@inproceedings{kubal-nagvenkar-2025-leveraging,
title = "Leveraging Multilingual Models for Robust Grammatical Error Correction Across Low-Resource Languages",
author = "Kubal, Divesh Ramesh and
Nagvenkar, Apurva Shrikant",
editor = "Rambow, Owen and
Wanner, Leo and
Apidianaki, Marianna and
Al-Khalifa, Hend and
Eugenio, Barbara Di and
Schockaert, Steven and
Darwish, Kareem and
Agarwal, Apoorv",
booktitle = "Proceedings of the 31st International Conference on Computational Linguistics: Industry Track",
month = jan,
year = "2025",
address = "Abu Dhabi, UAE",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.coling-industry.43/",
pages = "505--510",
abstract = "Grammatical Error Correction (GEC) is a crucial task in Natural Language Processing (NLP) aimed at improving the quality of user-generated content, particularly for non-native speakers. This paper introduces a novel end-to-end architecture utilizing the M2M100 multilingual transformer model to build a unified GEC system, with a focus on low-resource languages. A synthetic data generation pipeline is proposed, tailored to address language-specific error categories. The system has been implemented for the Spanish language, showing promising results based on evaluations conducted by linguists with expertise in Spanish. Additionally, we present a user analysis that tracks user interactions, revealing an acceptance rate of 88.2{\%}, as reflected by the actions performed by users."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kubal-nagvenkar-2025-leveraging">
<titleInfo>
<title>Leveraging Multilingual Models for Robust Grammatical Error Correction Across Low-Resource Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Divesh</namePart>
<namePart type="given">Ramesh</namePart>
<namePart type="family">Kubal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Apurva</namePart>
<namePart type="given">Shrikant</namePart>
<namePart type="family">Nagvenkar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-01</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 31st International Conference on Computational Linguistics: Industry Track</title>
</titleInfo>
<name type="personal">
<namePart type="given">Owen</namePart>
<namePart type="family">Rambow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marianna</namePart>
<namePart type="family">Apidianaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hend</namePart>
<namePart type="family">Al-Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="given">Di</namePart>
<namePart type="family">Eugenio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Schockaert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kareem</namePart>
<namePart type="family">Darwish</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Apoorv</namePart>
<namePart type="family">Agarwal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, UAE</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Grammatical Error Correction (GEC) is a crucial task in Natural Language Processing (NLP) aimed at improving the quality of user-generated content, particularly for non-native speakers. This paper introduces a novel end-to-end architecture utilizing the M2M100 multilingual transformer model to build a unified GEC system, with a focus on low-resource languages. A synthetic data generation pipeline is proposed, tailored to address language-specific error categories. The system has been implemented for the Spanish language, showing promising results based on evaluations conducted by linguists with expertise in Spanish. Additionally, we present a user analysis that tracks user interactions, revealing an acceptance rate of 88.2%, as reflected by the actions performed by users.</abstract>
<identifier type="citekey">kubal-nagvenkar-2025-leveraging</identifier>
<location>
<url>https://aclanthology.org/2025.coling-industry.43/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>505</start>
<end>510</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Leveraging Multilingual Models for Robust Grammatical Error Correction Across Low-Resource Languages
%A Kubal, Divesh Ramesh
%A Nagvenkar, Apurva Shrikant
%Y Rambow, Owen
%Y Wanner, Leo
%Y Apidianaki, Marianna
%Y Al-Khalifa, Hend
%Y Eugenio, Barbara Di
%Y Schockaert, Steven
%Y Darwish, Kareem
%Y Agarwal, Apoorv
%S Proceedings of the 31st International Conference on Computational Linguistics: Industry Track
%D 2025
%8 January
%I Association for Computational Linguistics
%C Abu Dhabi, UAE
%F kubal-nagvenkar-2025-leveraging
%X Grammatical Error Correction (GEC) is a crucial task in Natural Language Processing (NLP) aimed at improving the quality of user-generated content, particularly for non-native speakers. This paper introduces a novel end-to-end architecture utilizing the M2M100 multilingual transformer model to build a unified GEC system, with a focus on low-resource languages. A synthetic data generation pipeline is proposed, tailored to address language-specific error categories. The system has been implemented for the Spanish language, showing promising results based on evaluations conducted by linguists with expertise in Spanish. Additionally, we present a user analysis that tracks user interactions, revealing an acceptance rate of 88.2%, as reflected by the actions performed by users.
%U https://aclanthology.org/2025.coling-industry.43/
%P 505-510
Markdown (Informal)
[Leveraging Multilingual Models for Robust Grammatical Error Correction Across Low-Resource Languages](https://aclanthology.org/2025.coling-industry.43/) (Kubal & Nagvenkar, COLING 2025)
ACL