Deep Active Learning for Dialogue Generation

Abstract

We propose an online, end-to-end, neural generative conversational model for open-domain dialogue. It is trained using a unique combination of offline two-phase supervised learning and online human-in-the-loop active learning. While most existing research proposes offline supervision or hand-crafted reward functions for online reinforcement, we devise a novel interactive learning mechanism based on hamming-diverse beam search for response generation and one-character user-feedback at each step. Experiments show that our model inherently promotes the generation of semantically relevant and interesting responses, and can be used to train agents with customized personas, moods and conversational styles.

Accepted at 6th Joint Conference on Lexical and Computational Semantics (*SEM) 2017 (Previously titled "Online Sequence-to-Sequence Active Learning for Open-Domain Dialogue Generation" on ArXiv)

References in corpus (10)

• Sequence to Sequence Learning with Neural Networks
• Chameleons in imagined conversations: A new approach to understanding coordination of linguistic style in dialogs
• A Simple, Fast Diverse Decoding Algorithm for Neural Generation
• A Neural Network Approach to Context-Sensitive Generation of Conversational Responses
• Learning through Dialogue Interactions by Asking Questions
• Composite Task-Completion Dialogue Policy Learning via Hierarchical Deep Reinforcement Learning
• Deep Reinforcement Learning for Multi-Domain Dialogue Systems
• A Conditional Variational Framework for Dialog Generation
• Investigation of Language Understanding Impact for Reinforcement Learning Based Dialogue Systems
• Agent-Agnostic Human-in-the-Loop Reinforcement Learning

Cited by in corpus (8)

• Adversarial Learning for Neural Dialogue Generation
• A Survey of Natural Language Generation Techniques with a Focus on Dialogue Systems - Past, Present and Future Directions
• Data Distillation for Controlling Specificity in Dialogue Generation
• Are You Talking to Me? Reasoned Visual Dialog Generation through Adversarial Learning
• Non-Autoregressive Neural Dialogue Generation
• Diverse Beam Search for Increased Novelty in Abstractive Summarization
• Diversifying Topic-Coherent Response Generation for Natural Multi-turn Conversations
• Would you Like to Talk about Sports Now? Towards Contextual Topic Suggestion for Open-Domain Conversational Agents