——————————————————————————————
——————————————————————————————
——————————————————————————
——————————————————————————
深度学习中的注意力模型:https://zhuanlan.zhihu.com/p/37601161
Transformer的博客文章:
https://jalammar.github.io/illustrated-transformer/
http://nlp.seas.harvard.edu/2018/04/03/attention.html
http://www.52nlp.cn/tag/bert%E5%AE%9E%E6%88%98