Word embedding is central to neural machine translation (NMT), which has attracted intensive research interest in recent years. In NMT, the source embedding plays the role of the entrance while the target embedding acts as the terminal. These layers occupy most of the model parameters for representation learning. Furthermore, they indirectly interface via a soft-attention mechanism, which makes them comparatively isolated. In this paper, we propose shared-private bilingual word embeddings, which give a closer relationship between the source and target embeddings, and which also reduce the number of model parameters. For similar source and target words, their embeddings tend to share a part of the features and they cooperatively learn these common representation units. Experiments on 5 language pairs belonging to 6 different language families and written in 5 different alphabets demonstrate that the proposed model provides a significant performance boost over the strong baselines with dramatically fewer model parameters.

本文介绍一种共享—私有双语词嵌入方法，该方法能够在神经机器翻译中提升性能，同时减少模型参数。实验表明，该方法在不同语系和语言字母表的5种语言对中大大提高了性能。

神经机器翻译共享-私有双语词嵌入