Find or Classify? Dual Strategy for Slot-Value Predictions on Multi-Domain Dialog State Tracking

by   Jian-Guo Zhang, et al.
Zhejiang University
University of Illinois at Chicago

Dialog State Tracking (DST) is a core component in task-oriented dialog systems. Existing approaches for DST usually fall into two categories, i.e, the picklist-based and span-based. From one hand, the picklist-based methods perform classifications for each slot over a candidate-value list, under the condition that a pre-defined ontology is accessible. However, it is impractical in industry since it is hard to get full access to the ontology. On the other hand, the span-based methods track values for each slot through finding text spans in the dialog context. However, due to the diversity of value descriptions, it is hard to find a particular string in the dialog context. To mitigate these issues, this paper proposes a Dual Strategy for DST (DS-DST) to borrow advantages from both the picklist-based and span-based methods, by classifying over a picklist or finding values from a slot span. Empirical results show that DS-DST achieves the state-of-the-art scores in terms of joint accuracy, i.e., 51.2 ontology is accessible.


page 1

page 2

page 3

page 4


TripPy: A Triple Copy Strategy for Value Independent Neural Dialog State Tracking

Task-oriented dialog systems rely on dialog state tracking (DST) to moni...

Tracking of enriched dialog states for flexible conversational information access

Dialog state tracking (DST) is a crucial component in a task-oriented di...

Dialog State Tracking: A Neural Reading Comprehension Approach

Dialog state tracking is used to estimate the current belief state of a ...

Elastic CRFs for Open-ontology Slot Filling

Slot filling is a crucial component in task-oriented dialog systems, whi...

Robust Dialog State Tracking for Large Ontologies

The Dialog State Tracking Challenge 4 (DSTC 4) differentiates itself fro...

Span-ConveRT: Few-shot Span Extraction for Dialog with Pretrained Conversational Representations

We introduce Span-ConveRT, a light-weight model for dialog slot-filling ...

A Simple but Effective BERT Model for Dialog State Tracking on Resource-Limited Systems

In a task-oriented dialog system, the goal of dialog state tracking (DST...

Code Repositories


Official repository for "MMConv: An Environment for Multimodal Conversational Search across Multiple Domains"

view repo


Pytorch implementation of DS-DST paper (Zhang et al., 2019). (not official)

view repo

Please sign up or login with your details

Forgot password? Click here to reset