English

Deep Reinforcement Learning for On-line Dialogue State Tracking

Computation and Language 2020-09-23 v1

Abstract

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.

Keywords

Cite

@article{arxiv.2009.10321,
  title  = {Deep Reinforcement Learning for On-line Dialogue State Tracking},
  author = {Zhi Chen and Lu Chen and Xiang Zhou and Kai Yu},
  journal= {arXiv preprint arXiv:2009.10321},
  year   = {2020}
}

Comments

10 pages, 5 figures

R2 v1 2026-06-23T18:42:32.344Z