CUED Publications database

Word-based dialog state tracking with recurrent neural networks

Henderson, M and Thomson, B and Young, S (2014) Word-based dialog state tracking with recurrent neural networks. In: UNSPECIFIED pp. 292-299..

Full text not available from this repository.


© 2014 Association for Computational Linguistics. Recently discriminative methods for tracking the state of a spoken dialog have been shown to outperform traditional generative models. This paper presents a new wordbased tracking method which maps directly from the speech recognition results to the dialog state without using an explicit semantic decoder. The method is based on a recurrent neural network structure which is capable of generalising to unseen dialog state hypotheses, and which requires very little feature engineering. The method is evaluated on the second Dialog State Tracking Challenge (DSTC2) corpus and the results demonstrate consistently high performance across all of the metrics.

Item Type: Conference or Workshop Item (UNSPECIFIED)
Divisions: Div F > Machine Intelligence
Depositing User: Cron Job
Date Deposited: 17 Jul 2017 19:34
Last Modified: 07 Jun 2018 02:09