Zero-Resource Knowledge-Grounded Dialogue Generation
arXiv:2008.12918
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.
arXiv commentAccepted by NeurIPS 2020
References in corpus (31)
- 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
- Categorical Reparameterization with Gumbel-Softmax
- XLNet: Generalized Autoregressive Pretraining for Language Understanding
- A Neural Conversational Model
- Wizard of Wikipedia: Knowledge-Powered Conversational agents
- How NOT To Evaluate Your Dialogue System: An Empirical Study of Unsupervised Evaluation Metrics for Dialogue Response Generation
- Deep Reinforcement Learning for Dialogue Generation
- Topic Aware Neural Response Generation
- Towards a Human-like Open-Domain Chatbot
- Phrase-Based & Neural Unsupervised Machine Translation
- Adversarial Learning for Neural Dialogue Generation
- Conversational AI: The Science Behind the Alexa Prize
- Unsupervised Machine Translation Using Monolingual Corpora Only
- Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoders
- Learning Disentangled Representations with Semi-Supervised Deep Generative Models
- Sequential Latent Knowledge Selection for Knowledge-Grounded Dialogue
- Emotional Chatting Machine: Emotional Conversation Generation with Internal and External Memory
- DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generation
- A Teacher-Student Framework for Zero-Resource Neural Machine Translation
- MeanSum: A Neural Model for Unsupervised Multi-document Abstractive Summarization
- Unsupervised Neural Machine Translation
- Low-Resource Knowledge-Grounded Dialogue Generation
- Disentangling Factors of Variation Using Few Labels
- Differentiable Perturb-and-Parse: Semi-Supervised Parsing with a Structured Variational Autoencoder
- Towards Explainable and Controllable Open Domain Dialogue Generation with Dialogue Acts
- Learning to Select Knowledge for Response Generation in Dialog Systems
- Triangular Architecture for Rare Language Translation
- A Dataset for Document Grounded Conversations
- 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