keras-self-attention icon indicating copy to clipboard operation
keras-self-attention copied to clipboard

Published 20 hours ago • verified publisher icon CyberZHG

Self-attention before BiLSTM

Open katekats opened this issue 2 years ago • 0 comments

Hi,

Is it possible to put the self-attention layer from the library after the input vector (word embeddings) and before the BiLSTM layer? How can the equations of the self-attention layer be re-written?

katekats avatar May 22 '22 16:05 katekats