@inproceedings{bestgen-2020-reproducing,
title = "Reproducing Monolingual, Multilingual and Cross-Lingual {CEFR} Predictions",
author = "Bestgen, Yves",
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-1.687",
pages = "5595--5602",
abstract = "his study aims to reproduce the research of Vajjala and Rama (2018) which showed that it is possible to predict the quality of a text written by learners of a given language by means of a model built on the basis of texts written by learners of another language. These authors also pointed out that POStag and dependency n-grams were significantly more effective than text length and global linguistic indices frequently used for this kind of task. The analyses performed show that some important points of their code did not correspond to the explanations given in the paper. These analyses confirm the possibility to use syntactic n-gram features in cross-lingual experiments to categorize texts according to their CEFR level (Common European Framework of Reference for Languages). However, text length and some classical indexes of readability are much more effective in the monolingual and the multilingual experiments than what Vajjala and Rama concluded and are even the best performing features when the cross-lingual task is seen as a regression problem. This study emphasized the importance for reproducibility of setting explicitly the reading order of the instances when using a K-fold CV procedure and, more generally, the need to properly randomize these instances before. It also evaluates a two-step procedure to determine the degree of statistical significance of the differences observed in a K-fold cross-validation schema and argues against the use of a Bonferroni-type correction in this context.",
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="bestgen-2020-reproducing">
<titleInfo>
<title>Reproducing Monolingual, Multilingual and Cross-Lingual CEFR Predictions</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yves</namePart>
<namePart type="family">Bestgen</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>his study aims to reproduce the research of Vajjala and Rama (2018) which showed that it is possible to predict the quality of a text written by learners of a given language by means of a model built on the basis of texts written by learners of another language. These authors also pointed out that POStag and dependency n-grams were significantly more effective than text length and global linguistic indices frequently used for this kind of task. The analyses performed show that some important points of their code did not correspond to the explanations given in the paper. These analyses confirm the possibility to use syntactic n-gram features in cross-lingual experiments to categorize texts according to their CEFR level (Common European Framework of Reference for Languages). However, text length and some classical indexes of readability are much more effective in the monolingual and the multilingual experiments than what Vajjala and Rama concluded and are even the best performing features when the cross-lingual task is seen as a regression problem. This study emphasized the importance for reproducibility of setting explicitly the reading order of the instances when using a K-fold CV procedure and, more generally, the need to properly randomize these instances before. It also evaluates a two-step procedure to determine the degree of statistical significance of the differences observed in a K-fold cross-validation schema and argues against the use of a Bonferroni-type correction in this context.</abstract>
<identifier type="citekey">bestgen-2020-reproducing</identifier>
<location>
<url>https://aclanthology.org/2020.lrec-1.687</url>
</location>
<part>
<date>2020-05</date>
<extent unit="page">
<start>5595</start>
<end>5602</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Reproducing Monolingual, Multilingual and Cross-Lingual CEFR Predictions
%A Bestgen, Yves
%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 bestgen-2020-reproducing
%X his study aims to reproduce the research of Vajjala and Rama (2018) which showed that it is possible to predict the quality of a text written by learners of a given language by means of a model built on the basis of texts written by learners of another language. These authors also pointed out that POStag and dependency n-grams were significantly more effective than text length and global linguistic indices frequently used for this kind of task. The analyses performed show that some important points of their code did not correspond to the explanations given in the paper. These analyses confirm the possibility to use syntactic n-gram features in cross-lingual experiments to categorize texts according to their CEFR level (Common European Framework of Reference for Languages). However, text length and some classical indexes of readability are much more effective in the monolingual and the multilingual experiments than what Vajjala and Rama concluded and are even the best performing features when the cross-lingual task is seen as a regression problem. This study emphasized the importance for reproducibility of setting explicitly the reading order of the instances when using a K-fold CV procedure and, more generally, the need to properly randomize these instances before. It also evaluates a two-step procedure to determine the degree of statistical significance of the differences observed in a K-fold cross-validation schema and argues against the use of a Bonferroni-type correction in this context.
%U https://aclanthology.org/2020.lrec-1.687
%P 5595-5602
Markdown (Informal)
[Reproducing Monolingual, Multilingual and Cross-Lingual CEFR Predictions](https://aclanthology.org/2020.lrec-1.687) (Bestgen, LREC 2020)
ACL