Generative Deep Neural Networks for Dialogue: A Short Review

Abstract

Researchers have recently started investigating deep neural networks for dialogue applications. In particular, generative sequence-to-sequence (Seq2Seq) models have shown promising results for unstructured tasks, such as word-level dialogue response generation. The hope is that such models will be able to leverage massive amounts of data to learn meaningful natural language representations and response generation strategies, while requiring a minimum amount of domain knowledge and hand-crafting. An important challenge is to develop models that can effectively incorporate dialogue context and generate meaningful and diverse responses. In support of this goal, we review recently proposed models based on generative encoder-decoder neural network architectures, and show that these models have better ability to incorporate long-term dialogue history, to model uncertainty and ambiguity in dialogue, and to generate responses with high-level compositional structure.

arXiv comment6 pages, 1 figure, 3 tables; NIPS 2016 workshop on Learning Methods for Dialogue

References in corpus (10)

• A Neural Conversational Model
• Deep Reinforcement Learning for Dialogue Generation
• Optimizing Dialogue Management with Reinforcement Learning: Experiments with the NJFun System
• A Diversity-Promoting Objective Function for Neural Conversation Models
• Neural Responding Machine for Short-Text Conversation
• A Network-based End-to-End Trainable Task-oriented Dialogue System
• Smart Reply: Automated Response Suggestion for Email
• Dialog-based Language Learning
• Learning End-to-End Goal-Oriented Dialog
• Learning from Real Users: Rating Dialogue Success with Neural Networks for Reinforcement Learning in Spoken Dialogue Systems

Cited by in corpus (25)

• Wizard of Wikipedia: Knowledge-Powered Conversational agents
• Adversarial Learning for Neural Dialogue Generation
• Personalizing Dialogue Agents: I have a dog, do you have pets too?
• Variational Transformers for Diverse Response Generation
• Emergent Multi-Agent Communication in the Deep Learning Era
• Attention over Parameters for Dialogue Systems
• Data Distillation for Controlling Specificity in Dialogue Generation
• Augmenting Transformers with KNN-Based Composite Memory for Dialogue
• Retrieve and Refine: Improved Sequence Generation Models For Dialogue
• MIRIAM: A Multimodal Chat-Based Interface for Autonomous Systems
• Robust Conversational AI with Grounded Text Generation
• Non-Autoregressive Neural Dialogue Generation
• A Repository of Conversational Datasets
• Transfer Learning for British Sign Language Modelling
• Towards a Metric for Automated Conversational Dialogue System Evaluation and Improvement
• MoEL: Mixture of Empathetic Listeners
• Teaching Machines to Converse
• Modeling Psychotherapy Dialogues with Kernelized Hashcode Representations: A Nonparametric Information-Theoretic Approach
• Empathetic Dialogue Generation with Pre-trained RoBERTa-GPT2 and External Knowledge
• Know Deeper: Knowledge-Conversation Cyclic Utilization Mechanism for Open-domain Dialogue Generation
• Is this Dialogue Coherent? Learning from Dialogue Acts and Entities
• Diversifying Topic-Coherent Response Generation for Natural Multi-turn Conversations
• Automatic Evaluation of Neural Personality-based Chatbots
• Response Selection for Multi-Party Conversations with Dynamic Topic Tracking
• Reinforced Natural Language Interfaces via Entropy Decomposition