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

  title={Refine and Imitate: Reducing Repetition and Inconsistency in Persuasion Dialogues via Reinforcement Learning and Human Demonstration},
  author={Weiyan Shi and Yu Li and Saurav Sahay and Zhou Yu},
Persuasion dialogue systems reflect the machine’s ability to make strategic moves beyond verbal communication, and therefore differen-tiate 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… 

Figures and Tables from this paper

Empathetic Persuasion: Reinforcing Empathy and Persuasiveness in Dialogue Systems

Persuasion is an intricate process involving empathetic connection between two individuals. Plain persuasive responses may make a conversation non-engaging. Even the most well-intended and reasoned

How to Ask for Donations? Learning User-Specific Persuasive Dialogue Policies through Online Interactions

A prototype system that interacts with users with the goal of persuading them to donate to a charity is described and it is documented that the approach leads to learning context-sensitive persuasive strategies that focus on user’s reactions towards donation and contribute to increasing dialogue success.

Seamlessly Integrating Factual Information and Social Content with Persuasive Dialogue

A novel modular dialogue system framework that seamlessly integrates factual information and social content into persuasive dialogue is contributed that is generalizable to any dialogue tasks that have mixed social and task contents.

'Could You Describe the Reason for the Transfer?': A Reinforcement Learning Based Voice-Enabled Bot Protecting Customers from Financial Frauds

A voice-enabled bot that interacts with the customers who are involved with potential telecommunication and online frauds decided by the back-end system, and adopts offline reinforcement learning to learn dialogue policies from real-world human-human chat logs, indicating a significant improvement in user experience as well as anti-fraud effectiveness.

AutoReply: Detecting Nonsense in Dialogue Introspectively with Discriminative Replies

This paper shows that without external classifiers, dialogue models can detect errors in their own messages introspectively, by calculating the likelihood of replies that are indicative of poor messages, and designs an algorithm to search for such discriminative replies automatically.

Human-level play in the game of Diplomacy by combining language models with strategic reasoning.

Cicero is introduced, the first AI agent to achieve human-level performance in Diplomacy, a strategy game involving both cooperation and competition that emphasizes natural language negotiation and tactical coordination between seven players.