Deep Reinforcement Learning For Modeling Chit-Chat Dialog With Discrete Attributes

2019/07/05 by Chinnadhurai Sankar, Sujith Ravi, Sankar, Chinnadhurai +1
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Natural Language Processing Techniques #Speech and dialogue systems #Topic Modeling #cs.CL #cs.LG

paper · pdf · doi:10.48550/arxiv.1907.02848

SIGDIAL 2019 - BEST PAPER AWARD

openalex publication_date 2019/07/05 · arxiv created 2019/09/14 · arxiv updated 2019/09/17 · openalex created_date 2022/07/28 · openalex updated_date 2026/07/28

Abstract

Open domain dialog systems face the challenge of being repetitive and producing generic responses. In this paper, we demonstrate that by conditioning the response generation on interpretable discrete dialog attributes and composed attributes, it helps improve the model perplexity and results in diverse and interesting non-redundant responses. We propose to formulate the dialog attribute prediction as a reinforcement learning (RL) problem and use policy gradients methods to optimize utterance generation using long-term rewards. Unlike existing RL approaches which formulate the token prediction as a policy, our method reduces the complexity of the policy optimization by limiting the action space to dialog attributes, thereby making the policy optimization more practical and sample efficient. We demonstrate this with experimental and human evaluations.

Related

• Hierarchical Reinforcement Learning for Open-Domain Dialog
• Deep Reinforcement Learning for Dialogue Generation
• Guided Dialog Policy Learning: Reward Estimation for Multi-Domain Task-Oriented Dialog
• Integrating Pretrained Language Model for Dialogue Policy Learning
• Why Guided Dialog Policy Learning performs well? Understanding the role of adversarial learning and its alternative