Continuously Learning Neural Dialogue Management

06/08/2016
by   Pei-Hao Su, et al.
0

We describe a two-step approach for dialogue management in task-oriented spoken dialogue systems. A unified neural network framework is proposed to enable the system to first learn by supervision from a set of dialogue data and then continuously improve its behaviour via reinforcement learning, all using gradient-based algorithms on one single model. The experiments demonstrate the supervised model's effectiveness in the corpus-based evaluation, with user simulation, and with paid human subjects. The use of reinforcement learning further improves the model's performance in both interactive settings, especially under higher-noise conditions.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset