Neural machine translation between the writings of Shakespeare and modern English using TensorFlow - tokestermw/tensorflow-shakespeare

http://arxiv.org/abs/1506.05869
A Neural Conversational Model
Oriol Vinyals, Quoc Le
Conversational modeling is an important task in natural language understanding and machine intelligence. Although previous approaches exist, they are often restricted to specific domains (e.g., booking an airline ticket) and require hand-crafted rules. In this paper, we present a simple approach for this task which uses the recently proposed sequence to sequence framework. Our model converses by predicting the next sentence given the previous sentence or sentences in a conversation.
#nlp #seq2seq #paper

Trying to understand why dropout networks work so well, I was quite surprised to see that we can get principled uncertainty information from these models for free – without changing a thing.