Learning to Select Knowledge for Response Generation in Dialog Systems

Abstract

End-to-end neural models for intelligent dialogue systems suffer from the problem of generating uninformative responses. Various methods were proposed to generate more informative responses by leveraging external knowledge. However, few previous work has focused on selecting appropriate knowledge in the learning process. The inappropriate selection of knowledge could prohibit the model from learning to make full use of the knowledge. Motivated by this, we propose an end-to-end neural model which employs a novel knowledge selection mechanism where both prior and posterior distributions over knowledge are used to facilitate knowledge selection. Specifically, a posterior distribution over knowledge is inferred from both utterances and responses, and it ensures the appropriate selection of knowledge during the training process. Meanwhile, a prior distribution, which is inferred from utterances only, is used to approximate the posterior distribution so that appropriate knowledge can be selected even without responses during the inference process. Compared with the previous work, our model can better incorporate appropriate knowledge in response generation. Experiments on both automatic and human evaluation verify the superiority of our model over previous baselines.

References in corpus (6)

• Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
• Categorical Reparameterization with Gumbel-Softmax
• A Neural Conversational Model
• Wizard of Wikipedia: Knowledge-Powered Conversational agents
• Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoders
• Flexible End-to-End Dialogue System for Knowledge Grounded Conversation

Cited by in corpus (6)

• Zero-Resource Knowledge-Grounded Dialogue Generation
• Learning to Detect Relevant Contexts and Knowledge for Response Selection in Retrieval-based Dialogue Systems
• Are Pre-trained Language Models Knowledgeable to Ground Open Domain Dialogues?
• Knowledge-Grounded Dialogue Generation with Pre-trained Language Models
• Know More about Each Other: Evolving Dialogue Strategy via Compound Assessment
• Controllable Dialogue Generation with Disentangled Multi-grained Style Specification and Attribute Consistency Reward