Document Cohesion Flow: Striving towards Coherence

Scott A. Crossley; Mihai Dascalu; Stefan Trausan-Matu; Laura K. Allen; Danielle S. McNamara

Document Cohesion Flow: Striving towards Coherence

Scott A. Crossley
, Mihai Dascalu
, Stefan Trausan-Matu
, Laura K. Allen
, Danielle S. McNamara

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

Abstract

Text cohesion is an important element of discourse processing. This paper presents a new approach to modeling, quantifying, and visualizing text cohesion using automated cohesion flow indices that capture semantic links among paragraphs. Cohesion flow is calculated by applying Cohesion Network Analysis, a combination of semantic distances, Latent Semantic Analysis, and Latent Dirichlet Allocation, as well as Social Network Analysis. Experiments performed on 315 timed essays indicated that cohesion flow indices are significantly correlated with human ratings of text coherence and essay quality. Visualizations of the global cohesion indices are also included to support a more facile understanding of how cohesion flow impacts coherence in terms of semantic dependencies between paragraphs.

Original language	English (US)
Title of host publication	Proceedings of the 38th Annual Meeting of the Cognitive Science Society, CogSci 2016
Editors	Anna Papafragou, Daniel Grodner, Daniel Mirman, John C. Trueswell
Publisher	The Cognitive Science Society
Pages	764-769
Number of pages	6
ISBN (Electronic)	9780991196739
State	Published - 2016
Externally published	Yes
Event	38th Annual Meeting of the Cognitive Science Society: Recognizing and Representing Events, CogSci 2016 - Philadelphia, United States Duration: Aug 10 2016 → Aug 13 2016

Publication series

Name	Proceedings of the 38th Annual Meeting of the Cognitive Science Society, CogSci 2016

Conference

Conference	38th Annual Meeting of the Cognitive Science Society: Recognizing and Representing Events, CogSci 2016
Country/Territory	United States
City	Philadelphia
Period	8/10/16 → 8/13/16

Bibliographical note

Funding Information:
This research was partially supported by the EC H2020 project RAGE Grant agreement No 644187, as well as by the Institute for Education Sciences (IES R305A080589 and IES R305G20018-02) and NSF (1417997 and 1418378).

Publisher Copyright:
© 2016 Proceedings of the 38th Annual Meeting of the Cognitive Science Society, CogSci 2016. All rights reserved.

Keywords

Coherence
Cohesion Flow
Cohesion Network Analysis
Natural Language Processing, Computational Models
Writing Quality

Find It

Find It at U of M Libraries

Cite this

Crossley, S. A., Dascalu, M., Trausan-Matu, S., Allen, L. K., & McNamara, D. S. (2016). Document Cohesion Flow: Striving towards Coherence. In A. Papafragou, D. Grodner, D. Mirman, & J. C. Trueswell (Eds.), Proceedings of the 38th Annual Meeting of the Cognitive Science Society, CogSci 2016 (pp. 764-769). (Proceedings of the 38th Annual Meeting of the Cognitive Science Society, CogSci 2016). The Cognitive Science Society.

Document Cohesion Flow: Striving towards Coherence. / Crossley, Scott A.; Dascalu, Mihai; Trausan-Matu, Stefan et al.
Proceedings of the 38th Annual Meeting of the Cognitive Science Society, CogSci 2016. ed. / Anna Papafragou; Daniel Grodner; Daniel Mirman; John C. Trueswell. The Cognitive Science Society, 2016. p. 764-769 (Proceedings of the 38th Annual Meeting of the Cognitive Science Society, CogSci 2016).

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

Crossley, SA, Dascalu, M, Trausan-Matu, S, Allen, LK & McNamara, DS 2016, Document Cohesion Flow: Striving towards Coherence. in A Papafragou, D Grodner, D Mirman & JC Trueswell (eds), Proceedings of the 38th Annual Meeting of the Cognitive Science Society, CogSci 2016. Proceedings of the 38th Annual Meeting of the Cognitive Science Society, CogSci 2016, The Cognitive Science Society, pp. 764-769, 38th Annual Meeting of the Cognitive Science Society: Recognizing and Representing Events, CogSci 2016, Philadelphia, United States, 8/10/16.

Crossley SA, Dascalu M, Trausan-Matu S, Allen LK, McNamara DS. Document Cohesion Flow: Striving towards Coherence. In Papafragou A, Grodner D, Mirman D, Trueswell JC, editors, Proceedings of the 38th Annual Meeting of the Cognitive Science Society, CogSci 2016. The Cognitive Science Society. 2016. p. 764-769. (Proceedings of the 38th Annual Meeting of the Cognitive Science Society, CogSci 2016).

Crossley, Scott A. ; Dascalu, Mihai ; Trausan-Matu, Stefan et al. / Document Cohesion Flow : Striving towards Coherence. Proceedings of the 38th Annual Meeting of the Cognitive Science Society, CogSci 2016. editor / Anna Papafragou ; Daniel Grodner ; Daniel Mirman ; John C. Trueswell. The Cognitive Science Society, 2016. pp. 764-769 (Proceedings of the 38th Annual Meeting of the Cognitive Science Society, CogSci 2016).

