Towards End-to-end Learning For Dialog State Tracking And Management Using Deep Reinforcement Learning
Tiancheng Zhao, Maxine Eskenazi . Proceedings of the 17th Annual Meeting of the Special Interest Group on Discourse and Dialogue 2016 – 188 citations
This paper presents an end-to-end framework for task-oriented dialog systems using a variant of Deep Recurrent Q-Networks (DRQN). The model is able to interface with a relational database and jointly learn policies for both language understanding and dialog strategy. Moreover, we propose a hybrid algorithm that combines the strength of reinforcement learning and supervised learning to achieve faster learning speed. We evaluated the proposed model on a 20 Question Game conversational game simulator. Results show that the proposed method outperforms the modular-based baseline and learns a distributed representation of the latent dialog state.