An Efficient Transformer Decoder with Compressed Sub-layers. AAAI2021.

Release time:2024-01-09

Hits:

First Author:: Yanyang Li, Ye Lin, Tong Xiao, Jingbo Zhu.

Translation or Not:: no

Pre One:Learning Light-Weight Translation Models from Deep Transformer. AAAI2021.
Next One:Weight Distillation: Transferring the Knowledge in Neural Network Parameters. ACL2021