Great tutorial - Well written and good patterns for TensorFlow usage, e.g. checkpointing, name scopes for cleaning up the graph visualization, and using summaries/TensorBoard, and also nice explanations of the concepts.<p>Though I'm curious why you used VALID padding not SAME for the conv layers? It seems like it would be simpler to use SAME.<p>Also, minor nit: TensorFlow and TensorBoard should both have two letters capitalized
Looks neat. Why did you bother using <PAD> words to have sentences be the same length, when you're using a bag-of-words (document-term matrix) model anyway?<p>Each sentence vector ends up being the length of the vocabulary, so they're already the same length. You can probably drop step #3 in this case.
This looks pretty nice. It's worth pointing to the seq2seq TensorFlow example which covers a lot of similar topics.<p>Is there an example anywhere of how to initilize from the word2vec embeddings?