CUED Publications database

Multi-domain dialog state tracking using recurrent neural networks

Mrkšić, N and Séaghdha, DO and Thomson, B and Gašić, M and Su, PH and Vandyke, D and Wen, TH and Young, S (2015) Multi-domain dialog state tracking using recurrent neural networks. In: UNSPECIFIED pp. 794-799..

Full text not available from this repository.

Abstract

© 2015 Association for Computational Linguistics. Dialog state tracking is a key component of many modern dialog systems, most of which are designed with a single, welldefined 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 domainspecific 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.

Item Type: Conference or Workshop Item (UNSPECIFIED)
Subjects: UNSPECIFIED
Divisions: Div F > Machine Intelligence
Depositing User: Cron Job
Date Deposited: 17 Jul 2017 19:41
Last Modified: 23 Nov 2017 03:33
DOI: