R-Transformer: Recurrent Neural Network Enhanced Transformer

Wang Zhiwei
Wang Zhiwei
Liu Zitao
Liu Zitao
Cited by: 19|Views29

Abstract:

Recurrent Neural Networks have long been the dominating choice for sequence modeling. However, it severely suffers from two issues: impotent in capturing very long-term dependencies and unable to parallelize the sequential computation procedure. Therefore, many non-recurrent sequence models that are built on convolution and attention op...More

Code:

Data:

Full Text
Bibtex
Your rating :
0

 

Tags
Comments