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

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

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


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.