Multi-domain Dialog State Tracking using Recurrent Neural Networks

06/23/2015
by   Nikola Mrkšić, et al.
0

Dialog state tracking is a key component of many modern dialog systems, most of which are designed with a single, well-defined domain in mind. This paper shows that dialog data drawn from different dialog domains can be used to train a general belief tracking model which can operate across all of these domains, exhibiting superior performance to each of the domain-specific models. We propose a training procedure which uses out-of-domain data to initialise belief tracking models for entirely new domains. This procedure leads to improvements in belief tracking performance regardless of the amount of in-domain data available for training the model.

READ FULL TEXT

page 1

page 2

page 3

page 4

07/24/2015

YARBUS : Yet Another Rule Based belief Update System

We introduce a new rule based system for belief tracking in dialog syste...
02/20/2017

The Dialog State Tracking Challenge with Bayesian Approach

Generative model has been one of the most common approaches for solving ...
05/13/2018

Zero-Shot Dialog Generation with Cross-Domain Latent Actions

This paper introduces zero-shot dialog generation (ZSDG), as a step towa...
11/26/2018

Learning Latent Beliefs and Performing Epistemic Reasoning for Efficient and Meaningful Dialog Management

Many dialogue management frameworks allow the system designer to directl...
06/08/2019

Domain Adaptive Dialog Generation via Meta Learning

Domain adaptation is an essential task in dialog system building because...
06/01/2021

Preview, Attend and Review: Schema-Aware Curriculum Learning for Multi-Domain Dialog State Tracking

Existing dialog state tracking (DST) models are trained with dialog data...
09/17/2020

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

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