Demonstration of interactive dialog teaching for learning a practical end-to-end dialog manager

This is a demonstration of a platform for building practical, task-oriented, end-to-end dialog systems. Whereas traditional dialog systems consists of a pipeline of components such as intent detection,
state tracking, and action selection, an end-to-end dialog system is driven by a machine learning model which takes observable dialog history as input, and directly outputs a distribution over
dialog actions. The benefit of this approach is that intermediate quantities such as intent or dialog state do not need to be labeled – rather, learning can be done directly on example dialogs.