Deep Reinforcement Learning for Multi-Domain Dialogue Systems
This work addresses scalability issues in multi-domain dialogue systems, which is an incremental improvement for developers of spoken dialogue systems.
The authors tackled the scalability problem of deep reinforcement learning methods like DQN for multi-domain dialogue systems by proposing NDQN, which showed better scalability in simulations for restaurant and hotel domains.
Standard deep reinforcement learning methods such as Deep Q-Networks (DQN) for multiple tasks (domains) face scalability problems. We propose a method for multi-domain dialogue policy learning---termed NDQN, and apply it to an information-seeking spoken dialogue system in the domains of restaurants and hotels. Experimental results comparing DQN (baseline) versus NDQN (proposed) using simulations report that our proposed method exhibits better scalability and is promising for optimising the behaviour of multi-domain dialogue systems.