Zero-Resource Knowledge-Grounded Dialogue Generation

Abstract

While neural conversation models have shown great potentials towards generating informative and engaging responses via introducing external knowledge, learning such a model often requires knowledge-grounded dialogues that are difficult to obtain. To overcome the data challenge and reduce the cost of building a knowledge-grounded dialogue system, we explore the problem under a zero-resource setting by assuming no context-knowledge-response triples are needed for training. To this end, we propose representing the knowledge that bridges a context and a response and the way that the knowledge is expressed as latent variables, and devise a variational approach that can effectively estimate a generation model from a dialogue corpus and a knowledge corpus that are independent with each other. Evaluation results on three benchmarks of knowledge-grounded dialogue generation indicate that our model can achieve comparable performance with state-of-the-art methods that rely on knowledge-grounded dialogues for training, and exhibits a good generalization ability over different topics and different datasets.

Accepted by NeurIPS 2020

References in corpus (13)

• Sequence to Sequence Learning with Neural Networks
• Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
• Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
• XLNet: Generalized Autoregressive Pretraining for Language Understanding
• Towards a Human-like Open-Domain Chatbot
• Conversational AI: The Science Behind the Alexa Prize
• Learning Disentangled Representations with Semi-Supervised Deep Generative Models
• Sequential Latent Knowledge Selection for Knowledge-Grounded Dialogue
• DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generation
• Low-Resource Knowledge-Grounded Dialogue Generation
• Disentangling Factors of Variation Using Few Labels
• Learning to Select Knowledge for Response Generation in Dialog Systems
• Neural Response Generation with Meta-Words

Cited by in corpus (6)

• Are Pre-trained Language Models Knowledgeable to Ground Open Domain Dialogues?
• Knowledge-Grounded Dialogue Generation with Pre-trained Language Models
• ZRIGF: An Innovative Multimodal Framework for Zero-Resource Image-Grounded Dialogue Generation
• Resource Constrained Dialog Policy Learning via Differentiable Inductive Logic Programming
• StyleDGPT: Stylized Response Generation with Pre-trained Language Models
• Variational Learning for Unsupervised Knowledge Grounded Dialogs