Multi-branch Attentive Transformer

Yang Fan
Yang Fan
Shufang Xie
Shufang Xie
Lijun Wu
Lijun Wu
Xiang-Yang Li
Xiang-Yang Li
Cited by: 0|Bibtex|Views67
Other Links: arxiv.org

Abstract:

While the multi-branch architecture is one of the key ingredients to the success of computer vision tasks, it has not been well investigated in natural language processing, especially sequence learning tasks. In this work, we propose a simple yet effective variant of Transformer called multi-branch attentive Transformer (briefly, MAT), ...More

Code:

Data:

Your rating :
0

 

Tags
Comments