A Conditional Variational Framework for Dialog Generation

Abstract

Deep latent variable models have been shown to facilitate the response generation for open-domain dialog systems. However, these latent variables are highly randomized, leading to uncontrollable generated responses. In this paper, we propose a framework allowing conditional response generation based on specific attributes. These attributes can be either manually assigned or automatically detected. Moreover, the dialog states for both speakers are modeled separately in order to reflect personal features. We validate this framework on two different scenarios, where the attribute refers to genericness and sentiment states respectively. The experiment result testified the potential of our model, where meaningful responses can be generated in accordance with the specified attributes.

Accepted by ACL2017

References in corpus (6)

• Sequence to Sequence Learning with Neural Networks
• Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
• Sequence Transduction with Recurrent Neural Networks
• deltaBLEU: A Discriminative Metric for Generation Tasks with Intrinsically Diverse Targets
• A Neural Network Approach to Context-Sensitive Generation of Conversational Responses
• A Hybrid Convolutional Variational Autoencoder for Text Generation

Cited by in corpus (12)

• Topic-Guided Variational Autoencoders for Text Generation
• Deep Learning Based Chatbot Models
• A Survey of Natural Language Generation Techniques with a Focus on Dialogue Systems - Past, Present and Future Directions
• An Adversarial Approach to High-Quality, Sentiment-Controlled Neural Dialogue Generation
• Structured Variational Inference for Simulating Populations of Radio Galaxies
• Policy-Driven Neural Response Generation for Knowledge-Grounded Dialogue Systems
• Deep Active Learning for Dialogue Generation
• Generating Multiple Diverse Responses for Short-Text Conversation
• Why Do Neural Response Generation Models Prefer Universal Replies?
• Better Conversations by Modeling,Filtering,and Optimizing for Coherence and Diversity
• Incorporating Relevant Knowledge in Context Modeling and Response Generation
• Diversifying Topic-Coherent Response Generation for Natural Multi-turn Conversations