Global-to-local Memory Pointer Networks for Task-Oriented Dialogue
arXiv:1901.04713
Abstract
End-to-end task-oriented dialogue is challenging since knowledge bases are usually large, dynamic and hard to incorporate into a learning framework. We propose the global-to-local memory pointer (GLMP) networks to address this issue. In our model, a global memory encoder and a local memory decoder are proposed to share external knowledge. The encoder encodes dialogue history, modifies global contextual representation, and generates a global memory pointer. The decoder first generates a sketch response with unfilled slots. Next, it passes the global memory pointer to filter the external knowledge for relevant information, then instantiates the slots via the local memory pointers. We empirically show that our model can improve copy accuracy and mitigate the common out-of-vocabulary problem. As a result, GLMP is able to improve over the previous state-of-the-art models in both simulated bAbI Dialogue dataset and human-human Stanford Multi-domain Dialogue dataset on automatic and human evaluation.
ICLR 2019
References in corpus (3)
Cited by in corpus (11)
- Survey of Hallucination in Natural Language Generation
- A Simple Language Model for Task-Oriented Dialogue
- UBAR: Towards Fully End-to-End Task-Oriented Dialog Systems with GPT-2
- Multi-hop Reading Comprehension across Multiple Documents by Reasoning over Heterogeneous Graphs
- Recent Advances and Challenges in Task-oriented Dialog System
- Neural Assistant: Joint Action Prediction, Response Generation, and Latent Knowledge Reasoning
- KECRS: Towards Knowledge-Enriched Conversational Recommendation System
- Entity-Consistent End-to-end Task-Oriented Dialogue System with KB Retriever
- MoEL: Mixture of Empathetic Listeners
- Multipurpose Intelligent Process Automation via Conversational Assistant
- Unsupervised Learning of KB Queries in Task-Oriented Dialogs