Multi-domain Dialogue State Tracking as Dynamic Knowledge Graph Enhanced Question Answering

Abstract

Multi-domain dialogue state tracking (DST) is a critical component for conversational AI systems. The domain ontology (i.e., specification of domains, slots, and values) of a conversational AI system is generally incomplete, making the capability for DST models to generalize to new slots, values, and domains during inference imperative. In this paper, we propose to model multi-domain DST as a question answering problem, referred to as Dialogue State Tracking via Question Answering (DSTQA). Within DSTQA, each turn generates a question asking for the value of a (domain, slot) pair, thus making it naturally extensible to unseen domains, slots, and values. Additionally, we use a dynamically-evolving knowledge graph to explicitly learn relationships between (domain, slot) pairs. Our model has a 5.80% and 12.21% relative improvement over the current state-of-the-art model on MultiWOZ 2.0 and MultiWOZ 2.1 datasets, respectively. Additionally, our model consistently outperforms the state-of-the-art model in domain adaptation settings. (Code is released at https://github.com/alexa/dstqa )

References in corpus (2)

• Bidirectional Attention Flow for Machine Comprehension
• KG^2: Learning to Reason Science Exam Questions with Contextual Knowledge Graph Embeddings

Cited by in corpus (24)

• Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Survey
• A Simple Language Model for Task-Oriented Dialogue
• SOLOIST: Building Task Bots at Scale with Transfer Learning and Machine Teaching
• UBAR: Towards Fully End-to-End Task-Oriented Dialog Systems with GPT-2
• MultiWOZ 2.2 : A Dialogue Dataset with Additional Annotation Corrections and State Tracking Baselines
• Efficient Context and Schema Fusion Networks for Multi-Domain Dialogue State Tracking
• MultiWOZ 2.3: A multi-domain task-oriented dialogue dataset enhanced with annotation corrections and co-reference annotation
• A Survey on Dialog Management: Recent Advances and Challenges
• Jointly Optimizing State Operation Prediction and Value Generation for Dialogue State Tracking
• From Machine Reading Comprehension to Dialogue State Tracking: Bridging the Gap
• MinTL: Minimalist Transfer Learning for Task-Oriented Dialogue Systems
• Find or Classify? Dual Strategy for Slot-Value Predictions on Multi-Domain Dialog State Tracking
• A Contextual Hierarchical Attention Network with Adaptive Objective for Dialogue State Tracking
• SUMBT+LaRL: Effective Multi-domain End-to-end Neural Task-oriented Dialog System
• Multi-Domain Dialogue State Tracking based on State Graph
• Zero-shot Generalization in Dialog State Tracking through Generative Question Answering
• Leveraging Slot Descriptions for Zero-Shot Cross-Domain Dialogue State Tracking
• Pretraining the Noisy Channel Model for Task-Oriented Dialogue
• Zero-Shot Dialogue State Tracking via Cross-Task Transfer
• UniConv: A Unified Conversational Neural Architecture for Multi-domain Task-oriented Dialogues
• Modeling Long Context for Task-Oriented Dialogue State Generation
• Neural Dialogue State Tracking with Temporally Expressive Networks
• Coreference Augmentation for Multi-Domain Task-Oriented Dialogue State Tracking
• Dialogue State Tracking with a Language Model using Schema-Driven Prompting