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

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 DS...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2021-01
Main Authors: Li, Shuyang, Cao, Jin, Sridhar, Mukund, Zhu, Henghui, Shang-Wen, Li, Hamza, Wael, McAuley, Julian
Format: Article
Language:English
Subjects:
Domains
Model accuracy
Ontology
Questions
Sentences
Tracking
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:2331-8422