Zero-shot translation, directly translating between language pairs unseen in training, is a promising capability of multilingual neural machine translation (NMT). However, it usually suffers from capturing spurious correlations between the output language and language invariant semantics due to the maximum likelihood training objective, leading to poor transfer performance on zero-shot translation. In this paper, we introduce a denoising autoencoder objective based on pivot language into traditional training objective to improve the translation accuracy on zero-shot directions. The theoretical analysis from the perspective of latent variables shows that our approach actually implicitly maximizes the probability distributions for zero-shot directions. On two benchmark machine translation datasets, we demonstrate that the proposed method is able to effectively eliminate the spurious correlations and significantly outperforms state-of-the-art methods with a remarkable performance. Our code is available at https://github.com/Victorwz/zs-nmt-dae.
翻译:培训中看不见的语言对口之间直接翻译零光翻译,是多语种神经机翻译(NMT)的一个很有希望的能力。然而,由于培训目标极有可能,通常会捕捉产出语言和语言变异语语义之间的虚假关联,导致零光翻译的转换性能差。在本文中,我们引入了基于节点语言的取消自动编码器目标,将其引入传统培训目标,以提高零光方向的翻译准确性。从潜在变量的角度进行的理论分析表明,我们的方法实际上隐含着将零光方向的概率分布最大化。在两个基准机器翻译数据集中,我们证明拟议的方法能够有效地消除虚假的关联性,并显著地超越了最先进的方法。我们的代码可以在 https://github.com/Victorwz/zs-nmt-dae上查阅。