Abstract
We incorporate an explicit neural interlingua into a multilingual encoder-decoder neural machine translation (NMT) architecture. We demonstrate that our model learns a true interlingua by performing direct zero-shot translation (without using pivot translation), and by using the interlingual sentence embeddings to train an English Yelp review classifier that, through the mediation of the interlingua, can also classify French and German reviews. Furthermore, we show that, despite using a smaller number of parameters than a pairwise collection of bilingual NMT models, our interlingual approach produces comparable BLEU scores for each language pair in WMT15.
Abstract (translated)
我们将显式神经中间语融合到多语言编码器 - 解码器神经机器翻译(NMT)架构中。我们通过执行直接零镜头翻译(不使用支点翻译),并通过使用语际句子嵌入来训练英语Yelp评论分类器,通过中间语言的调解,我们可以证明我们的模型学习真正的中间语言,也可以对法语进行分类和德国的评论。此外,我们表明,尽管使用较少数量的参数而不是成对的双语NMT模型集合,我们的语际方法在WMT15中为每个语言对产生相当的BLEU分数。
URL
https://arxiv.org/abs/1804.08198