SPIRIT: A tree kernel-based method for topic person interaction detection (Extended abstract)

Yung Chun Chang; Chien Chin Chen; Wen Lian Hsu

doi:10.1109/ICDE.2017.13

SPIRIT: A tree kernel-based method for topic person interaction detection (Extended abstract)

Yung Chun Chang, Chien Chin Chen, Wen Lian Hsu

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

Abstract

In this paper, we investigate the interactions between topic persons to help readers construct the background knowledge of a topic. We proposed a rich interactive tree structure to represent syntactic, context, and semantic information of text, and this structure is incorporated into a treebased convolution kernel to identify segments that convey person interactions and further construct person interaction networks. Empirical evaluations demonstrate that the proposed method is effective in detecting and extracting the interactions between topic persons in the text, and outperforms other extraction approaches used for comparison. Furthermore, readers will be able to easily navigate through the topic persons of interest within the interaction networks, and further construct the background knowledge of the topic to facilitate comprehension.

Original language	English
Title of host publication	Proceedings - 2017 IEEE 33rd International Conference on Data Engineering, ICDE 2017
Publisher	IEEE Computer Society
Pages	13-14
Number of pages	2
ISBN (Electronic)	9781509065431
DOIs	https://doi.org/10.1109/ICDE.2017.13
Publication status	Published - May 16 2017
Externally published	Yes
Event	33rd IEEE International Conference on Data Engineering, ICDE 2017 - San Diego, United States Duration: Apr 19 2017 → Apr 22 2017

Conference

Conference	33rd IEEE International Conference on Data Engineering, ICDE 2017
Country	United States
City	San Diego
Period	4/19/17 → 4/22/17

Fingerprint

ASJC Scopus subject areas

Software
Signal Processing
Information Systems

Cite this

Chang, Y. C., Chen, C. C., & Hsu, W. L. (2017). SPIRIT: A tree kernel-based method for topic person interaction detection (Extended abstract). In Proceedings - 2017 IEEE 33rd International Conference on Data Engineering, ICDE 2017 (pp. 13-14). [7929909] IEEE Computer Society. https://doi.org/10.1109/ICDE.2017.13

SPIRIT : A tree kernel-based method for topic person interaction detection (Extended abstract). / Chang, Yung Chun; Chen, Chien Chin; Hsu, Wen Lian.

Proceedings - 2017 IEEE 33rd International Conference on Data Engineering, ICDE 2017. IEEE Computer Society, 2017. p. 13-14 7929909.

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

Chang, YC, Chen, CC & Hsu, WL 2017, SPIRIT: A tree kernel-based method for topic person interaction detection (Extended abstract). in Proceedings - 2017 IEEE 33rd International Conference on Data Engineering, ICDE 2017., 7929909, IEEE Computer Society, pp. 13-14, 33rd IEEE International Conference on Data Engineering, ICDE 2017, San Diego, United States, 4/19/17. https://doi.org/10.1109/ICDE.2017.13

@inproceedings{c68d34aed89a4130808c599fd7545f85,

title = "SPIRIT: A tree kernel-based method for topic person interaction detection (Extended abstract)",

abstract = "In this paper, we investigate the interactions between topic persons to help readers construct the background knowledge of a topic. We proposed a rich interactive tree structure to represent syntactic, context, and semantic information of text, and this structure is incorporated into a treebased convolution kernel to identify segments that convey person interactions and further construct person interaction networks. Empirical evaluations demonstrate that the proposed method is effective in detecting and extracting the interactions between topic persons in the text, and outperforms other extraction approaches used for comparison. Furthermore, readers will be able to easily navigate through the topic persons of interest within the interaction networks, and further construct the background knowledge of the topic to facilitate comprehension.",

author = "Chang, {Yung Chun} and Chen, {Chien Chin} and Hsu, {Wen Lian}",

year = "2017",

month = may

day = "16",

doi = "10.1109/ICDE.2017.13",

language = "English",

pages = "13--14",

booktitle = "Proceedings - 2017 IEEE 33rd International Conference on Data Engineering, ICDE 2017",

publisher = "IEEE Computer Society",

address = "United States",

note = "33rd IEEE International Conference on Data Engineering, ICDE 2017 ; Conference date: 19-04-2017 Through 22-04-2017",

}

TY - GEN

T1 - SPIRIT

T2 - 33rd IEEE International Conference on Data Engineering, ICDE 2017

AU - Chang, Yung Chun

AU - Chen, Chien Chin

AU - Hsu, Wen Lian

PY - 2017/5/16

Y1 - 2017/5/16

N2 - In this paper, we investigate the interactions between topic persons to help readers construct the background knowledge of a topic. We proposed a rich interactive tree structure to represent syntactic, context, and semantic information of text, and this structure is incorporated into a treebased convolution kernel to identify segments that convey person interactions and further construct person interaction networks. Empirical evaluations demonstrate that the proposed method is effective in detecting and extracting the interactions between topic persons in the text, and outperforms other extraction approaches used for comparison. Furthermore, readers will be able to easily navigate through the topic persons of interest within the interaction networks, and further construct the background knowledge of the topic to facilitate comprehension.

AB - In this paper, we investigate the interactions between topic persons to help readers construct the background knowledge of a topic. We proposed a rich interactive tree structure to represent syntactic, context, and semantic information of text, and this structure is incorporated into a treebased convolution kernel to identify segments that convey person interactions and further construct person interaction networks. Empirical evaluations demonstrate that the proposed method is effective in detecting and extracting the interactions between topic persons in the text, and outperforms other extraction approaches used for comparison. Furthermore, readers will be able to easily navigate through the topic persons of interest within the interaction networks, and further construct the background knowledge of the topic to facilitate comprehension.

UR - http://www.scopus.com/inward/record.url?scp=85021249385&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85021249385&partnerID=8YFLogxK

U2 - 10.1109/ICDE.2017.13

DO - 10.1109/ICDE.2017.13

M3 - Conference contribution

AN - SCOPUS:85021249385

SP - 13

EP - 14

BT - Proceedings - 2017 IEEE 33rd International Conference on Data Engineering, ICDE 2017

PB - IEEE Computer Society

Y2 - 19 April 2017 through 22 April 2017

ER -

Access to Document

10.1109/ICDE.2017.13