译的泛化能力。