@inproceedings{korre-pavlopoulos-2022-enriching,
title = "Enriching Grammatical Error Correction Resources for {M}odern {G}reek",
author = "Korre, Katerina and
Pavlopoulos, John",
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
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.532",
pages = "4984--4991",
abstract = "Grammatical Error Correction (GEC), a task of Natural Language Processing (NLP), is challenging for underepresented languages. This issue is most prominent in languages other than English. This paper addresses the issue of data and system sparsity for GEC purposes in the modern Greek Language. Following the most popular current approaches in GEC, we develop and test an MT5 multilingual text-to-text transformer for Greek. To our knowledge this the first attempt to create a fully-fledged GEC model for Greek. Our evaluation shows that our system reaches up to 52.63{\%} F0.5 score on part of the Greek Native Corpus (GNC), which is 16{\%} below the winning system of the BEA-19 shared task on English GEC. In addition, we provide an extended version of the Greek Learner Corpus (GLC), on which our model reaches up to 22.76{\%} F0.5. Previous versions did not include corrections with the annotations which hindered the potential development of efficient GEC systems. For that reason we provide a new set of corrections. This new dataset facilitates an exploration of the generalisation abilities and robustness of our system, given that the assessment is conducted on learner data while the training on native data.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="korre-pavlopoulos-2022-enriching">
<titleInfo>
<title>Enriching Grammatical Error Correction Resources for Modern Greek</title>
</titleInfo>
<name type="personal">
<namePart type="given">Katerina</namePart>
<namePart type="family">Korre</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">John</namePart>
<namePart type="family">Pavlopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Thirteenth 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">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>
</relatedItem>
<abstract>Grammatical Error Correction (GEC), a task of Natural Language Processing (NLP), is challenging for underepresented languages. This issue is most prominent in languages other than English. This paper addresses the issue of data and system sparsity for GEC purposes in the modern Greek Language. Following the most popular current approaches in GEC, we develop and test an MT5 multilingual text-to-text transformer for Greek. To our knowledge this the first attempt to create a fully-fledged GEC model for Greek. Our evaluation shows that our system reaches up to 52.63% F0.5 score on part of the Greek Native Corpus (GNC), which is 16% below the winning system of the BEA-19 shared task on English GEC. In addition, we provide an extended version of the Greek Learner Corpus (GLC), on which our model reaches up to 22.76% F0.5. Previous versions did not include corrections with the annotations which hindered the potential development of efficient GEC systems. For that reason we provide a new set of corrections. This new dataset facilitates an exploration of the generalisation abilities and robustness of our system, given that the assessment is conducted on learner data while the training on native data.</abstract>
<identifier type="citekey">korre-pavlopoulos-2022-enriching</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.532</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>4984</start>
<end>4991</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Enriching Grammatical Error Correction Resources for Modern Greek
%A Korre, Katerina
%A Pavlopoulos, John
%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 Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F korre-pavlopoulos-2022-enriching
%X Grammatical Error Correction (GEC), a task of Natural Language Processing (NLP), is challenging for underepresented languages. This issue is most prominent in languages other than English. This paper addresses the issue of data and system sparsity for GEC purposes in the modern Greek Language. Following the most popular current approaches in GEC, we develop and test an MT5 multilingual text-to-text transformer for Greek. To our knowledge this the first attempt to create a fully-fledged GEC model for Greek. Our evaluation shows that our system reaches up to 52.63% F0.5 score on part of the Greek Native Corpus (GNC), which is 16% below the winning system of the BEA-19 shared task on English GEC. In addition, we provide an extended version of the Greek Learner Corpus (GLC), on which our model reaches up to 22.76% F0.5. Previous versions did not include corrections with the annotations which hindered the potential development of efficient GEC systems. For that reason we provide a new set of corrections. This new dataset facilitates an exploration of the generalisation abilities and robustness of our system, given that the assessment is conducted on learner data while the training on native data.
%U https://aclanthology.org/2022.lrec-1.532
%P 4984-4991
Markdown (Informal)
[Enriching Grammatical Error Correction Resources for Modern Greek](https://aclanthology.org/2022.lrec-1.532) (Korre & Pavlopoulos, LREC 2022)
ACL