@inproceedings{caines-buttery-2020-reprolang,
title = "{REPROLANG} 2020: Automatic Proficiency Scoring of {C}zech, {E}nglish, {G}erman, {I}talian, and {S}panish Learner Essays",
author = "Caines, Andrew and
Buttery, Paula",
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-1.689",
pages = "5614--5623",
abstract = "We report on our attempts to reproduce the work described in Vajjala {\&} Rama 2018, {`}Experiments with universal CEFR classification{'}, as part of REPROLANG 2020: this involves featured-based and neural approaches to essay scoring in Czech, German and Italian. Our results are broadly in line with those from the original paper, with some differences due to the stochastic nature of machine learning and programming language used. We correct an error in the reported metrics, introduce new baselines, apply the experiments to English and Spanish corpora, and generate adversarial data to test classifier robustness. We conclude that feature-based approaches perform better than neural network classifiers for text datasets of this size, though neural network modifications do bring performance closer to the best feature-based models.",
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="caines-buttery-2020-reprolang">
<titleInfo>
<title>REPROLANG 2020: Automatic Proficiency Scoring of Czech, English, German, Italian, and Spanish Learner Essays</title>
</titleInfo>
<name type="personal">
<namePart type="given">Andrew</namePart>
<namePart type="family">Caines</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paula</namePart>
<namePart type="family">Buttery</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>We report on our attempts to reproduce the work described in Vajjala & Rama 2018, ‘Experiments with universal CEFR classification’, as part of REPROLANG 2020: this involves featured-based and neural approaches to essay scoring in Czech, German and Italian. Our results are broadly in line with those from the original paper, with some differences due to the stochastic nature of machine learning and programming language used. We correct an error in the reported metrics, introduce new baselines, apply the experiments to English and Spanish corpora, and generate adversarial data to test classifier robustness. We conclude that feature-based approaches perform better than neural network classifiers for text datasets of this size, though neural network modifications do bring performance closer to the best feature-based models.</abstract>
<identifier type="citekey">caines-buttery-2020-reprolang</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.689</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>5614</start>
<end>5623</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T REPROLANG 2020: Automatic Proficiency Scoring of Czech, English, German, Italian, and Spanish Learner Essays
%A Caines, Andrew
%A Buttery, Paula
%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 caines-buttery-2020-reprolang
%X We report on our attempts to reproduce the work described in Vajjala & Rama 2018, ‘Experiments with universal CEFR classification’, as part of REPROLANG 2020: this involves featured-based and neural approaches to essay scoring in Czech, German and Italian. Our results are broadly in line with those from the original paper, with some differences due to the stochastic nature of machine learning and programming language used. We correct an error in the reported metrics, introduce new baselines, apply the experiments to English and Spanish corpora, and generate adversarial data to test classifier robustness. We conclude that feature-based approaches perform better than neural network classifiers for text datasets of this size, though neural network modifications do bring performance closer to the best feature-based models.
%U https://aclanthology.org/2020.lrec-1.689
%P 5614-5623
Markdown (Informal)
[REPROLANG 2020: Automatic Proficiency Scoring of Czech, English, German, Italian, and Spanish Learner Essays](https://aclanthology.org/2020.lrec-1.689) (Caines & Buttery, LREC 2020)
ACL