Encoding Word Confusion Networks with Recurrent Neural Networks for Dialog State Tracking

Jagfeld, Glorianna and Vu, Ngoc Thang (2017) Encoding Word Confusion Networks with Recurrent Neural Networks for Dialog State Tracking. In: Proceedings of the Workshop on Speech-Centric Natural Language Processing. Association for Computational Linguistics, DNK, pp. 10-17. ISBN 9781945626920

Full text not available from this repository.

Abstract

This paper presents our novel method to encode word confusion networks, which can represent a rich hypothesis space of automatic speech recognition systems, via recurrent neural networks. We demonstrate the utility of our approach for the task of dialog state tracking in spoken dialog systems that relies on automatic speech recognition output. Encoding confusion networks outperforms encoding the best hypothesis of the automatic speech recognition in a neural system for dialog state tracking on the well-known second Dialog State Tracking Challenge dataset.

Item Type: Contribution in Book/Report/Proceedings
Departments: Faculty of Health and Medicine > Health Research
ID Code: 130541
Deposited By: ep_importer_pure
Deposited On: 23 Jan 2019 10:25
Refereed?: Yes
Published?: Published
Last Modified: 03 Oct 2019 09:41
URI: https://eprints.lancs.ac.uk/id/eprint/130541

Actions (login required)

View Item View Item