Spectral decomposition method of dialog state tracking via collective matrix factorization

by   Julien Perez, et al.

The task of dialog management is commonly decomposed into two sequential subtasks: dialog state tracking and dialog policy learning. In an end-to-end dialog system, the aim of dialog state tracking is to accurately estimate the true dialog state from noisy observations produced by the speech recognition and the natural language understanding modules. The state tracking task is primarily meant to support a dialog policy. From a probabilistic perspective, this is achieved by maintaining a posterior distribution over hidden dialog states composed of a set of context dependent variables. Once a dialog policy is learned, it strives to select an optimal dialog act given the estimated dialog state and a defined reward function. This paper introduces a novel method of dialog state tracking based on a bilinear algebric decomposition model that provides an efficient inference schema through collective matrix factorization. We evaluate the proposed approach on the second Dialog State Tracking Challenge (DSTC-2) dataset and we show that the proposed tracker gives encouraging results compared to the state-of-the-art trackers that participated in this standard benchmark. Finally, we show that the prediction schema is computationally efficient in comparison to the previous approaches.


page 1

page 2

page 3

page 4


Dialog state tracking, a machine reading approach using Memory Network

In an end-to-end dialog system, the aim of dialog state tracking is to a...

Show Us the Way: Learning to Manage Dialog from Demonstrations

We present our submission to the End-to-End Multi-Domain Dialog Challeng...

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...

The Dialog State Tracking Challenge with Bayesian Approach

Generative model has been one of the most common approaches for solving ...

A Probabilistic Framework for Representing Dialog Systems and Entropy-Based Dialog Management through Dynamic Stochastic State Evolution

In this paper, we present a probabilistic framework for goal-driven spok...

A Hybrid Task-Oriented Dialog System with Domain and Task Adaptive Pretraining

This paper describes our submission for the End-to-end Multi-domain Task...

Robust Dialog State Tracking for Large Ontologies

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

Please sign up or login with your details

Forgot password? Click here to reset