Disfluency detection using a noisy channel model and a deep neural language model

Paria Jamshid Lou; Mark Johnson

doi:10.18653/v1/P17-2087

Disfluency detection using a noisy channel model and a deep neural language model

Paria Jamshid Lou, Mark Johnson

School of Computing

Research output: Chapter in Book/Report/Conference proceeding › Conference proceeding contribution › peer-review

28 Citations (Scopus)

41 Downloads (Pure)

Abstract

This paper presents a model for disfluency detection in spontaneous speech transcripts called LSTM Noisy Channel Model. The model uses a Noisy Channel Model (NCM) to generate n-best candidate disfluency analyses and a Long Short-Term Memory (LSTM) language model to score the underlying fluent sentences of each analysis. The LSTM language model scores, along with other features, are used in a MaxEnt reranker to identify the most plausible analysis. We show that using an LSTM language model in the reranking process of noisy channel disfluency model improves the state-of-the-art in disfluency detection.

Original language	English
Title of host publication	ACL 2017 - The 55th Annual Meeting of the Association for Computational Linguistics
Subtitle of host publication	Proceedings of the Conference, Vol. 2 (Short Papers)
Editors	Regina Barzilay, Min-Yen Kan
Place of Publication	Stroudsburg PA
Publisher	Association for Computational Linguistics (ACL)
Pages	547-553
Number of pages	7
Volume	2
ISBN (Electronic)	9781945626760
DOIs	https://doi.org/10.18653/v1/P17-2087
Publication status	Published - 2017
Event	55th Annual Meeting of the Association for Computational Linguistics, ACL 2017 - Vancouver, Canada Duration: 30 Jul 2017 → 4 Aug 2017

Conference

Conference	55th Annual Meeting of the Association for Computational Linguistics, ACL 2017
Country/Territory	Canada
City	Vancouver
Period	30/07/17 → 4/08/17

Bibliographical note

Copyright the Publisher. Version archived for private and non-commercial use with the permission of the author/s and according to publisher conditions. For further rights please contact the publisher.

Access to Document

10.18653/v1/P17-2087

Publisher version (open access)Final published version, 212 KBLicence: CC BY

Cite this

Jamshid Lou, P., & Johnson, M. (2017). Disfluency detection using a noisy channel model and a deep neural language model. In R. Barzilay, & M.-Y. Kan (Eds.), ACL 2017 - The 55th Annual Meeting of the Association for Computational Linguistics: Proceedings of the Conference, Vol. 2 (Short Papers) (Vol. 2, pp. 547-553). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/P17-2087

Jamshid Lou, Paria ; Johnson, Mark. / Disfluency detection using a noisy channel model and a deep neural language model. ACL 2017 - The 55th Annual Meeting of the Association for Computational Linguistics: Proceedings of the Conference, Vol. 2 (Short Papers). editor / Regina Barzilay ; Min-Yen Kan. Vol. 2 Stroudsburg PA : Association for Computational Linguistics (ACL), 2017. pp. 547-553

@inproceedings{7a52c3bc461540798c96d280a3b86adb,

title = "Disfluency detection using a noisy channel model and a deep neural language model",

abstract = "This paper presents a model for disfluency detection in spontaneous speech transcripts called LSTM Noisy Channel Model. The model uses a Noisy Channel Model (NCM) to generate n-best candidate disfluency analyses and a Long Short-Term Memory (LSTM) language model to score the underlying fluent sentences of each analysis. The LSTM language model scores, along with other features, are used in a MaxEnt reranker to identify the most plausible analysis. We show that using an LSTM language model in the reranking process of noisy channel disfluency model improves the state-of-the-art in disfluency detection.",

author = "{Jamshid Lou}, Paria and Mark Johnson",

note = "Copyright the Publisher. Version archived for private and non-commercial use with the permission of the author/s and according to publisher conditions. For further rights please contact the publisher.; 55th Annual Meeting of the Association for Computational Linguistics, ACL 2017 ; Conference date: 30-07-2017 Through 04-08-2017",

