Deep Reinforcement Learning for Inquiry Dialog Policies with Logical Formula Embeddings
This work addresses the problem of automating inquiry dialog systems for users, but it is incremental as it builds on existing logical formula representations.
The paper tackled learning inquiry dialog policies by combining deep reinforcement learning with a novel logical formula embedding framework, achieving performance comparable to or better than existing rule-based methods.
This paper is the first attempt to learn the policy of an inquiry dialog system (IDS) by using deep reinforcement learning (DRL). Most IDS frameworks represent dialog states and dialog acts with logical formulae. In order to make learning inquiry dialog policies more effective, we introduce a logical formula embedding framework based on a recursive neural network. The results of experiments to evaluate the effect of 1) the DRL and 2) the logical formula embedding framework show that the combination of the two are as effective or even better than existing rule-based methods for inquiry dialog policies.