Towards Explainable and Controllable Open Domain Dialogue Generation with Dialogue Acts

Abstract

We study open domain dialogue generation with dialogue acts designed to explain how people engage in social chat. To imitate human behavior, we propose managing the flow of human-machine interactions with the dialogue acts as policies. The policies and response generation are jointly learned from human-human conversations, and the former is further optimized with a reinforcement learning approach. With the dialogue acts, we achieve significant improvement over state-of-the-art methods on response quality for given contexts and dialogue length in both machine-machine simulation and human-machine conversation.

arXiv commentThe paper is also available on OpenReview of ICLR 2018 (https://openreview.net/forum?id=Bym0cU1CZ)

References in corpus (13)

• Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
• ADADELTA: An Adaptive Learning Rate Method
• A Neural Conversational Model
• Dialogue Act Modeling for Automatic Tagging and Recognition of Conversational Speech
• How NOT To Evaluate Your Dialogue System: An Empirical Study of Unsupervised Evaluation Metrics for Dialogue Response Generation
• Deep Reinforcement Learning for Dialogue Generation
• A Deep Reinforcement Learning Chatbot
• Conversational AI: The Science Behind the Alexa Prize
• A Network-based End-to-End Trainable Task-oriented Dialogue System
• Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoders
• Emotional Chatting Machine: Emotional Conversation Generation with Internal and External Memory
• Google's Multilingual Neural Machine Translation System: Enabling Zero-Shot Translation
• A Neural Network Approach to Context-Sensitive Generation of Conversational Responses

Cited by in corpus (12)

• Zero-Resource Knowledge-Grounded Dialogue Generation
• Policy-Driven Neural Response Generation for Knowledge-Grounded Dialogue Systems
• Probing Neural Dialog Models for Conversational Understanding
• Generating Multiple Diverse Responses with Multi-Mapping and Posterior Mapping Selection
• Democratizing Chatbot Debugging: A Computational Framework for Evaluating and Explaining Inappropriate Chatbot Responses
• A Taxonomy of Empathetic Response Intents in Human Social Conversations
• Fine-grained Emotion and Intent Learning in Movie Dialogues
• Document-editing Assistants and Model-based Reinforcement Learning as a Path to Conversational AI
• Semantic-Enhanced Explainable Finetuning for Open-Domain Dialogues
• Controllable Dialogue Generation with Disentangled Multi-grained Style Specification and Attribute Consistency Reward
• Proposal Towards a Personalized Knowledge-powered Self-play Based Ensemble Dialog System
• Local Explanation of Dialogue Response Generation