The role of cause-effect link within scientific paper

Mengyun Cao; Xiaoping Sun; Hai Zhuge

doi:10.1109/SKG.2016.013

The role of cause-effect link within scientific paper

Mengyun Cao, Xiaoping Sun, Hai Zhuge

Computer Science

Research output: Chapter in Book/Published conference output › Conference publication

Abstract

Semantic links within text play an important role in understanding text. Cause-effect link is one of the basic semantic links that represents logic order between representation components of text. The importance of cause-effect link has been recognized and investigated in linguistics, but it has not been accurately measured to support computing applications. This paper is to investigate the role of cause-effect link within scientific paper. Research is conducted along two paths: (1) Human observations: Professionals find cause-effect links within a set of given papers, and then observe the number, the distribution and the keywords coverage of cause-effect links within each paper. The statistical results show that cause-effect links cover 76% keywords within paper on average. (2) Automatically discover more cause-effect links within a set of papers by developing a pattern-based algorithm. The automatically discovered cause-effect links validate the properties drawn from human observations. Experiments show that the algorithm can extract more than 80% of manually labeled links, and the automatically extracted links contain 75% of keywords within paper on average.

Original language	English
Title of host publication	Proceedings - 2016 12th International Conference on Semantics, Knowledge and Grids, SKG 2016
Editors	Hai Zhuge, Xiaoping Sun
Place of Publication	Piscataway, NJ (US)
Publisher	IEEE
Pages	32-39
Number of pages	8
ISBN (Electronic)	978-1-5090-4795-6
DOIs	https://doi.org/10.1109/SKG.2016.013
Publication status	Published - 11 Jan 2017
Event	12th International Conference on Semantics, Knowledge and Grids, SKG 2016 - Beijing, China Duration: 15 Aug 2016 → 17 Aug 2016

Conference

Conference	12th International Conference on Semantics, Knowledge and Grids, SKG 2016
Country/Territory	China
City	Beijing
Period	15/08/16 → 17/08/16

Bibliographical note

-

Keywords

causal relation
cause-effect link
natural language understanding
semantic link
semantic link network

Access to Document

10.1109/SKG.2016.013

Cite this

@inproceedings{5f959524e7c6441099b971cf5b18c57e,

title = "The role of cause-effect link within scientific paper",

abstract = "Semantic links within text play an important role in understanding text. Cause-effect link is one of the basic semantic links that represents logic order between representation components of text. The importance of cause-effect link has been recognized and investigated in linguistics, but it has not been accurately measured to support computing applications. This paper is to investigate the role of cause-effect link within scientific paper. Research is conducted along two paths: (1) Human observations: Professionals find cause-effect links within a set of given papers, and then observe the number, the distribution and the keywords coverage of cause-effect links within each paper. The statistical results show that cause-effect links cover 76% keywords within paper on average. (2) Automatically discover more cause-effect links within a set of papers by developing a pattern-based algorithm. The automatically discovered cause-effect links validate the properties drawn from human observations. Experiments show that the algorithm can extract more than 80% of manually labeled links, and the automatically extracted links contain 75% of keywords within paper on average.",

keywords = "causal relation, cause-effect link, natural language understanding, semantic link, semantic link network",

author = "Mengyun Cao and Xiaoping Sun and Hai Zhuge",

note = "-; 12th International Conference on Semantics, Knowledge and Grids, SKG 2016 ; Conference date: 15-08-2016 Through 17-08-2016",

year = "2017",

month = jan,

day = "11",

doi = "10.1109/SKG.2016.013",

language = "English",

pages = "32--39",

editor = "Hai Zhuge and Xiaoping Sun",

booktitle = "Proceedings - 2016 12th International Conference on Semantics, Knowledge and Grids, SKG 2016",

publisher = "IEEE",

address = "United States",

}

Cao, M, Sun, X & Zhuge, H 2017, The role of cause-effect link within scientific paper. in H Zhuge & X Sun (eds), Proceedings - 2016 12th International Conference on Semantics, Knowledge and Grids, SKG 2016., 7815074, IEEE, Piscataway, NJ (US), pp. 32-39, 12th International Conference on Semantics, Knowledge and Grids, SKG 2016, Beijing, China, 15/08/16. https://doi.org/10.1109/SKG.2016.013

TY - GEN

T1 - The role of cause-effect link within scientific paper

AU - Cao, Mengyun

AU - Sun, Xiaoping

AU - Zhuge, Hai

N1 - -

PY - 2017/1/11

Y1 - 2017/1/11

N2 - Semantic links within text play an important role in understanding text. Cause-effect link is one of the basic semantic links that represents logic order between representation components of text. The importance of cause-effect link has been recognized and investigated in linguistics, but it has not been accurately measured to support computing applications. This paper is to investigate the role of cause-effect link within scientific paper. Research is conducted along two paths: (1) Human observations: Professionals find cause-effect links within a set of given papers, and then observe the number, the distribution and the keywords coverage of cause-effect links within each paper. The statistical results show that cause-effect links cover 76% keywords within paper on average. (2) Automatically discover more cause-effect links within a set of papers by developing a pattern-based algorithm. The automatically discovered cause-effect links validate the properties drawn from human observations. Experiments show that the algorithm can extract more than 80% of manually labeled links, and the automatically extracted links contain 75% of keywords within paper on average.

AB - Semantic links within text play an important role in understanding text. Cause-effect link is one of the basic semantic links that represents logic order between representation components of text. The importance of cause-effect link has been recognized and investigated in linguistics, but it has not been accurately measured to support computing applications. This paper is to investigate the role of cause-effect link within scientific paper. Research is conducted along two paths: (1) Human observations: Professionals find cause-effect links within a set of given papers, and then observe the number, the distribution and the keywords coverage of cause-effect links within each paper. The statistical results show that cause-effect links cover 76% keywords within paper on average. (2) Automatically discover more cause-effect links within a set of papers by developing a pattern-based algorithm. The automatically discovered cause-effect links validate the properties drawn from human observations. Experiments show that the algorithm can extract more than 80% of manually labeled links, and the automatically extracted links contain 75% of keywords within paper on average.

KW - causal relation

KW - cause-effect link

KW - natural language understanding

KW - semantic link

KW - semantic link network

UR - http://ieeexplore.ieee.org/document/7815074/

UR - http://www.scopus.com/inward/record.url?scp=85013344117&partnerID=8YFLogxK

U2 - 10.1109/SKG.2016.013

DO - 10.1109/SKG.2016.013

M3 - Conference publication

AN - SCOPUS:85013344117

SP - 32

EP - 39

BT - Proceedings - 2016 12th International Conference on Semantics, Knowledge and Grids, SKG 2016

A2 - Zhuge, Hai

A2 - Sun, Xiaoping

PB - IEEE

CY - Piscataway, NJ (US)

T2 - 12th International Conference on Semantics, Knowledge and Grids, SKG 2016

Y2 - 15 August 2016 through 17 August 2016

ER -

The role of cause-effect link within scientific paper

Abstract

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Automatic question answering based on single document

Ranking scientific articles in a dynamically evolving citation network

Summarization of related work through citations

Cite this