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。