Deep Reinforcement Learning for On-line Dialogue State Tracking

被引：2

作者：

Chen, Zhi ^{[1
]}

Chen, Lu ^{[1
]}

Zhou, Xiang ^{[1
]}

Yu, Kai ^{[1
]}

机构：

[1] Shanghai Jiao Tong Univ, AI Inst, MoE Key Lab Artificial Intelligence, X LANCE Lab,Dept Comp Sci & Engn, Shanghai, Peoples R China

来源：

MAN-MACHINE SPEECH COMMUNICATION, NCMMSC 2022 | 2023年 / 1765卷

关键词：

Task-oriented Dialogue System; Joint Training; Reinforcement Learning;

D O I：

10.1007/978-981-99-2401-1_25

中图分类号：

O42 [声学];

学科分类号：

070206 ; 082403 ;

摘要：

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.

引用

页码：278 / 292

页数：15