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

by   Shuyang Li, et al.

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 state-of-the-art on the MultiWOZ 2.1 dataset.


page 1

page 2

page 3

page 4


MA-DST: Multi-Attention Based Scalable Dialog State Tracking

Task oriented dialog agents provide a natural language interface for use...

Annotation Inconsistency and Entity Bias in MultiWOZ

MultiWOZ is one of the most popular multi-domain task-oriented dialog da...

Natural Language Generation at Scale: A Case Study for Open Domain Question Answering

Current approaches to Natural Language Generation (NLG) focus on domain-...

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

Multi-domain dialogue state tracking (DST) is a critical component for c...

Likelihood Ratios and Generative Classifiers for Unsupervised Out-of-Domain Detection In Task Oriented Dialog

The task of identifying out-of-domain (OOD) input examples directly at t...

A Slot Is Not Built in One Utterance: Spoken Language Dialogs with Sub-Slots

A slot value might be provided segment by segment over multiple-turn int...

Zero-shot Multi-Domain Dialog State Tracking Using Descriptive Rules

In this work, we present a framework for incorporating descriptive logic...