In this work, we explore multiple neural architectures adapted for the task
of automatic post-editing of machine translation output. We focus on neural
end-to-end models that combine both inputs $mt$ (raw MT output) and $src$
(source language input) in a single neural architecture, modeling $\{mt, src\}
\rightarrow pe$ directly. Apart from that, we investigate the influence of
hard-attention models which seem to be well-suited for monolingual tasks, as
well as combinations of both ideas. We report results on data sets provided
during the WMT-2016 shared task on automatic post-editing and can demonstrate
that dual-attention models that incorporate all available data in the APE
scenario in a single model improve on the best shared task system and on all
other published results after the shared task. Dual-attention models that are
combined with hard attention remain competitive despite applying fewer changes
to the input.

本文研究了多种神经架构用于机器翻译自动后编辑任务。研究内容包括：将 $mt$ 和 $src$ 结合在一起直接对目标进行建模的端到端模型、硬注意力模型和以上两种结合。结果表明：将多个神经架构和硬注意力相结合，所构建的双注意力模型在自动后编辑任务中提供了更好的表现。