seq2seq with TensorFlow
Collection of unfinished tutorials. May be good for educational purposes.
simple sequence-to-sequence model with dynamic unrolling
1 -Deliberately slow-moving, explicit tutorial. I tried to thoroughly explain everything that I found in any way confusing.
Implements simple seq2seq model described in Sutskever at al., 2014 and tests it against toy memorization task.
Picture from Sutskever at al., 2014
advanced dynamic seq2seq
2 -Encoder is bidirectional now. Decoder is implemented using
tf.nn.raw_rnn
. It feeds previously generated tokens during training as inputs, instead of target sequence.
Picture from Deep Learning for Chatbots
Using tf.contrib.seq2seq
(TF<=1.1)
3 - New dynamic seq2seq appeared in r1.0. Let's try it.
UPDATE: that this tutorial doesn't work with tf version > 1.1, API. I recommend checking out new official tutorial instead to learn high-level seq2seq API.