Sparse Sinkhorn Attention

26 Feb 2020Yi TayDara BahriLiu YangDonald MetzlerDa-Cheng Juan

We propose Sparse Sinkhorn Attention, a new efficient and sparse method for learning to attend. Our method is based on differentiable sorting of internal representations... (read more)

PDF Abstract

Results from the Paper


  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.

Methods used in the Paper