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

TL;DR

This paper presents an ontology-free, generative question-answering approach for dialog state tracking that enhances zero-shot domain adaptation, enabling better handling of unseen slots and constraints in multi-domain dialogs.

Contribution

It introduces a novel generative QA framework for DST that does not rely on predefined ontologies, improving zero-shot generalization in multi-domain dialog systems.

Findings

Achieves up to 9% absolute improvement in joint goal accuracy on MultiWOZ 2.1.

Supports natural language queries for unseen constraints and slots.

Operates effectively without known ontologies for slot types and values.

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.