In recent years, several studies on neural machine translation (NMT) have
attempted to use document-level context by using a multi-encoder and two
attention mechanisms to read the current and previous sentences to incorporate
the context of the previous sentences. These studies concluded that the
target-side context is less useful than the source-side context. However, we
considered that the reason why the target-side context is less useful lies in
the architecture used to model these contexts.
Therefore, in this study, we investigate how the target-side context can
improve context-aware neural machine translation. We propose a weight sharing
method wherein NMT saves decoder states and calculates an attention vector
using the saved states when translating a current sentence. Our experiments
show that the target-side context is also useful if we plug it into NMT as the
decoder state when translating a previous sentence.

本文研究使用多编码器和两个注意力机制以读取当前和先前句子以融入上下文的神经机器翻译（NMT）的文档级上下文问题，提出了一种权重共享方法，并得出结论，当在 NMT 中作为解码器状态插入目标端上下文时，目标端上下文也是有用的。