Low-Resource Knowledge-Grounded Dialogue Generation

Abstract

Responding with knowledge has been recognized as an important capability for an intelligent conversational agent. Yet knowledge-grounded dialogues, as training data for learning such a response generation model, are difficult to obtain. Motivated by the challenge in practice, we consider knowledge-grounded dialogue generation under a natural assumption that only limited training examples are available. In such a low-resource setting, we devise a disentangled response decoder in order to isolate parameters that depend on knowledge-grounded dialogues from the entire generation model. By this means, the major part of the model can be learned from a large number of ungrounded dialogues and unstructured documents, while the remaining small parameters can be well fitted using the limited training examples. Evaluation results on two benchmarks indicate that with only 1/8 training data, our model can achieve the state-of-the-art performance and generalize well on out-of-domain knowledge.

Published in ICLR 2020

References in corpus (10)

• Auto-Encoding Variational Bayes
• Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
• Categorical Reparameterization with Gumbel-Softmax
• XLNet: Generalized Autoregressive Pretraining for Language Understanding
• A Neural Conversational Model
• MASS: Masked Sequence to Sequence Pre-training for Language Generation
• Topic Aware Neural Response Generation
• A Diversity-Promoting Objective Function for Neural Conversation Models
• Conversational AI: The Science Behind the Alexa Prize
• Disentangling Factors of Variation Using Few Labels

Cited by in corpus (17)

• Zero-Resource Knowledge-Grounded Dialogue Generation
• Learning to Detect Relevant Contexts and Knowledge for Response Selection in Retrieval-based Dialogue Systems
• Exploring Prompt-based Few-shot Learning for Grounded Dialog Generation
• Learning Retrieval Augmentation for Personalized Dialogue Generation
• BoB: BERT Over BERT for Training Persona-based Dialogue Models from Limited Personalized Data
• Are Pre-trained Language Models Knowledgeable to Ground Open Domain Dialogues?
• Meaningful Answer Generation of E-Commerce Question-Answering
• Conditional Text Generation for Harmonious Human-Machine Interaction
• Knowledge-Grounded Dialogue Generation with Pre-trained Language Models
• Retrieval Augmentation Reduces Hallucination in Conversation
• Difference-aware Knowledge Selection for Knowledge-grounded Conversation Generation
• Knowledge Enhanced Fine-Tuning for Better Handling Unseen Entities in Dialogue Generation
• Predict-then-Decide: A Predictive Approach for Wait or Answer Task in Dialogue Systems
• Maria: A Visual Experience Powered Conversational Agent
• StyleDGPT: Stylized Response Generation with Pre-trained Language Models
• Towards information-rich, logical text generation with knowledge-enhanced neural models
• A Three-Stage Learning Framework for Low-Resource Knowledge-Grounded Dialogue Generation