@inproceedings{ouahrani-bennouar-2020-ar,
title = "{AR}-{ASAG} An {AR}abic Dataset for Automatic Short Answer Grading Evaluation",
author = "Ouahrani, Leila and
Bennouar, Djamal",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
month = may,
year = "2020",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2020.lrec-1.321",
pages = "2634--2643",
abstract = "Automatic short answer grading is a significant problem in E-assessment. Several models have been proposed to deal with it. Evaluation and comparison of such solutions need the availability of Datasets with manual examples. In this paper, we introduce AR-ASAG, an Arabic Dataset for automatic short answer grading. The Dataset contains 2133 pairs of (Model Answer, Student Answer) in several versions (txt, xml, Moodle xml and .db). We explore then an unsupervised corpus based approach for automatic grading adapted to the Arabic Language. We use COALS (Correlated Occurrence Analogue to Lexical Semantic) algorithm to create semantic space for word distribution. The summation vector model is combined to term weighting and common words to achieve similarity between a teacher model answer and a student answer. The approach is particularly suitable for languages with scarce resources such as Arabic language where robust specific resources are not yet available. A set of experiments were conducted to analyze the effect of domain specificity, semantic space dimension and stemming techniques on the effectiveness of the grading model. The proposed approach gives promising results for Arabic language. The reported results may serve as baseline for future research work evaluation",
language = "English",
ISBN = "979-10-95546-34-4",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ouahrani-bennouar-2020-ar">
<titleInfo>
<title>AR-ASAG An ARabic Dataset for Automatic Short Answer Grading Evaluation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Leila</namePart>
<namePart type="family">Ouahrani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Djamal</namePart>
<namePart type="family">Bennouar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Twelfth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asuncion</namePart>
<namePart type="family">Moreno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-10-95546-34-4</identifier>
</relatedItem>
<abstract>Automatic short answer grading is a significant problem in E-assessment. Several models have been proposed to deal with it. Evaluation and comparison of such solutions need the availability of Datasets with manual examples. In this paper, we introduce AR-ASAG, an Arabic Dataset for automatic short answer grading. The Dataset contains 2133 pairs of (Model Answer, Student Answer) in several versions (txt, xml, Moodle xml and .db). We explore then an unsupervised corpus based approach for automatic grading adapted to the Arabic Language. We use COALS (Correlated Occurrence Analogue to Lexical Semantic) algorithm to create semantic space for word distribution. The summation vector model is combined to term weighting and common words to achieve similarity between a teacher model answer and a student answer. The approach is particularly suitable for languages with scarce resources such as Arabic language where robust specific resources are not yet available. A set of experiments were conducted to analyze the effect of domain specificity, semantic space dimension and stemming techniques on the effectiveness of the grading model. The proposed approach gives promising results for Arabic language. The reported results may serve as baseline for future research work evaluation</abstract>
<identifier type="citekey">ouahrani-bennouar-2020-ar</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.321</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>2634</start>
<end>2643</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T AR-ASAG An ARabic Dataset for Automatic Short Answer Grading Evaluation
%A Ouahrani, Leila
%A Bennouar, Djamal
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Twelfth Language Resources and Evaluation Conference
%D 2020
%8 May
%I European Language Resources Association
%C Marseille, France
%@ 979-10-95546-34-4
%G English
%F ouahrani-bennouar-2020-ar
%X Automatic short answer grading is a significant problem in E-assessment. Several models have been proposed to deal with it. Evaluation and comparison of such solutions need the availability of Datasets with manual examples. In this paper, we introduce AR-ASAG, an Arabic Dataset for automatic short answer grading. The Dataset contains 2133 pairs of (Model Answer, Student Answer) in several versions (txt, xml, Moodle xml and .db). We explore then an unsupervised corpus based approach for automatic grading adapted to the Arabic Language. We use COALS (Correlated Occurrence Analogue to Lexical Semantic) algorithm to create semantic space for word distribution. The summation vector model is combined to term weighting and common words to achieve similarity between a teacher model answer and a student answer. The approach is particularly suitable for languages with scarce resources such as Arabic language where robust specific resources are not yet available. A set of experiments were conducted to analyze the effect of domain specificity, semantic space dimension and stemming techniques on the effectiveness of the grading model. The proposed approach gives promising results for Arabic language. The reported results may serve as baseline for future research work evaluation
%U https://aclanthology.org/2020.lrec-1.321
%P 2634-2643
Markdown (Informal)
[AR-ASAG An ARabic Dataset for Automatic Short Answer Grading Evaluation](https://aclanthology.org/2020.lrec-1.321) (Ouahrani & Bennouar, LREC 2020)
ACL