论文标题
$ m^4apapter $：与元适配器的多种语言多域改编
$m^4Adapter$: Multilingual Multi-Domain Adaptation for Machine Translation with a Meta-Adapter
论文作者
论文摘要
在训练时看到的数据和语言对的数据评估时，多语言神经机器翻译模型（MNMT）会产生最先进的性能。但是，当使用MNMT模型在域移动或新语言对下转换时，性能会急剧下降。我们认为一个非常具有挑战性的场景：将MNMT模型改编为新的域和新语言对。在本文中，我们提出了$ m^4apapter $（用于机器翻译的多语言多域改编版与元适配器），该元使用使用元学习与适配器结合了域和语言知识。我们提出的结果表明，我们的方法是一种参数有效的解决方案，可以有效地调整模型对新语言对和新域，同时超过其他适配器方法。一项消融研究还表明，我们的方法更有效地跨不同的语言和语言信息传输域知识。
Multilingual neural machine translation models (MNMT) yield state-of-the-art performance when evaluated on data from a domain and language pair seen at training time. However, when a MNMT model is used to translate under domain shift or to a new language pair, performance drops dramatically. We consider a very challenging scenario: adapting the MNMT model both to a new domain and to a new language pair at the same time. In this paper, we propose $m^4Adapter$ (Multilingual Multi-Domain Adaptation for Machine Translation with a Meta-Adapter), which combines domain and language knowledge using meta-learning with adapters. We present results showing that our approach is a parameter-efficient solution which effectively adapts a model to both a new language pair and a new domain, while outperforming other adapter methods. An ablation study also shows that our approach more effectively transfers domain knowledge across different languages and language information across different domains.
