3
$\begingroup$

n this paper (here) they suppose a "unified architecture for NLP" with deep neural networks with multitask learning

My problem is to understand the layer architecture in figure 1, see below: unified deep learning architecture for NLP

  1. Is someone able to give me a concrete, reproducible example how this architecture processing 3 sentences through their layers?
  2. What are the outputs after each layer?
  3. Why they choose which layer?

Thans in advance!

$\endgroup$
0

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.