search

wangqiangneu / MT-PaperReading

Record my paper reading about Machine Translation and other related works.
36 stars 2 forks source link

20-ICLR(reviewing)-REDUCING TRANSFORMER DEPTH ON DEMAND WITH STRUCTURED DROPOUT #3

Open wangqiangneu opened 5 years ago

wangqiangneu commented 5 years ago

简介

只训练一个模型，能在inference时根据需求切换不同的子网络(减少层数)，而不必像传统的pruning或distillation方法那样得为不同尺寸的自网络分别训练。

论文信息

总结