[Attention is all you need] (https://papers.nips.cc/paper/7181-attention-is-all-you-need.pdf)

[Self-Attentional Acoustic Models] （https://arxiv.org/abs/1803.09519）

[Agreement-based Joint Training for Bidirectional Attention-based Neural Machine Translation] (https://arxiv.org/pdf/1512.04650.pdf)

[WEIGHTED TRANSFORMER NETWORK FOR MACHINE TRANSLATION] (https://arxiv.org/pdf/1711.02132)