Home > Research > Publications & Outputs > Encoding Word Confusion Networks with Recurrent...

Research

Links

Text available via DOI:

View graph of relations

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

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review

Published

Standard

Encoding Word Confusion Networks with Recurrent Neural Networks for Dialog State Tracking. / Jagfeld, Glorianna; Vu, Ngoc Thang.
Proceedings of the Workshop on Speech-Centric Natural Language Processing . Stroudsburg, PA : Association for Computational Linguistics, 2017. p. 10-17.

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review

Harvard

Jagfeld, G & Vu, NT 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, Stroudsburg, PA , pp. 10-17, Speech-Centric Natural Language Processing Workshop, co-located with EMNLP 2017, Copenhagen, Denmark, 7/09/17. https://doi.org/10.18653/v1/W17-4602

APA

Jagfeld, G., & Vu, N. T. (2017). Encoding Word Confusion Networks with Recurrent Neural Networks for Dialog State Tracking. In Proceedings of the Workshop on Speech-Centric Natural Language Processing (pp. 10-17). Association for Computational Linguistics. https://doi.org/10.18653/v1/W17-4602

Vancouver

Jagfeld G, Vu NT. Encoding Word Confusion Networks with Recurrent Neural Networks for Dialog State Tracking. In Proceedings of the Workshop on Speech-Centric Natural Language Processing . Stroudsburg, PA : Association for Computational Linguistics. 2017. p. 10-17 doi: 10.18653/v1/W17-4602

Author

Jagfeld, Glorianna ; Vu, Ngoc Thang. / Encoding Word Confusion Networks with Recurrent Neural Networks for Dialog State Tracking. Proceedings of the Workshop on Speech-Centric Natural Language Processing . Stroudsburg, PA : Association for Computational Linguistics, 2017. pp. 10-17

Bibtex

@inproceedings{449f24e9871448689b5e2748d3017d86,
title = "Encoding Word Confusion Networks with Recurrent Neural Networks for Dialog State Tracking",
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.",
author = "Glorianna Jagfeld and Vu, {Ngoc Thang}",
year = "2017",
month = sep,
day = "7",
doi = "10.18653/v1/W17-4602",
language = "English",
isbn = "9781945626920",
pages = "10--17",
booktitle = "Proceedings of the Workshop on Speech-Centric Natural Language Processing",
publisher = "Association for Computational Linguistics",
note = "Speech-Centric Natural Language Processing Workshop, co-located with EMNLP 2017, SCNLP ; Conference date: 07-09-2017",
url = "https://speechnlp.github.io/2017/",

}

RIS

TY - GEN

T1 - Encoding Word Confusion Networks with Recurrent Neural Networks for Dialog State Tracking

AU - Jagfeld, Glorianna

AU - Vu, Ngoc Thang

PY - 2017/9/7

Y1 - 2017/9/7

N2 - 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.

AB - 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.

U2 - 10.18653/v1/W17-4602

DO - 10.18653/v1/W17-4602

M3 - Conference contribution/Paper

SN - 9781945626920

SP - 10

EP - 17

BT - Proceedings of the Workshop on Speech-Centric Natural Language Processing

PB - Association for Computational Linguistics

CY - Stroudsburg, PA

T2 - Speech-Centric Natural Language Processing Workshop, co-located with EMNLP 2017

Y2 - 7 September 2017

ER -