Sequential Latent Knowledge Selection for Knowledge-Grounded Dialogue
arXiv:2002.07510
Abstract
Knowledge-grounded dialogue is a task of generating an informative response based on both discourse context and external knowledge. As we focus on better modeling the knowledge selection in the multi-turn knowledge-grounded dialogue, we propose a sequential latent variable model as the first approach to this matter. The model named sequential knowledge transformer (SKT) can keep track of the prior and posterior distribution over knowledge; as a result, it can not only reduce the ambiguity caused from the diversity in knowledge selection of conversation but also better leverage the response information for proper choice of knowledge. Our experimental results show that the proposed model improves the knowledge selection accuracy and subsequently the performance of utterance generation. We achieve the new state-of-the-art performance on Wizard of Wikipedia (Dinan et al., 2019) as one of the most large-scale and challenging benchmarks. We further validate the effectiveness of our model over existing conversation methods in another knowledge-based dialogue Holl-E dataset (Moghe et al., 2018).
arXiv commentPublished in ICLR 2020 (Spotlight)
References in corpus (13)
- Categorical Reparameterization with Gumbel-Softmax
- The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables
- A Recurrent Latent Variable Model for Sequential Data
- Wizard of Wikipedia: Knowledge-Powered Conversational agents
- Regularizing Neural Networks by Penalizing Confident Output Distributions
- Personalizing Dialogue Agents: I have a dog, do you have pets too?
- Latent Alignment and Variational Attention
- ACUTE-EVAL: Improved Dialogue Evaluation with Optimized Questions and Multi-turn Comparisons
- Uncertainty-Aware Attention for Reliable Interpretation and Prediction
- Z-Forcing: Training Stochastic Recurrent Networks
- Efficient and Robust Question Answering from Minimal Context over Documents
- Conversing by Reading: Contentful Neural Conversation with On-demand Machine Reading
- Long and Diverse Text Generation with Planning-based Hierarchical Variational Model
Cited by in corpus (22)
- A Survey of Knowledge-Enhanced Text Generation
- Zero-Resource Knowledge-Grounded Dialogue Generation
- Semi-Supervised Variational Reasoning for Medical Dialogue Generation
- Efficient Retrieval Augmented Generation from Unstructured Knowledge for Task-Oriented Dialog
- PLATO-2: Towards Building an Open-Domain Chatbot via Curriculum Learning
- Search-Engine-augmented Dialogue Response Generation with Cheaply Supervised Query Production
- Conditional Text Generation for Harmonious Human-Machine Interaction
- A Unified Pre-training Framework for Conversational AI
- Retrieval Augmentation Reduces Hallucination in Conversation
- Knowledge-Grounded Dialogue Generation with Pre-trained Language Models
- A Probabilistic End-To-End Task-Oriented Dialog Model with Latent Belief States towards Semi-Supervised Learning
- Difference-aware Knowledge Selection for Knowledge-grounded Conversation Generation
- Knowledge Enhanced Fine-Tuning for Better Handling Unseen Entities in Dialogue Generation
- Variational Latent-State GPT for Semi-Supervised Task-Oriented Dialog Systems
- A Compare Aggregate Transformer for Understanding Document-grounded Dialogue
- Maria: A Visual Experience Powered Conversational Agent
- Towards information-rich, logical text generation with knowledge-enhanced neural models
- Increasing Faithfulness in Knowledge-Grounded Dialogue with Controllable Features
- Variational Learning for Unsupervised Knowledge Grounded Dialogs
- DIALKI: Knowledge Identification in Conversational Systems through Dialogue-Document Contextualization
- A Three-Stage Learning Framework for Low-Resource Knowledge-Grounded Dialogue Generation
- CAiRE in DialDoc21: Data Augmentation for Information-Seeking Dialogue System