Towards Learning Transferable Conversational Skills using Multi-dimensional Dialogue Modelling
This addresses the limitation of reliance on in-domain data for dialogue systems, offering a method to improve cross-domain adaptability, though it appears incremental based on existing statistical approaches.
The paper tackles the problem of cross-domain scalability in spoken dialogue systems by proposing a multi-dimensional dialogue management framework that learns transferable conversational skills, with initial experiments showing accelerated learning through policy transfer.
Recent statistical approaches have improved the robustness and scalability of spoken dialogue systems. However, despite recent progress in domain adaptation, their reliance on in-domain data still limits their cross-domain scalability. In this paper, we argue that this problem can be addressed by extending current models to reflect and exploit the multi-dimensional nature of human dialogue. We present our multi-dimensional, statistical dialogue management framework, in which transferable conversational skills can be learnt by separating out domain-independent dimensions of communication and using multi-agent reinforcement learning. Our initial experiments with a simulated user show that we can speed up the learning process by transferring learnt policies.