While modern machine translation has relied on large parallel corpora, a
recent line of work has managed to train Neural Machine Translation (NMT)
systems from monolingual corpora only (Artetxe et al., 2018c; Lample et al.,
2018). Despite the potential of this approach for low-resource settings,
existing systems are far behind their supervised counterparts, limiting their
practical interest. In this paper, we propose an alternative approach based on
phrase-based Statistical Machine Translation (SMT) that significantly closes
the gap with supervised systems. Our method profits from the modular
architecture of SMT: we first induce a phrase table from monolingual corpora
through cross-lingual embedding mappings, combine it with an n-gram language
model, and fine-tune hyperparameters through an unsupervised MERT variant. In
addition, iterative backtranslation improves results further, yielding, for
instance, 14.08 and 26.22 BLEU points in WMT 2014 English-German and
English-French, respectively, an improvement of more than 7-10 BLEU points over
previous unsupervised systems, and closing the gap with supervised SMT (Moses
trained on Europarl) down to 2-5 BLEU points. Our implementation is available
at this https URL

本文提出了一种基于 SMT 的新颖方法，通过跨语言嵌入映射从单语料库中诱导短语表，再将其与 N-gram 语言模型相结合，通过无监督超参数微调的变体来实现迭代反向翻译，并在 WMT 2014 中实现了超过 7-10 BLEU 点的改进，与监督 SMT 相比关闭了 2-5 BLEU 点的差距。

无监督统计机器翻译

Unsupervised Statistical Machine Translation

Compared to traditional statistical machine translation (SMT), neural machine
translation (NMT) often sacrifices adequacy for the sake of fluency. We propose
a method to combine the advantages of traditional SMT and NMT by exploiting an
existing phrase-based SMT model to compute the phrase-based decoding cost for
an NMT output and then using this cost to rerank the n-best NMT outputs. The
main challenge in implementing this approach is that NMT outputs may not be in
the search space of the standard phrase-based decoding algorithm, because the
search space of phrase-based SMT is limited by the phrase-based translation
rule table. We propose a soft forced decoding algorithm, which can always
successfully find a decoding path for any NMT output. We show that using the
forced decoding cost to rerank the NMT outputs can successfully improve
translation quality on four different language pairs.

本研究提出了一种将传统 SMT 模型与神经机器翻译相结合的方法，从而提高翻译质量。该方法利用现有的基于短语的 SMT 模型计算基于短语的解码成本，并将其用于重新排列 n 个最佳 NMT 输出。研究表明，利用强制解码成本对 NMT 输出进行排序可以成功提高四种不同语言的翻译质量。

基于短语的强制解码改进神经机器翻译

Improving Neural Machine Translation through Phrase-based Forced  Decoding

This paper describes QCRI's machine translation systems for the IWSLT 2016
evaluation campaign. We participated in the Arabic->English and English->Arabic
tracks. We built both Phrase-based and Neural machine translation models, in an
effort to probe whether the newly emerged NMT framework surpasses the
traditional phrase-based systems in Arabic-English language pairs. We trained a
very strong phrase-based system including, a big language model, the Operation
Sequence Model, Neural Network Joint Model and Class-based models along with
different domain adaptation techniques such as MML filtering, mixture modeling
and using fine tuning over NNJM model. However, a Neural MT system, trained by
stacking data from different genres through fine-tuning, and applying ensemble
over 8 models, beat our very strong phrase-based system by a significant 2 BLEU
points margin in Arabic->English direction. We did not obtain similar gains in
the other direction but were still able to outperform the phrase-based system.
We also applied system combination on phrase-based and NMT outputs.

本文介绍了 QCRI 针对 IWSLT 2016 的机器翻译系统。作者们建立了基于短语和神经网络的机器翻译模型，并比较了两种模型在阿拉伯语 - 英语语言对中性能的表现。研究结果表明，在阿拉伯语 - 英语翻译中，神经网络模型的 BLEU 值比基于短语的模型高 2 点。作者还将两种模型的输出进行了系统组合。