@inproceedings{tack-etal-2017-human,
title = "Human and Automated {CEFR}-based Grading of Short Answers",
author = {Tack, Ana{\"\i}s and
Fran{\c{c}}ois, Thomas and
Roekhaut, Sophie and
Fairon, C{\'e}drick},
editor = "Tetreault, Joel and
Burstein, Jill and
Leacock, Claudia and
Yannakoudakis, Helen",
booktitle = "Proceedings of the 12th Workshop on Innovative Use of {NLP} for Building Educational Applications",
month = sep,
year = "2017",
address = "Copenhagen, Denmark",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W17-5018",
doi = "10.18653/v1/W17-5018",
pages = "169--179",
abstract = "This paper is concerned with the task of automatically assessing the written proficiency level of non-native (L2) learners of English. Drawing on previous research on automated L2 writing assessment following the Common European Framework of Reference for Languages (CEFR), we investigate the possibilities and difficulties of deriving the CEFR level from short answers to open-ended questions, which has not yet been subjected to numerous studies up to date. The object of our study is twofold: to examine the intricacy involved with both human and automated CEFR-based grading of short answers. On the one hand, we describe the compilation of a learner corpus of short answers graded with CEFR levels by three certified Cambridge examiners. We mainly observe that, although the shortness of the answers is reported as undermining a clear-cut evaluation, the length of the answer does not necessarily correlate with inter-examiner disagreement. On the other hand, we explore the development of a soft-voting system for the automated CEFR-based grading of short answers and draw tentative conclusions about its use in a computer-assisted testing (CAT) setting.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tack-etal-2017-human">
<titleInfo>
<title>Human and Automated CEFR-based Grading of Short Answers</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anaïs</namePart>
<namePart type="family">Tack</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thomas</namePart>
<namePart type="family">François</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sophie</namePart>
<namePart type="family">Roekhaut</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cédrick</namePart>
<namePart type="family">Fairon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2017-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 12th Workshop on Innovative Use of NLP for Building Educational Applications</title>
</titleInfo>
<name type="personal">
<namePart type="given">Joel</namePart>
<namePart type="family">Tetreault</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jill</namePart>
<namePart type="family">Burstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Claudia</namePart>
<namePart type="family">Leacock</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helen</namePart>
<namePart type="family">Yannakoudakis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Copenhagen, Denmark</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper is concerned with the task of automatically assessing the written proficiency level of non-native (L2) learners of English. Drawing on previous research on automated L2 writing assessment following the Common European Framework of Reference for Languages (CEFR), we investigate the possibilities and difficulties of deriving the CEFR level from short answers to open-ended questions, which has not yet been subjected to numerous studies up to date. The object of our study is twofold: to examine the intricacy involved with both human and automated CEFR-based grading of short answers. On the one hand, we describe the compilation of a learner corpus of short answers graded with CEFR levels by three certified Cambridge examiners. We mainly observe that, although the shortness of the answers is reported as undermining a clear-cut evaluation, the length of the answer does not necessarily correlate with inter-examiner disagreement. On the other hand, we explore the development of a soft-voting system for the automated CEFR-based grading of short answers and draw tentative conclusions about its use in a computer-assisted testing (CAT) setting.</abstract>
<identifier type="citekey">tack-etal-2017-human</identifier>
<identifier type="doi">10.18653/v1/W17-5018</identifier>
<location>
<url>https://aclanthology.org/W17-5018</url>
</location>
<part>
<date>2017-09</date>
<extent unit="page">
<start>169</start>
<end>179</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Human and Automated CEFR-based Grading of Short Answers
%A Tack, Anaïs
%A François, Thomas
%A Roekhaut, Sophie
%A Fairon, Cédrick
%Y Tetreault, Joel
%Y Burstein, Jill
%Y Leacock, Claudia
%Y Yannakoudakis, Helen
%S Proceedings of the 12th Workshop on Innovative Use of NLP for Building Educational Applications
%D 2017
%8 September
%I Association for Computational Linguistics
%C Copenhagen, Denmark
%F tack-etal-2017-human
%X This paper is concerned with the task of automatically assessing the written proficiency level of non-native (L2) learners of English. Drawing on previous research on automated L2 writing assessment following the Common European Framework of Reference for Languages (CEFR), we investigate the possibilities and difficulties of deriving the CEFR level from short answers to open-ended questions, which has not yet been subjected to numerous studies up to date. The object of our study is twofold: to examine the intricacy involved with both human and automated CEFR-based grading of short answers. On the one hand, we describe the compilation of a learner corpus of short answers graded with CEFR levels by three certified Cambridge examiners. We mainly observe that, although the shortness of the answers is reported as undermining a clear-cut evaluation, the length of the answer does not necessarily correlate with inter-examiner disagreement. On the other hand, we explore the development of a soft-voting system for the automated CEFR-based grading of short answers and draw tentative conclusions about its use in a computer-assisted testing (CAT) setting.
%R 10.18653/v1/W17-5018
%U https://aclanthology.org/W17-5018
%U https://doi.org/10.18653/v1/W17-5018
%P 169-179
Markdown (Informal)
[Human and Automated CEFR-based Grading of Short Answers](https://aclanthology.org/W17-5018) (Tack et al., BEA 2017)
ACL
- Anaïs Tack, Thomas François, Sophie Roekhaut, and Cédrick Fairon. 2017. Human and Automated CEFR-based Grading of Short Answers. In Proceedings of the 12th Workshop on Innovative Use of NLP for Building Educational Applications, pages 169–179, Copenhagen, Denmark. Association for Computational Linguistics.