English

Adaptive Natural Language Generation for Task-oriented Dialogue via Reinforcement Learning

Computation and Language 2022-09-19 v1 Artificial Intelligence

Abstract

When a natural language generation (NLG) component is implemented in a real-world task-oriented dialogue system, it is necessary to generate not only natural utterances as learned on training data but also utterances adapted to the dialogue environment (e.g., noise from environmental sounds) and the user (e.g., users with low levels of understanding ability). Inspired by recent advances in reinforcement learning (RL) for language generation tasks, we propose ANTOR, a method for Adaptive Natural language generation for Task-Oriented dialogue via Reinforcement learning. In ANTOR, a natural language understanding (NLU) module, which corresponds to the user's understanding of system utterances, is incorporated into the objective function of RL. If the NLG's intentions are correctly conveyed to the NLU, which understands a system's utterances, the NLG is given a positive reward. We conducted experiments on the MultiWOZ dataset, and we confirmed that ANTOR could generate adaptive utterances against speech recognition errors and the different vocabulary levels of users.

Keywords

Cite

@article{arxiv.2209.07873,
  title  = {Adaptive Natural Language Generation for Task-oriented Dialogue via Reinforcement Learning},
  author = {Atsumoto Ohashi and Ryuichiro Higashinaka},
  journal= {arXiv preprint arXiv:2209.07873},
  year   = {2022}
}

Comments

Accepted by COLING 2022

R2 v1 2026-06-28T01:26:41.286Z