Towards End-to-End Learning for Dialog State Tracking and Management using Deep Reinforcement Learning
Year: 2016
Type: conference-paper
Abstract: 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.
DOI: 10.18653/v1/w16-3601
Authors: Tiancheng Zhao, Maxine Eskenazi
Institution: Carnegie Mellon University
Language: English
Topic: Speech and dialogue systems
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
Funder: National Science Foundation
OpenAlex ID: W2962776342
