0

I have recently been trying to learn DL4J but have run into some issues. They have an example of a neural network generating Shakespeare-like text based off and input character but I can't seem to find anything that wold indicate a possible way of creating a response to an input statement.

I would like to use an input string such as "Hello" and have it be able to generate a response of varying length depended on the input. I would like to know if this is possible using LSTM and have a point in the right direction as I have no idea where to even start.

mkrieger1
  • 19,194
  • 5
  • 54
  • 65
Drok_
  • 149
  • 1
  • 7
  • I don't want to provide this as the answer, but will respond with this as a comment: For an indepth question like this we have our support chat channel: https://gitter.im/deeplearning4j/deeplearning4j It is hard for us to support every possible use case people have. We also have our oreilly book if you are new to deep learning: http://shop.oreilly.com/product/0636920035343.do – Adam Gibson Nov 30 '16 at 00:03

1 Answers1

0

We have plenty of documentation this actually. This gives you a layout of what an RNN looks like: http://deeplearning4j.org/usingrnns

The model you would be looking at is character level, in general what you want is question answering though. You may want to look at an architecture like this: https://cs.umd.edu/~miyyer/pubs/2014_qb_rnn.pdf

If you are completely new to NLP, I would look at this class: https://www.youtube.com/playlist?list=PLhVhwi0Pz282aSA2uZX4jR3SkF3BKyMOK

It covers question answering as well.

Adam Gibson
  • 3,055
  • 1
  • 10
  • 12