Neural sequence to sequence learning recently became a very promising
paradigm in machine translation, achieving competitive results with statistical
phrase-based systems. In this system description paper, we attempt to utilize
several recently published methods used for neural sequential learning in order
to build systems for WMT 2016 shared tasks of Automatic Post-Editing and
Multimodal Machine Translation.

本文利用最近发表的多种神经序列学习方法，构建用于 WMT 2016 共享任务的自动后期编辑和多模态机器翻译系统。

WMT16 自动后编辑和多模式翻译任务中的 CUNI 系统

CUNI System for WMT16 Automatic Post-Editing and Multimodal Translation  Tasks

We participated in the WMT 2016 shared news translation task by building
neural translation systems for four language pairs, each trained in both
directions: English<->Czech, English<->German, English<->Romanian and
English<->Russian. Our systems are based on an attentional encoder-decoder,
using BPE subword segmentation for open-vocabulary translation with a fixed
vocabulary. We experimented with using automatic back-translations of the
monolingual News corpus as additional training data, pervasive dropout, and
target-bidirectional models. All reported methods give substantial
improvements, and we see improvements of 4.3--11.2 BLEU over our baseline
systems. In the human evaluation, our systems were the (tied) best constrained
system for 7 out of 8 translation directions in which we participated.

我们参加了 WMT 2016 分享的新闻翻译任务，并为四种语言建立了神经翻译系统，每种语言都在英语和其它语言的两个方向上进行训练。使用了基于注意力的编码器 - 解码器、BPE 子词段和自动回译等技术，我们的方法使得我们的结果比基准系统提高了 4.3-11.2 BLEU，人工评估显示我们的系统在 8 个翻译方向中有 7 个是最好的约束系统。

WMT 16 爱丁堡神经机器翻译系统

Edinburgh Neural Machine Translation Systems for WMT 16

This paper describes the AMU-UEDIN submissions to the WMT 2016 shared task on
news translation. We explore methods of decode-time integration of
attention-based neural translation models with phrase-based statistical machine
translation. Efficient batch-algorithms for GPU-querying are proposed and
implemented. For English-Russian, our system stays behind the state-of-the-art
pure neural models in terms of BLEU. Among restricted systems, manual
evaluation places it in the first cluster tied with the pure neural model. For
the Russian-English task, our submission achieves the top BLEU result,
outperforming the best pure neural system by 1.1 BLEU points and our own
phrase-based baseline by 1.6 BLEU. After manual evaluation, this system is the
best restricted system in its own cluster. In follow-up experiments we improve
results by additional 0.8 BLEU.

本文提出了将基于注意力的神经翻译模型与基于短语的统计机器翻译方法集成的方法，并使用有效的 GPU 批处理算法。在 WMT 2016 共享任务上，该方法的英俄翻译系统表现早期略逊于基于纯神经网络的系统，但在限制系统方面表现优异。而其俄英翻译系统在 BLEU 评估中取得最佳结果，表现优于最佳纯神经网络系统 1.1 个 BLEU 点和基于短语的基线系统 1.6 个 BLEU 点，且在其限制系统的聚类中表现最佳。