SPIRIT: A Tree Kernel-Based Method for Topic Person Interaction Detection

Yung Chun Chang, Chien Chin Chen, Wen Lian Hsu

研究成果: 雜誌貢獻文章

2 引文 (Scopus)

摘要

The development of a topic in a set of topic documents is constituted by a series of person interactions at a specific time and place. Knowing the interactions of the persons mentioned in these documents is helpful for readers to better comprehend the documents. In this paper, we propose a topic person interaction detection method called SPIRIT, which classifies the text segments in a set of topic documents that convey person interactions. We design the rich interactive tree structure to represent syntactic, context, and semantic information of text, and this structure is incorporated into a tree-based convolution kernel to identify interactive segments. Experiment results based on real world topics demonstrate that the proposed rich interactive tree structure effectively detects the topic person interactions and that our method outperforms many well-known relation extraction and protein-protein interaction methods.
原文英語
文章編號7468551
頁(從 - 到)2494-2507
頁數14
期刊IEEE Transactions on Knowledge and Data Engineering
28
發行號9
DOIs
出版狀態已發佈 - 九月 1 2016
對外發佈Yes

指紋

Proteins
Syntactics
Convolution
Semantics
Experiments

ASJC Scopus subject areas

  • Information Systems
  • Computer Science Applications
  • Computational Theory and Mathematics

引用此文

SPIRIT : A Tree Kernel-Based Method for Topic Person Interaction Detection. / Chang, Yung Chun; Chen, Chien Chin; Hsu, Wen Lian.

於: IEEE Transactions on Knowledge and Data Engineering, 卷 28, 編號 9, 7468551, 01.09.2016, p. 2494-2507.

研究成果: 雜誌貢獻文章

@article{13e21366ed194202aebc24e8061e1995,
title = "SPIRIT: A Tree Kernel-Based Method for Topic Person Interaction Detection",
abstract = "The development of a topic in a set of topic documents is constituted by a series of person interactions at a specific time and place. Knowing the interactions of the persons mentioned in these documents is helpful for readers to better comprehend the documents. In this paper, we propose a topic person interaction detection method called SPIRIT, which classifies the text segments in a set of topic documents that convey person interactions. We design the rich interactive tree structure to represent syntactic, context, and semantic information of text, and this structure is incorporated into a tree-based convolution kernel to identify interactive segments. Experiment results based on real world topics demonstrate that the proposed rich interactive tree structure effectively detects the topic person interactions and that our method outperforms many well-known relation extraction and protein-protein interaction methods.",
keywords = "classification, natural language processing, Text mining",
author = "Chang, {Yung Chun} and Chen, {Chien Chin} and Hsu, {Wen Lian}",
year = "2016",
month = "9",
day = "1",
doi = "10.1109/TKDE.2016.2566620",
language = "English",
volume = "28",
pages = "2494--2507",
journal = "IEEE Transactions on Knowledge and Data Engineering",
issn = "1041-4347",
publisher = "IEEE Computer Society",
number = "9",

}

TY - JOUR

T1 - SPIRIT

T2 - A Tree Kernel-Based Method for Topic Person Interaction Detection

AU - Chang, Yung Chun

AU - Chen, Chien Chin

AU - Hsu, Wen Lian

PY - 2016/9/1

Y1 - 2016/9/1

N2 - The development of a topic in a set of topic documents is constituted by a series of person interactions at a specific time and place. Knowing the interactions of the persons mentioned in these documents is helpful for readers to better comprehend the documents. In this paper, we propose a topic person interaction detection method called SPIRIT, which classifies the text segments in a set of topic documents that convey person interactions. We design the rich interactive tree structure to represent syntactic, context, and semantic information of text, and this structure is incorporated into a tree-based convolution kernel to identify interactive segments. Experiment results based on real world topics demonstrate that the proposed rich interactive tree structure effectively detects the topic person interactions and that our method outperforms many well-known relation extraction and protein-protein interaction methods.

AB - The development of a topic in a set of topic documents is constituted by a series of person interactions at a specific time and place. Knowing the interactions of the persons mentioned in these documents is helpful for readers to better comprehend the documents. In this paper, we propose a topic person interaction detection method called SPIRIT, which classifies the text segments in a set of topic documents that convey person interactions. We design the rich interactive tree structure to represent syntactic, context, and semantic information of text, and this structure is incorporated into a tree-based convolution kernel to identify interactive segments. Experiment results based on real world topics demonstrate that the proposed rich interactive tree structure effectively detects the topic person interactions and that our method outperforms many well-known relation extraction and protein-protein interaction methods.

KW - classification

KW - natural language processing

KW - Text mining

UR - http://www.scopus.com/inward/record.url?scp=84982121559&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84982121559&partnerID=8YFLogxK

U2 - 10.1109/TKDE.2016.2566620

DO - 10.1109/TKDE.2016.2566620

M3 - Article

AN - SCOPUS:84982121559

VL - 28

SP - 2494

EP - 2507

JO - IEEE Transactions on Knowledge and Data Engineering

JF - IEEE Transactions on Knowledge and Data Engineering

SN - 1041-4347

IS - 9

M1 - 7468551

ER -