Coherence-Based Automatic Essay Assessment

Diego Palma; John Atkinson

doi:10.1109/MIS.2018.2877278

Coherence-Based Automatic Essay Assessment

Diego Palma, John Atkinson

Research output: Contribution to journal › Article › peer-review

14 Scopus citations

Abstract

In this paper, a discourse-based method that merges semantic and syntactic models for automated essay assessment is proposed. The approach combines shallow linguistic features and discourse patterns in order to predict an essay's score by using decision trees regression techniques. Unlike current approaches, our method directly measures an essay coherence by using corpus-based semantics and text centering techniques so as to determine discourse patterns underlying high-quality essays when compared with human assessed essays. Experiments using standard datasets showed that the proposed discourse-based approach outperformed traditional shallow features-based methods.

Original language	English
Article number	8506398
Pages (from-to)	26-36
Number of pages	11
Journal	IEEE Intelligent Systems
Volume	33
Issue number	5
DOIs	https://doi.org/10.1109/MIS.2018.2877278
State	Published - 1 Sep 2018
Externally published	Yes

Keywords

Discourse Processing
Essay Assessment
Machine Learning
Semantic Analysis

Access to Document

10.1109/MIS.2018.2877278

Cite this

@article{bf7729a25e4e4e1bade6dcb1a1b650e3,

title = "Coherence-Based Automatic Essay Assessment",

abstract = "In this paper, a discourse-based method that merges semantic and syntactic models for automated essay assessment is proposed. The approach combines shallow linguistic features and discourse patterns in order to predict an essay's score by using decision trees regression techniques. Unlike current approaches, our method directly measures an essay coherence by using corpus-based semantics and text centering techniques so as to determine discourse patterns underlying high-quality essays when compared with human assessed essays. Experiments using standard datasets showed that the proposed discourse-based approach outperformed traditional shallow features-based methods.",

keywords = "Discourse Processing, Essay Assessment, Machine Learning, Semantic Analysis",

author = "Diego Palma and John Atkinson",

note = "Publisher Copyright: {\textcopyright} 2001-2011 IEEE.",

year = "2018",

month = sep,

day = "1",

doi = "10.1109/MIS.2018.2877278",

language = "English",

volume = "33",

pages = "26--36",

journal = "IEEE Intelligent Systems",

issn = "1541-1672",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

number = "5",

}

TY - JOUR

T1 - Coherence-Based Automatic Essay Assessment

AU - Palma, Diego

AU - Atkinson, John

PY - 2018/9/1

Y1 - 2018/9/1

N2 - In this paper, a discourse-based method that merges semantic and syntactic models for automated essay assessment is proposed. The approach combines shallow linguistic features and discourse patterns in order to predict an essay's score by using decision trees regression techniques. Unlike current approaches, our method directly measures an essay coherence by using corpus-based semantics and text centering techniques so as to determine discourse patterns underlying high-quality essays when compared with human assessed essays. Experiments using standard datasets showed that the proposed discourse-based approach outperformed traditional shallow features-based methods.

AB - In this paper, a discourse-based method that merges semantic and syntactic models for automated essay assessment is proposed. The approach combines shallow linguistic features and discourse patterns in order to predict an essay's score by using decision trees regression techniques. Unlike current approaches, our method directly measures an essay coherence by using corpus-based semantics and text centering techniques so as to determine discourse patterns underlying high-quality essays when compared with human assessed essays. Experiments using standard datasets showed that the proposed discourse-based approach outperformed traditional shallow features-based methods.

KW - Discourse Processing

KW - Essay Assessment

KW - Machine Learning

KW - Semantic Analysis

UR - http://www.scopus.com/inward/record.url?scp=85055676094&partnerID=8YFLogxK

U2 - 10.1109/MIS.2018.2877278

DO - 10.1109/MIS.2018.2877278

M3 - Article

AN - SCOPUS:85055676094

SN - 1541-1672

VL - 33

SP - 26

EP - 36

JO - IEEE Intelligent Systems

JF - IEEE Intelligent Systems

IS - 5

M1 - 8506398

ER -

Coherence-Based Automatic Essay Assessment

Abstract

Keywords

Access to Document

Fingerprint

Cite this