Convolution neural network based syntactic and semantic aware paraphrase identification

Xiang Zhang; Wenge Rong; Jingshuang Liu; Chuan Tian; Zhang Xiong

doi:10.1109/IJCNN.2017.7966116

Convolution neural network based syntactic and semantic aware paraphrase identification

Xiang Zhang
, Wenge Rong
, Jingshuang Liu
, Chuan Tian
, Zhang Xiong

School of Computer Science and Engineering

Beihang University

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

11 Scopus citations

Abstract

Paraphrase identification is a fundamental task in natural language process areas. During the process of fulfilling this challenge, different features are exploited. Semantically equivalence and syntactic similarity are of the most importance. Apart from advance feature extraction, deep learning based models are also proven their promising in natural language process jobs. As a result in this research, we adopted an interactive representation to modelling the relationship between two sentences not only on word level, but also on phrase and sentence level by employing convolution neural network to conduct paraphrase identification by using semantic and syntactic features at the same time. The experimental study on commonly used MSRP has shown the proposed method's promising potential.

Original language	English
Title of host publication	2017 International Joint Conference on Neural Networks, IJCNN 2017 - Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	2158-2163
Number of pages	6
ISBN (Electronic)	9781509061815
DOIs	https://doi.org/10.1109/IJCNN.2017.7966116
State	Published - 30 Jun 2017
Event	2017 International Joint Conference on Neural Networks, IJCNN 2017 - Anchorage, United States Duration: 14 May 2017 → 19 May 2017

Publication series

Name	Proceedings of the International Joint Conference on Neural Networks
Volume	2017-May

Conference

Conference	2017 International Joint Conference on Neural Networks, IJCNN 2017
Country/Territory	United States
City	Anchorage
Period	14/05/17 → 19/05/17

Keywords

Convolution Neural Network
Paraphrase Identification
Semantics
Syntactics

Access to Document

10.1109/IJCNN.2017.7966116

Cite this

Zhang, X., Rong, W., Liu, J., Tian, C., & Xiong, Z. (2017). Convolution neural network based syntactic and semantic aware paraphrase identification. In 2017 International Joint Conference on Neural Networks, IJCNN 2017 - Proceedings (pp. 2158-2163). Article 7966116 (Proceedings of the International Joint Conference on Neural Networks; Vol. 2017-May). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IJCNN.2017.7966116

Zhang, Xiang ; Rong, Wenge ; Liu, Jingshuang et al. / Convolution neural network based syntactic and semantic aware paraphrase identification. 2017 International Joint Conference on Neural Networks, IJCNN 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2017. pp. 2158-2163 (Proceedings of the International Joint Conference on Neural Networks).

@inproceedings{db2c9c1083de4d23953b5d2b4fbec862,

title = "Convolution neural network based syntactic and semantic aware paraphrase identification",

abstract = "Paraphrase identification is a fundamental task in natural language process areas. During the process of fulfilling this challenge, different features are exploited. Semantically equivalence and syntactic similarity are of the most importance. Apart from advance feature extraction, deep learning based models are also proven their promising in natural language process jobs. As a result in this research, we adopted an interactive representation to modelling the relationship between two sentences not only on word level, but also on phrase and sentence level by employing convolution neural network to conduct paraphrase identification by using semantic and syntactic features at the same time. The experimental study on commonly used MSRP has shown the proposed method's promising potential.",

keywords = "Convolution Neural Network, Paraphrase Identification, Semantics, Syntactics",

author = "Xiang Zhang and Wenge Rong and Jingshuang Liu and Chuan Tian and Zhang Xiong",

note = "Publisher Copyright: {\textcopyright} 2017 IEEE.; 2017 International Joint Conference on Neural Networks, IJCNN 2017 ; Conference date: 14-05-2017 Through 19-05-2017",

year = "2017",

month = jun,

day = "30",

doi = "10.1109/IJCNN.2017.7966116",

language = "英语",

series = "Proceedings of the International Joint Conference on Neural Networks",

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

pages = "2158--2163",

booktitle = "2017 International Joint Conference on Neural Networks, IJCNN 2017 - Proceedings",

address = "美国",

}

Zhang, X, Rong, W, Liu, J, Tian, C & Xiong, Z 2017, Convolution neural network based syntactic and semantic aware paraphrase identification. in 2017 International Joint Conference on Neural Networks, IJCNN 2017 - Proceedings., 7966116, Proceedings of the International Joint Conference on Neural Networks, vol. 2017-May, Institute of Electrical and Electronics Engineers Inc., pp. 2158-2163, 2017 International Joint Conference on Neural Networks, IJCNN 2017, Anchorage, United States, 14/05/17. https://doi.org/10.1109/IJCNN.2017.7966116

Convolution neural network based syntactic and semantic aware paraphrase identification. / Zhang, Xiang; Rong, Wenge; Liu, Jingshuang et al.
2017 International Joint Conference on Neural Networks, IJCNN 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2017. p. 2158-2163 7966116 (Proceedings of the International Joint Conference on Neural Networks; Vol. 2017-May).

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

TY - GEN

T1 - Convolution neural network based syntactic and semantic aware paraphrase identification

AU - Zhang, Xiang

AU - Rong, Wenge

AU - Liu, Jingshuang

AU - Tian, Chuan

AU - Xiong, Zhang

PY - 2017/6/30

Y1 - 2017/6/30

N2 - Paraphrase identification is a fundamental task in natural language process areas. During the process of fulfilling this challenge, different features are exploited. Semantically equivalence and syntactic similarity are of the most importance. Apart from advance feature extraction, deep learning based models are also proven their promising in natural language process jobs. As a result in this research, we adopted an interactive representation to modelling the relationship between two sentences not only on word level, but also on phrase and sentence level by employing convolution neural network to conduct paraphrase identification by using semantic and syntactic features at the same time. The experimental study on commonly used MSRP has shown the proposed method's promising potential.

AB - Paraphrase identification is a fundamental task in natural language process areas. During the process of fulfilling this challenge, different features are exploited. Semantically equivalence and syntactic similarity are of the most importance. Apart from advance feature extraction, deep learning based models are also proven their promising in natural language process jobs. As a result in this research, we adopted an interactive representation to modelling the relationship between two sentences not only on word level, but also on phrase and sentence level by employing convolution neural network to conduct paraphrase identification by using semantic and syntactic features at the same time. The experimental study on commonly used MSRP has shown the proposed method's promising potential.

KW - Convolution Neural Network

KW - Paraphrase Identification

KW - Semantics

KW - Syntactics

UR - https://www.scopus.com/pages/publications/85030990495

U2 - 10.1109/IJCNN.2017.7966116

DO - 10.1109/IJCNN.2017.7966116

M3 - 会议稿件

AN - SCOPUS:85030990495

T3 - Proceedings of the International Joint Conference on Neural Networks

SP - 2158

EP - 2163

BT - 2017 International Joint Conference on Neural Networks, IJCNN 2017 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2017 International Joint Conference on Neural Networks, IJCNN 2017

Y2 - 14 May 2017 through 19 May 2017

ER -

Zhang X, Rong W, Liu J, Tian C, Xiong Z. Convolution neural network based syntactic and semantic aware paraphrase identification. In 2017 International Joint Conference on Neural Networks, IJCNN 2017 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2017. p. 2158-2163. 7966116. (Proceedings of the International Joint Conference on Neural Networks). doi: 10.1109/IJCNN.2017.7966116

Convolution neural network based syntactic and semantic aware paraphrase identification

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this