Efficient Context and Schema Fusion Networks for Multi-Domain Dialogue State Tracking

Abstract

Dialogue state tracking (DST) aims at estimating the current dialogue state given all the preceding conversation. For multi-domain DST, the data sparsity problem is a major obstacle due to increased numbers of state candidates and dialogue lengths. To encode the dialogue context efficiently, we utilize the previous dialogue state (predicted) and the current dialogue utterance as the input for DST. To consider relations among different domain-slots, the schema graph involving prior knowledge is exploited. In this paper, a novel context and schema fusion network is proposed to encode the dialogue context and schema graph by using internal and external attention mechanisms. Experiment results show that our approach can obtain new state-of-the-art performance of the open-vocabulary DST on both MultiWOZ 2.0 and MultiWOZ 2.1 benchmarks.

16 pages, 4 figures, 11 tables. Accepted to EMNLP 2020 Findings

References in corpus (6)

• Adam: A Method for Stochastic Optimization
• On the Properties of Neural Machine Translation: Encoder-Decoder Approaches
• Get To The Point: Summarization with Pointer-Generator Networks
• Multi-domain Dialogue State Tracking as Dynamic Knowledge Graph Enhanced Question Answering
• Non-Autoregressive Dialog State Tracking
• Efficient Dialogue State Tracking by Selectively Overwriting Memory

Cited by in corpus (10)

• Jointly Optimizing State Operation Prediction and Value Generation for Dialogue State Tracking
• Multi-Domain Dialogue State Tracking based on State Graph
• Preview, Attend and Review: Schema-Aware Curriculum Learning for Multi-Domain Dialog State Tracking
• A Probabilistic End-To-End Task-Oriented Dialog Model with Latent Belief States towards Semi-Supervised Learning
• Context-Sensitive Generation Network for Handing Unknown Slot Values in Dialogue State Tracking
• Decoupled Dialogue Modeling and Semantic Parsing for Multi-Turn Text-to-SQL
• ShadowGNN: Graph Projection Neural Network for Text-to-SQL Parser
• Comprehensive Study: How the Context Information of Different Granularity Affects Dialogue State Tracking?
• Ontology-Enhanced Slot Filling
• Amendable Generation for Dialogue State Tracking