Machine translation systems achieve near human-level performance on some languages, yet their effectiveness strongly relies on the availability of large amounts of bitexts, which hinders their applicability to the majority of language pairs. This work investigates how to learn to translate when having access to only large monolingual corpora in each language. We propose two model variants, a neural and a phrase-based model. Both versions leverage automatic generation of parallel data by backtranslating with a backward model operating in the other direction, and the denoising effect of a language model trained on the target side. These models are significantly better than methods from the literature, while being simpler and having fewer hyper-parameters. On the widely used WMT14 English-French and WMT16 German-English benchmarks, our models respectively obtain 27.1 and 23.6 BLEU points without using a single parallel sentence, outperforming the state of the art by more than 11 BLEU points.

该研究研究了如何在只有大型单语语料库的情况下学习翻译。提出了两种模型，一种是神经模型，一种是基于短语的模型。这些模型通过参数的精心初始化、语言模型的去噪效应和反向迭代自动生成的并行数据来提高翻译性能。在 WMT'14 英语-法语和 WMT'16 德语-英语 基准测试上，这些模型分别获得28.1和25.2 BLEU分数，比现有方法的 BLEU 分数高出11个分数。方法在英语-乌尔都语和英语-罗马尼亚语等低资源语言中也取得了良好的结果。

基于短语和神经网络的无监督机器翻译