Zero-shot Generalization in Dialog State Tracking through Generative Question Answering

Abstract

Dialog State Tracking (DST), an integral part of modern dialog systems, aims to track user preferences and constraints (slots) in task-oriented dialogs. In real-world settings with constantly changing services, DST systems must generalize to new domains and unseen slot types. Existing methods for DST do not generalize well to new slot names and many require known ontologies of slot types and values for inference. We introduce a novel ontology-free framework that supports natural language queries for unseen constraints and slots in multi-domain task-oriented dialogs. Our approach is based on generative question-answering using a conditional language model pre-trained on substantive English sentences. Our model improves joint goal accuracy in zero-shot domain adaptation settings by up to 9% (absolute) over the previous state-of-the-art on the MultiWOZ 2.1 dataset.

Accepted as a Long Paper at EACL 2021

References in corpus (14)

• Sequence to Sequence Learning with Neural Networks
• Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
• Language Models are Few-Shot Learners
• The Natural Language Decathlon: Multitask Learning as Question Answering
• Building a Conversational Agent Overnight with Dialogue Self-Play
• A Simple Language Model for Task-Oriented Dialogue
• SOLOIST: Building Task Bots at Scale with Transfer Learning and Machine Teaching
• Multi-domain Dialogue State Tracking as Dynamic Knowledge Graph Enhanced Question Answering
• The Eighth Dialog System Technology Challenge
• Unifying Question Answering, Text Classification, and Regression via Span Extraction
• End-to-End Synthetic Data Generation for Domain Adaptation of Question Answering Systems
• From Machine Reading Comprehension to Dialogue State Tracking: Bridging the Gap
• TripPy: A Triple Copy Strategy for Value Independent Neural Dialog State Tracking
• MA-DST: Multi-Attention Based Scalable Dialog State Tracking

Cited by in corpus (3)

• SGD-X: A Benchmark for Robust Generalization in Schema-Guided Dialogue Systems
• Modeling Text-visual Mutual Dependency for Multi-modal Dialog Generation
• NeuralWOZ: Learning to Collect Task-Oriented Dialogue via Model-Based Simulation