On identifying cited texts for citances and classifying their discourse facets by classification techniques

Jen Yuan Yeh, Tien Yu Hsu, Cheng Jung Tsai, Pei Cheng Cheng, Jung Yi Lin

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Creating the faceted citation summary of a research paper involves identifying cited texts for citation sentences (i.e., citances), classifying their discourse facets, and generating a structured summary from the cited texts. This paper proposes a supervised method for the first two tasks by classification techniques. The first task uses binary classification to distinguish relevant pairs of citances and reference sentences from irrelevant pairs. The second task applies multi-class classification to assign one of the predefined discourse facets to relevant pairs of the first task. The proposed method is evaluated using the CL-SciSumm 2016 datasets and found to be competitive in producing superior results compared to state-of-the-art methods.

Original languageEnglish
Pages (from-to)61-86
Number of pages26
JournalJournal of Information Science and Engineering
Volume35
Issue number1
DOIs
Publication statusPublished - 2019 Jan 1

Fingerprint

discourse

All Science Journal Classification (ASJC) codes

  • Software
  • Human-Computer Interaction
  • Hardware and Architecture
  • Library and Information Sciences
  • Computational Theory and Mathematics

Cite this

@article{b079f275202e4cb89a8561a974bd5354,
title = "On identifying cited texts for citances and classifying their discourse facets by classification techniques",
abstract = "Creating the faceted citation summary of a research paper involves identifying cited texts for citation sentences (i.e., citances), classifying their discourse facets, and generating a structured summary from the cited texts. This paper proposes a supervised method for the first two tasks by classification techniques. The first task uses binary classification to distinguish relevant pairs of citances and reference sentences from irrelevant pairs. The second task applies multi-class classification to assign one of the predefined discourse facets to relevant pairs of the first task. The proposed method is evaluated using the CL-SciSumm 2016 datasets and found to be competitive in producing superior results compared to state-of-the-art methods.",
author = "Yeh, {Jen Yuan} and Hsu, {Tien Yu} and Tsai, {Cheng Jung} and Cheng, {Pei Cheng} and Lin, {Jung Yi}",
year = "2019",
month = "1",
day = "1",
doi = "10.6688/JISE.201901_35(1).0004",
language = "English",
volume = "35",
pages = "61--86",
journal = "Journal of Information Science and Engineering",
issn = "1016-2364",
publisher = "Institute of Information Science",
number = "1",

}

On identifying cited texts for citances and classifying their discourse facets by classification techniques. / Yeh, Jen Yuan; Hsu, Tien Yu; Tsai, Cheng Jung; Cheng, Pei Cheng; Lin, Jung Yi.

In: Journal of Information Science and Engineering, Vol. 35, No. 1, 01.01.2019, p. 61-86.

Research output: Contribution to journalArticle

TY - JOUR

T1 - On identifying cited texts for citances and classifying their discourse facets by classification techniques

AU - Yeh, Jen Yuan

AU - Hsu, Tien Yu

AU - Tsai, Cheng Jung

AU - Cheng, Pei Cheng

AU - Lin, Jung Yi

PY - 2019/1/1

Y1 - 2019/1/1

N2 - Creating the faceted citation summary of a research paper involves identifying cited texts for citation sentences (i.e., citances), classifying their discourse facets, and generating a structured summary from the cited texts. This paper proposes a supervised method for the first two tasks by classification techniques. The first task uses binary classification to distinguish relevant pairs of citances and reference sentences from irrelevant pairs. The second task applies multi-class classification to assign one of the predefined discourse facets to relevant pairs of the first task. The proposed method is evaluated using the CL-SciSumm 2016 datasets and found to be competitive in producing superior results compared to state-of-the-art methods.

AB - Creating the faceted citation summary of a research paper involves identifying cited texts for citation sentences (i.e., citances), classifying their discourse facets, and generating a structured summary from the cited texts. This paper proposes a supervised method for the first two tasks by classification techniques. The first task uses binary classification to distinguish relevant pairs of citances and reference sentences from irrelevant pairs. The second task applies multi-class classification to assign one of the predefined discourse facets to relevant pairs of the first task. The proposed method is evaluated using the CL-SciSumm 2016 datasets and found to be competitive in producing superior results compared to state-of-the-art methods.

UR - http://www.scopus.com/inward/record.url?scp=85063953427&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85063953427&partnerID=8YFLogxK

U2 - 10.6688/JISE.201901_35(1).0004

DO - 10.6688/JISE.201901_35(1).0004

M3 - Article

AN - SCOPUS:85063953427

VL - 35

SP - 61

EP - 86

JO - Journal of Information Science and Engineering

JF - Journal of Information Science and Engineering

SN - 1016-2364

IS - 1

ER -