4
$\begingroup$

Is there any available recursive neural network implementation in TensorFlow TensorFlow's tutorials do not present any recursive neural networks. Most TensorFlow code I've found is CNN, LSTM, GRU, vanilla recurrent neural networks or MLP. I am most interested in implementations for natural language processing.

Example of a recursive neural network:

enter image description here

The tree structure may vary between different inputs. I.e., I do not want the tree structure to be fixed.

$\endgroup$
  • $\begingroup$ I was looking for something similar, if you're open to using theano instead of tensorflow you could have a look github.com/ofirnachum/tree_rnn. There are a few examples on display. $\endgroup$ – Lukasz Nov 22 '16 at 17:42
1
$\begingroup$

Take a look at Tensorflow Fold:

https://github.com/tensorflow/fold

TensorFlow Fold is a library for creating TensorFlow models that consume structured data, where the structure of the computation graph depends on the structure of the input data.

$\endgroup$
0
$\begingroup$

These types of architectures are awkward in Tensorflow. I think someone did implement them though. http://www.kdnuggets.com/2016/06/recursive-neural-networks-tensorflow.html

You might prefer to use DyNet, which was designed to allow for dynamically changing architectures. https://github.com/clab/dynet

$\endgroup$
0
$\begingroup$

I hope this is what you need: https://github.com/sapruash/RecursiveNN:

Tensorflow implementation of Recursive Neural Networks using LSTM units as described in "Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networks" by Kai Sheng Tai, Richard Socher, and Christopher D. Manning.

$\endgroup$
  • 1
    $\begingroup$ You need to explain your answer and not just give a link that you think may be applicable. $\endgroup$ – Michael Chernick May 25 '17 at 15:40
  • $\begingroup$ This is rather a comment. Can someone convert this answer to a comment? $\endgroup$ – Ferdi May 25 '17 at 16:00
  • 1
    $\begingroup$ I have added some information, it qualifies as an answer in my opinion. Is that okay for you Ferdi and Michael Chernick? $\endgroup$ – Franck Dernoncourt May 25 '17 at 16:05

Your Answer

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

Not the answer you're looking for? Browse other questions tagged or ask your own question.