Hybrid Code Networks: practical and efficient end-to-end dialog control with supervised and reinforcement learning

Task-oriented dialog systems help a user to accomplish some goal using natural language, such as making a restaurant reservation, getting technical support, or placing a phonecall. Historically, these dialog systems have been built as a pipeline, with modules for language understanding, state tracking, action selection, and language generation. However, dependencies between modules introduce considerable complexity – for example, it is often unclear how to define the dialog state and what history to maintain, yet action selection relies exclusively on the state for input. Moreover, training each module requires specialized labels.