Deep Reinforcement Learning for On-line Dialogue State Tracking

by   Zhi Chen, et al.

Dialogue state tracking (DST) is a crucial module in dialogue management. It is usually cast as a supervised training problem, which is not convenient for on-line optimization. In this paper, a novel companion teaching based deep reinforcement learning (DRL) framework for on-line DST optimization is proposed. To the best of our knowledge, this is the first effort to optimize the DST module within DRL framework for on-line task-oriented spoken dialogue systems. In addition, dialogue policy can be further jointly updated. Experiments show that on-line DST optimization can effectively improve the dialogue manager performance while keeping the flexibility of using predefined policy. Joint training of both DST and policy can further improve the performance.


page 1

page 2

page 3

page 4


Distributed Structured Actor-Critic Reinforcement Learning for Universal Dialogue Management

The task-oriented spoken dialogue system (SDS) aims to assist a human us...

High-Quality Diversification for Task-Oriented Dialogue Systems

Many task-oriented dialogue systems use deep reinforcement learning (DRL...

Strategic Dialogue Management via Deep Reinforcement Learning

Artificially intelligent agents equipped with strategic skills that can ...

AgentGraph: Towards Universal Dialogue Management with Structured Deep Reinforcement Learning

Dialogue policy plays an important role in task-oriented spoken dialogue...

Findings from Experiments of On-line Joint Reinforcement Learning of Semantic Parser and Dialogue Manager with real Users

Design of dialogue systems has witnessed many advances lately, yet acqui...

Optimization of Information-Seeking Dialogue Strategy for Argumentation-Based Dialogue System

Argumentation-based dialogue systems, which can handle and exchange argu...

Joint On-line Learning of a Zero-shot Spoken Semantic Parser and a Reinforcement Learning Dialogue Manager

Despite many recent advances for the design of dialogue systems, a true ...