year = "2017",

doi = "10.18653/v1/P17-2087",

language = "English",

volume = "2",

pages = "547--553",

editor = "Regina Barzilay and Min-Yen Kan",

booktitle = "ACL 2017 - The 55th Annual Meeting of the Association for Computational Linguistics",

publisher = "Association for Computational Linguistics (ACL)",

}

Jamshid Lou, P & Johnson, M 2017, Disfluency detection using a noisy channel model and a deep neural language model. in R Barzilay & M-Y Kan (eds), ACL 2017 - The 55th Annual Meeting of the Association for Computational Linguistics: Proceedings of the Conference, Vol. 2 (Short Papers). vol. 2, Association for Computational Linguistics (ACL), Stroudsburg PA, pp. 547-553, 55th Annual Meeting of the Association for Computational Linguistics, ACL 2017, Vancouver, Canada, 30/07/17. https://doi.org/10.18653/v1/P17-2087

Disfluency detection using a noisy channel model and a deep neural language model. / Jamshid Lou, Paria; Johnson, Mark.
ACL 2017 - The 55th Annual Meeting of the Association for Computational Linguistics: Proceedings of the Conference, Vol. 2 (Short Papers). ed. / Regina Barzilay; Min-Yen Kan. Vol. 2 Stroudsburg PA: Association for Computational Linguistics (ACL), 2017. p. 547-553.

Research output: Chapter in Book/Report/Conference proceeding › Conference proceeding contribution › peer-review

TY - GEN

T1 - Disfluency detection using a noisy channel model and a deep neural language model

AU - Jamshid Lou, Paria

AU - Johnson, Mark

N1 - Copyright the Publisher. Version archived for private and non-commercial use with the permission of the author/s and according to publisher conditions. For further rights please contact the publisher.

PY - 2017

Y1 - 2017

N2 - This paper presents a model for disfluency detection in spontaneous speech transcripts called LSTM Noisy Channel Model. The model uses a Noisy Channel Model (NCM) to generate n-best candidate disfluency analyses and a Long Short-Term Memory (LSTM) language model to score the underlying fluent sentences of each analysis. The LSTM language model scores, along with other features, are used in a MaxEnt reranker to identify the most plausible analysis. We show that using an LSTM language model in the reranking process of noisy channel disfluency model improves the state-of-the-art in disfluency detection.

AB - This paper presents a model for disfluency detection in spontaneous speech transcripts called LSTM Noisy Channel Model. The model uses a Noisy Channel Model (NCM) to generate n-best candidate disfluency analyses and a Long Short-Term Memory (LSTM) language model to score the underlying fluent sentences of each analysis. The LSTM language model scores, along with other features, are used in a MaxEnt reranker to identify the most plausible analysis. We show that using an LSTM language model in the reranking process of noisy channel disfluency model improves the state-of-the-art in disfluency detection.

UR - http://www.scopus.com/inward/record.url?scp=85040554204&partnerID=8YFLogxK

U2 - 10.18653/v1/P17-2087

DO - 10.18653/v1/P17-2087

M3 - Conference proceeding contribution

AN - SCOPUS:85040554204

VL - 2

SP - 547

EP - 553

BT - ACL 2017 - The 55th Annual Meeting of the Association for Computational Linguistics

A2 - Barzilay, Regina

A2 - Kan, Min-Yen

PB - Association for Computational Linguistics (ACL)

CY - Stroudsburg PA

T2 - 55th Annual Meeting of the Association for Computational Linguistics, ACL 2017

Y2 - 30 July 2017 through 4 August 2017

ER -

Jamshid Lou P, Johnson M. Disfluency detection using a noisy channel model and a deep neural language model. In Barzilay R, Kan MY, editors, ACL 2017 - The 55th Annual Meeting of the Association for Computational Linguistics: Proceedings of the Conference, Vol. 2 (Short Papers). Vol. 2. Stroudsburg PA: Association for Computational Linguistics (ACL). 2017. p. 547-553 doi: 10.18653/v1/P17-2087

Disfluency detection using a noisy channel model and a deep neural language model

Abstract

Conference

Bibliographical note

Access to Document

Other files and links

Fingerprint

Cite this