@inproceedings{197c66bb800c431ebdb9f314ab9b4aa8,

title = "Document Cohesion Flow: Striving towards Coherence",

abstract = "Text cohesion is an important element of discourse processing. This paper presents a new approach to modeling, quantifying, and visualizing text cohesion using automated cohesion flow indices that capture semantic links among paragraphs. Cohesion flow is calculated by applying Cohesion Network Analysis, a combination of semantic distances, Latent Semantic Analysis, and Latent Dirichlet Allocation, as well as Social Network Analysis. Experiments performed on 315 timed essays indicated that cohesion flow indices are significantly correlated with human ratings of text coherence and essay quality. Visualizations of the global cohesion indices are also included to support a more facile understanding of how cohesion flow impacts coherence in terms of semantic dependencies between paragraphs.",

keywords = "Coherence, Cohesion Flow, Cohesion Network Analysis, Natural Language Processing, Computational Models, Writing Quality",

author = "Crossley, \{Scott A.\} and Mihai Dascalu and Stefan Trausan-Matu and Allen, \{Laura K.\} and McNamara, \{Danielle S.\}",

note = "Funding Information: This research was partially supported by the EC H2020 project RAGE Grant agreement No 644187, as well as by the Institute for Education Sciences (IES R305A080589 and IES R305G20018-02) and NSF (1417997 and 1418378). Publisher Copyright: {\textcopyright} 2016 Proceedings of the 38th Annual Meeting of the Cognitive Science Society, CogSci 2016. All rights reserved.; 38th Annual Meeting of the Cognitive Science Society: Recognizing and Representing Events, CogSci 2016 ; Conference date: 10-08-2016 Through 13-08-2016",

year = "2016",

language = "English (US)",

series = "Proceedings of the 38th Annual Meeting of the Cognitive Science Society, CogSci 2016",

publisher = "The Cognitive Science Society",

pages = "764--769",

editor = "Anna Papafragou and Daniel Grodner and Daniel Mirman and Trueswell, \{John C.\}",

booktitle = "Proceedings of the 38th Annual Meeting of the Cognitive Science Society, CogSci 2016",

}

TY - GEN

T1 - Document Cohesion Flow

T2 - 38th Annual Meeting of the Cognitive Science Society: Recognizing and Representing Events, CogSci 2016

AU - Crossley, Scott A.

AU - Dascalu, Mihai

AU - Trausan-Matu, Stefan

AU - Allen, Laura K.

AU - McNamara, Danielle S.

N1 - Funding Information: This research was partially supported by the EC H2020 project RAGE Grant agreement No 644187, as well as by the Institute for Education Sciences (IES R305A080589 and IES R305G20018-02) and NSF (1417997 and 1418378). Publisher Copyright: © 2016 Proceedings of the 38th Annual Meeting of the Cognitive Science Society, CogSci 2016. All rights reserved.

PY - 2016

Y1 - 2016

N2 - Text cohesion is an important element of discourse processing. This paper presents a new approach to modeling, quantifying, and visualizing text cohesion using automated cohesion flow indices that capture semantic links among paragraphs. Cohesion flow is calculated by applying Cohesion Network Analysis, a combination of semantic distances, Latent Semantic Analysis, and Latent Dirichlet Allocation, as well as Social Network Analysis. Experiments performed on 315 timed essays indicated that cohesion flow indices are significantly correlated with human ratings of text coherence and essay quality. Visualizations of the global cohesion indices are also included to support a more facile understanding of how cohesion flow impacts coherence in terms of semantic dependencies between paragraphs.

AB - Text cohesion is an important element of discourse processing. This paper presents a new approach to modeling, quantifying, and visualizing text cohesion using automated cohesion flow indices that capture semantic links among paragraphs. Cohesion flow is calculated by applying Cohesion Network Analysis, a combination of semantic distances, Latent Semantic Analysis, and Latent Dirichlet Allocation, as well as Social Network Analysis. Experiments performed on 315 timed essays indicated that cohesion flow indices are significantly correlated with human ratings of text coherence and essay quality. Visualizations of the global cohesion indices are also included to support a more facile understanding of how cohesion flow impacts coherence in terms of semantic dependencies between paragraphs.

KW - Coherence

KW - Cohesion Flow

KW - Cohesion Network Analysis

KW - Natural Language Processing, Computational Models

KW - Writing Quality

UR - https://www.scopus.com/pages/publications/84996842422

UR - https://www.scopus.com/pages/publications/84996842422#tab=citedBy

M3 - Conference contribution

AN - SCOPUS:84996842422

T3 - Proceedings of the 38th Annual Meeting of the Cognitive Science Society, CogSci 2016

SP - 764

EP - 769

BT - Proceedings of the 38th Annual Meeting of the Cognitive Science Society, CogSci 2016

A2 - Papafragou, Anna

A2 - Grodner, Daniel

A2 - Mirman, Daniel

A2 - Trueswell, John C.

PB - The Cognitive Science Society

Y2 - 10 August 2016 through 13 August 2016

ER -

Document Cohesion Flow: Striving towards Coherence

Abstract

Publication series

Conference

Bibliographical note

Keywords

Find It

Other files and links

Fingerprint

Cite this