2021

Transformer的9种变体概览 February 20, 2021

论文阅读笔记：类似于Multi-head注意力的Multi-Cast-Attention网络 February 2, 2021

2020

NLP中遇到的各类Attention结构汇总以及代码复现 December 20, 2020

论文阅读笔记：全局-局部自注意力的对话状态跟踪 October 20, 2020

论文阅读笔记：Attention-Is-All-You-Need September 17, 2020