Affordable Access

Towards End-to-End Learning for Dialog State Tracking and Management using Deep Reinforcement Learning

Authors
  • Zhao, Tiancheng
  • Eskenazi, Maxine
Type
Preprint
Publication Date
Jun 08, 2016
Submission Date
Jun 08, 2016
Identifiers
arXiv ID: 1606.02560
Source
arXiv
License
Unknown
External links

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.

Report this publication

Statistics

Seen <100 times