https://zhuanlan.zhihu.com/p/129316415 参考: Neural Machine Translation by Jointly Learning to Align and TranslateEffective Approaches to Attention-based Neural Machine TranslationAttention VariantsBahdanauAttention与LuongAttention注意力机制简介-CSDN博客胡文星:seq2seq中的两种attention机制(图+公式)