Machine translation systems achieve near human-level performance on some
languages, yet their effectiveness strongly relies on the availability of large
amounts of parallel sentences, 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 a careful initialization of the parameters, the denoising effect of
language models and automatic generation of parallel data by iterative
back-translation. These models are significantly better than methods from the
literature, while being simpler and having fewer hyper-parameters. On the
widely used WMT'14 English-French and WMT'16 German-English benchmarks, our
models respectively obtain 28.1 and 25.2 BLEU points without using a single
parallel sentence, outperforming the state of the art by more than 11 BLEU
points. On low-resource languages like English-Urdu and English-Romanian, our
methods achieve even better results than semi-supervised and supervised
approaches leveraging the paucity of available bitexts. Our code for NMT and
PBSMT is publicly available.

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。