FISER: A Feature-Based Detection System for Person Interactions

Yung Chun Chang, Pi Hua Chuang, Chien Chin Chen, Wen Lian Hsu

Research output: Contribution to journalArticle

Abstract

Discovering the interactions between the persons mentioned in a set of topic documents can help readers construct the background of the topic and facilitate document comprehension. To discover person interactions, we need a detection method that can identify text segments containing information about the interactions. Information extraction algorithms then analyze the segments to extract interaction tuples and construct a network of person interaction. In this article, we define interaction detection as a classification problem. The proposed interaction detection method, called feature-based interactive segment recognizer (FISER), exploits 19 features covering syntactic, context-dependent, and semantic information in text to detect intra-clausal and inter-clausal interactive segments in topic documents. Empirical evaluations demonstrate that FISER outperformed many well-known relation extraction and protein-protein interaction detection methods on identifying interactive segments in topic documents. In addition, the precision, recall, and F1-score of the best feature combination are 72.9%, 55.8%, and 63.2%, respectively.

Original languageEnglish
Pages (from-to)656-679
JournalComputational Intelligence
Volume33
Issue number4
DOIs
Publication statusPublished - Nov 2017
Externally publishedYes

Fingerprint

Person
Proteins
Syntactics
Interaction
Semantics
Information Extraction
Protein-protein Interaction
Classification Problems
Covering
Dependent
Evaluation
Demonstrate
Text

Keywords

  • Information extraction
  • Interactive segment
  • Person interaction
  • Relation extraction
  • Text mining

ASJC Scopus subject areas

  • Computational Mathematics
  • Artificial Intelligence

Cite this

FISER : A Feature-Based Detection System for Person Interactions. / Chang, Yung Chun; Chuang, Pi Hua; Chen, Chien Chin; Hsu, Wen Lian.

In: Computational Intelligence, Vol. 33, No. 4, 11.2017, p. 656-679.

Research output: Contribution to journalArticle

Chang, Yung Chun ; Chuang, Pi Hua ; Chen, Chien Chin ; Hsu, Wen Lian. / FISER : A Feature-Based Detection System for Person Interactions. In: Computational Intelligence. 2017 ; Vol. 33, No. 4. pp. 656-679.
@article{73cdca8c06ad4814842d5b901e0f5acd,
title = "FISER: A Feature-Based Detection System for Person Interactions",
abstract = "Discovering the interactions between the persons mentioned in a set of topic documents can help readers construct the background of the topic and facilitate document comprehension. To discover person interactions, we need a detection method that can identify text segments containing information about the interactions. Information extraction algorithms then analyze the segments to extract interaction tuples and construct a network of person interaction. In this article, we define interaction detection as a classification problem. The proposed interaction detection method, called feature-based interactive segment recognizer (FISER), exploits 19 features covering syntactic, context-dependent, and semantic information in text to detect intra-clausal and inter-clausal interactive segments in topic documents. Empirical evaluations demonstrate that FISER outperformed many well-known relation extraction and protein-protein interaction detection methods on identifying interactive segments in topic documents. In addition, the precision, recall, and F1-score of the best feature combination are 72.9{\%}, 55.8{\%}, and 63.2{\%}, respectively.",
keywords = "Information extraction, Interactive segment, Person interaction, Relation extraction, Text mining",
author = "Chang, {Yung Chun} and Chuang, {Pi Hua} and Chen, {Chien Chin} and Hsu, {Wen Lian}",
year = "2017",
month = "11",
doi = "10.1111/coin.12108",
language = "English",
volume = "33",
pages = "656--679",
journal = "Computational Intelligence",
issn = "0824-7935",
publisher = "Wiley-Blackwell",
number = "4",

}

TY - JOUR

T1 - FISER

T2 - A Feature-Based Detection System for Person Interactions

AU - Chang, Yung Chun

AU - Chuang, Pi Hua

AU - Chen, Chien Chin

AU - Hsu, Wen Lian

PY - 2017/11

Y1 - 2017/11

N2 - Discovering the interactions between the persons mentioned in a set of topic documents can help readers construct the background of the topic and facilitate document comprehension. To discover person interactions, we need a detection method that can identify text segments containing information about the interactions. Information extraction algorithms then analyze the segments to extract interaction tuples and construct a network of person interaction. In this article, we define interaction detection as a classification problem. The proposed interaction detection method, called feature-based interactive segment recognizer (FISER), exploits 19 features covering syntactic, context-dependent, and semantic information in text to detect intra-clausal and inter-clausal interactive segments in topic documents. Empirical evaluations demonstrate that FISER outperformed many well-known relation extraction and protein-protein interaction detection methods on identifying interactive segments in topic documents. In addition, the precision, recall, and F1-score of the best feature combination are 72.9%, 55.8%, and 63.2%, respectively.

AB - Discovering the interactions between the persons mentioned in a set of topic documents can help readers construct the background of the topic and facilitate document comprehension. To discover person interactions, we need a detection method that can identify text segments containing information about the interactions. Information extraction algorithms then analyze the segments to extract interaction tuples and construct a network of person interaction. In this article, we define interaction detection as a classification problem. The proposed interaction detection method, called feature-based interactive segment recognizer (FISER), exploits 19 features covering syntactic, context-dependent, and semantic information in text to detect intra-clausal and inter-clausal interactive segments in topic documents. Empirical evaluations demonstrate that FISER outperformed many well-known relation extraction and protein-protein interaction detection methods on identifying interactive segments in topic documents. In addition, the precision, recall, and F1-score of the best feature combination are 72.9%, 55.8%, and 63.2%, respectively.

KW - Information extraction

KW - Interactive segment

KW - Person interaction

KW - Relation extraction

KW - Text mining

UR - http://www.scopus.com/inward/record.url?scp=85011706103&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85011706103&partnerID=8YFLogxK

U2 - 10.1111/coin.12108

DO - 10.1111/coin.12108

M3 - Article

AN - SCOPUS:85011706103

VL - 33

SP - 656

EP - 679

JO - Computational Intelligence

JF - Computational Intelligence

SN - 0824-7935

IS - 4

ER -