This paper describes the Microsoft submission to the WMT2018 news translation
shared task. We participated in one language direction -- English-German. Our
system follows current best-practice and combines state-of-the-art models with
new data filtering (dual conditional cross-entropy filtering) and sentence
weighting methods. We trained fairly standard Transformer-big models with an
updated version of Edinburgh's training scheme for WMT2017 and experimented
with different filtering schemes for Paracrawl. According to automatic metrics
(BLEU) we reached the highest score for this subtask with a nearly 2 BLEU point
margin over the next strongest system. Based on human evaluation we ranked
first among constrained systems. We believe this is mostly caused by our data
filtering/weighting regime.

本文介绍了微软参加 WMT2018 新闻翻译共享任务的提交，对于英语到德语的一种语言方向中，基于最佳实践，采用了最先进的模型和新数据过滤和句子加权方法来训练在 Paracrawl 上实验结果表明，根据自动指标 (BLEU)，我们在此子任务中得分最高，比接下来最强大的系统高近 2 BLEU 分数，根据人工评估，我们在受限系统中排名第一，我们认为这主要是由于我们的数据过滤 / 加权组合的实施。

微软提交 WMT2018 新闻翻译任务报告：如何不再担忧，爱上数据

Microsoft's Submission to the WMT2018 News Translation Task: How I  Learned to Stop Worrying and Love the Data

This paper describes the Microsoft and University of Edinburgh submission to
the Automatic Post-editing shared task at WMT2018. Based on training data and
systems from the WMT2017 shared task, we re-implement our own models from the
last shared task and introduce improvements based on extensive parameter
sharing. Next we experiment with our implementation of dual-source transformer
models and data selection for the IT domain. Our submissions decisively wins
the SMT post-editing sub-task establishing the new state-of-the-art and is a
very close second (or equal, 16.46 vs 16.50 TER) in the NMT sub-task. Based on
the rather weak results in the NMT sub-task, we hypothesize that
neural-on-neural APE might not be actually useful.

这篇论文介绍了微软和爱丁堡大学 2018 年 WMT 共享任务中的自动后编辑竞赛，利用上一次共享任务的训练数据和系统，重新实现了我们自己的模型，并以广泛的参数共享为基础进行改进。接着，我们对 IT 领域的双源变压器模型和数据选择进行了实验。我们的提交结果在 SMT 后编辑子任务中占据了决定性胜利，建立了新的技术水平，并在 NMT 子任务中获得了非常接近的第二名（或相等，16.46 vs. 16.50 TER）。根据 NMT 子任务的相对较弱结果，我们假设神经对神经的 APE 实际上并不有用。