Refine and Imitate: Reducing Repetition and Inconsistency in Persuasion Dialogues via Reinforcement Learning and Human Demonstration

TL;DR

This paper introduces a reinforcement learning approach combined with human demonstration to improve persuasion dialogue systems by reducing repetition and inconsistency, leading to more persuasive and diverse conversations without relying on user simulators.

Contribution

The study proposes a novel RL-based refinement method that distills sentence-level rewards and learns from human demonstrations to enhance persuasion dialogue quality.

Findings

Outperforms previous models on automatic and human evaluations

Generates more diverse and consistent responses

Achieves higher persuasion success in donation tasks

Abstract

Persuasion dialogue systems reflect the machine's ability to make strategic moves beyond verbal communication, and therefore differentiate themselves from task-oriented or open-domain dialogue systems and have their own unique values. However, the repetition and inconsistency problems still persist in dialogue response generation and could substantially impact user experience and impede the persuasion outcome. Besides, although reinforcement learning (RL) approaches have achieved big success in strategic tasks such as games, they require a sophisticated user simulator to provide real-time feedback to the dialogue system, which limits the application of RL on persuasion dialogues. To address these issues towards a better persuasion dialogue system, we apply RL to refine a language model baseline without user simulators, and distill sentence-level information about repetition, inconsistency, and task relevance through rewards. Moreover, to better accomplish the persuasion task, the model learns from human demonstration to imitate human persuasion behavior and selects the most persuasive responses. Experiments show that our model outperforms previous state-of-the-art dialogue models on both automatic metrics and human evaluation results on a donation persuasion task, and generates more diverse, consistent and persuasive conversations according to the user feedback.