Continuously Learning Neural Dialogue Management
This work addresses dialogue management for task-oriented spoken dialogue systems, presenting an incremental improvement by combining supervised and reinforcement learning in a single model.
The authors tackled the problem of dialogue management in task-oriented spoken dialogue systems by proposing a two-step neural network approach that learns from supervised data and then continuously improves via reinforcement learning, resulting in improved performance in interactive settings, especially under higher-noise conditions.
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.