English

Dialog Action-Aware Transformer for Dialog Policy Learning

Computation and Language 2023-09-06 v1

Abstract

Recent works usually address Dialog policy learning DPL by training a reinforcement learning (RL) agent to determine the best dialog action. However, existing works on deep RL require a large volume of agent-user interactions to achieve acceptable performance. In this paper, we propose to make full use of the plain text knowledge from the pre-trained language model to accelerate the RL agent's learning speed. Specifically, we design a dialog action-aware transformer encoder (DaTrans), which integrates a new fine-tuning procedure named masked last action task to encourage DaTrans to be dialog-aware and distils action-specific features. Then, DaTrans is further optimized in an RL setting with ongoing interactions and evolves through exploration in the dialog action space toward maximizing long-term accumulated rewards. The effectiveness and efficiency of the proposed model are demonstrated with both simulator evaluation and human evaluation.

Keywords

Cite

@article{arxiv.2309.02240,
  title  = {Dialog Action-Aware Transformer for Dialog Policy Learning},
  author = {Huimin Wang and Wai-Chung Kwan and Kam-Fai Wong},
  journal= {arXiv preprint arXiv:2309.02240},
  year   = {2023}
}

Comments

To be appeared in SIGdial 2023

R2 v1 2026-06-28T12:13:08.460Z