Investigating LSTM for punctuation prediction

Kaituo Xu; Lei Xie; Kaisheng Yao

doi:10.1109/ISCSLP.2016.7918492

Investigating LSTM for punctuation prediction

Kaituo Xu, Lei Xie, Kaisheng Yao

School of Computer Science

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

24 Scopus citations

Abstract

We present a neural network based punctuation prediction method using Long Short-Term Memory (LSTM) network. The proposed method uses bidirectional LSTM to encode both the past and future observation as its inputs. It models the dependency between input features and output labels through multiple layers. We also empirically study the impacts of modeling the dependency between output labels. Our results show that using a deep bi-directional LSTM is able to achieve state-of-the-art performance in punctuation prediction.

Original language	English
Title of host publication	Proceedings of 2016 10th International Symposium on Chinese Spoken Language Processing, ISCSLP 2016
Editors	Hsin-Min Wang, Qingzhi Hou, Yuan Wei, Tan Lee, Jianguo Wei, Lei Xie, Hui Feng, Jianwu Dang, Jianwu Dang
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781509042937
DOIs	https://doi.org/10.1109/ISCSLP.2016.7918492
State	Published - 2 May 2017
Event	10th International Symposium on Chinese Spoken Language Processing, ISCSLP 2016 - Tianjin, China Duration: 17 Oct 2016 → 20 Oct 2016

Publication series

Name	Proceedings of 2016 10th International Symposium on Chinese Spoken Language Processing, ISCSLP 2016

Conference

Conference	10th International Symposium on Chinese Spoken Language Processing, ISCSLP 2016
Country/Territory	China
City	Tianjin
Period	17/10/16 → 20/10/16

Keywords

Conditional random field
Long short term memory
Punctuation prediction
Recurrent neural network

Access to Document

10.1109/ISCSLP.2016.7918492

Cite this

Xu, K., Xie, L., & Yao, K. (2017). Investigating LSTM for punctuation prediction. In H.-M. Wang, Q. Hou, Y. Wei, T. Lee, J. Wei, L. Xie, H. Feng, J. Dang, & J. Dang (Eds.), Proceedings of 2016 10th International Symposium on Chinese Spoken Language Processing, ISCSLP 2016 Article 7918492 (Proceedings of 2016 10th International Symposium on Chinese Spoken Language Processing, ISCSLP 2016). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ISCSLP.2016.7918492

Xu, Kaituo ; Xie, Lei ; Yao, Kaisheng. / Investigating LSTM for punctuation prediction. Proceedings of 2016 10th International Symposium on Chinese Spoken Language Processing, ISCSLP 2016. editor / Hsin-Min Wang ; Qingzhi Hou ; Yuan Wei ; Tan Lee ; Jianguo Wei ; Lei Xie ; Hui Feng ; Jianwu Dang ; Jianwu Dang. Institute of Electrical and Electronics Engineers Inc., 2017. (Proceedings of 2016 10th International Symposium on Chinese Spoken Language Processing, ISCSLP 2016).

@inproceedings{b35ad3690a8c4f038d02a74850d2f46c,

title = "Investigating LSTM for punctuation prediction",

abstract = "We present a neural network based punctuation prediction method using Long Short-Term Memory (LSTM) network. The proposed method uses bidirectional LSTM to encode both the past and future observation as its inputs. It models the dependency between input features and output labels through multiple layers. We also empirically study the impacts of modeling the dependency between output labels. Our results show that using a deep bi-directional LSTM is able to achieve state-of-the-art performance in punctuation prediction.",

keywords = "Conditional random field, Long short term memory, Punctuation prediction, Recurrent neural network",

author = "Kaituo Xu and Lei Xie and Kaisheng Yao",

note = "Publisher Copyright: {\textcopyright} 2016 IEEE.; 10th International Symposium on Chinese Spoken Language Processing, ISCSLP 2016 ; Conference date: 17-10-2016 Through 20-10-2016",

year = "2017",

month = may,

day = "2",

doi = "10.1109/ISCSLP.2016.7918492",

language = "英语",

series = "Proceedings of 2016 10th International Symposium on Chinese Spoken Language Processing, ISCSLP 2016",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

editor = "Hsin-Min Wang and Qingzhi Hou and Yuan Wei and Tan Lee and Jianguo Wei and Lei Xie and Hui Feng and Jianwu Dang and Jianwu Dang",

booktitle = "Proceedings of 2016 10th International Symposium on Chinese Spoken Language Processing, ISCSLP 2016",

}

Xu, K, Xie, L & Yao, K 2017, Investigating LSTM for punctuation prediction. in H-M Wang, Q Hou, Y Wei, T Lee, J Wei, L Xie, H Feng, J Dang & J Dang (eds), Proceedings of 2016 10th International Symposium on Chinese Spoken Language Processing, ISCSLP 2016., 7918492, Proceedings of 2016 10th International Symposium on Chinese Spoken Language Processing, ISCSLP 2016, Institute of Electrical and Electronics Engineers Inc., 10th International Symposium on Chinese Spoken Language Processing, ISCSLP 2016, Tianjin, China, 17/10/16. https://doi.org/10.1109/ISCSLP.2016.7918492

Investigating LSTM for punctuation prediction. / Xu, Kaituo; Xie, Lei; Yao, Kaisheng.
Proceedings of 2016 10th International Symposium on Chinese Spoken Language Processing, ISCSLP 2016. ed. / Hsin-Min Wang; Qingzhi Hou; Yuan Wei; Tan Lee; Jianguo Wei; Lei Xie; Hui Feng; Jianwu Dang; Jianwu Dang. Institute of Electrical and Electronics Engineers Inc., 2017. 7918492 (Proceedings of 2016 10th International Symposium on Chinese Spoken Language Processing, ISCSLP 2016).

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

TY - GEN

T1 - Investigating LSTM for punctuation prediction

AU - Xu, Kaituo

AU - Xie, Lei

AU - Yao, Kaisheng

PY - 2017/5/2

Y1 - 2017/5/2

N2 - We present a neural network based punctuation prediction method using Long Short-Term Memory (LSTM) network. The proposed method uses bidirectional LSTM to encode both the past and future observation as its inputs. It models the dependency between input features and output labels through multiple layers. We also empirically study the impacts of modeling the dependency between output labels. Our results show that using a deep bi-directional LSTM is able to achieve state-of-the-art performance in punctuation prediction.

AB - We present a neural network based punctuation prediction method using Long Short-Term Memory (LSTM) network. The proposed method uses bidirectional LSTM to encode both the past and future observation as its inputs. It models the dependency between input features and output labels through multiple layers. We also empirically study the impacts of modeling the dependency between output labels. Our results show that using a deep bi-directional LSTM is able to achieve state-of-the-art performance in punctuation prediction.

KW - Conditional random field

KW - Long short term memory

KW - Punctuation prediction

KW - Recurrent neural network

UR - http://www.scopus.com/inward/record.url?scp=85020222174&partnerID=8YFLogxK

U2 - 10.1109/ISCSLP.2016.7918492

DO - 10.1109/ISCSLP.2016.7918492

M3 - 会议稿件

AN - SCOPUS:85020222174

T3 - Proceedings of 2016 10th International Symposium on Chinese Spoken Language Processing, ISCSLP 2016

BT - Proceedings of 2016 10th International Symposium on Chinese Spoken Language Processing, ISCSLP 2016

A2 - Wang, Hsin-Min

A2 - Hou, Qingzhi

A2 - Wei, Yuan

A2 - Lee, Tan

A2 - Wei, Jianguo

A2 - Xie, Lei

A2 - Feng, Hui

A2 - Dang, Jianwu

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 10th International Symposium on Chinese Spoken Language Processing, ISCSLP 2016

Y2 - 17 October 2016 through 20 October 2016

ER -

Xu K, Xie L, Yao K. Investigating LSTM for punctuation prediction. In Wang HM, Hou Q, Wei Y, Lee T, Wei J, Xie L, Feng H, Dang J, Dang J, editors, Proceedings of 2016 10th International Symposium on Chinese Spoken Language Processing, ISCSLP 2016. Institute of Electrical and Electronics Engineers Inc. 2017. 7918492. (Proceedings of 2016 10th International Symposium on Chinese Spoken Language Processing, ISCSLP 2016). doi: 10.1109/ISCSLP.2016.7918492

Investigating LSTM for punctuation prediction

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this