@inproceedings{bondarenko-etal-2023-comparative,
title = "Comparative Study of Models Trained on Synthetic Data for {U}krainian Grammatical Error Correction",
author = "Bondarenko, Maksym and
Yushko, Artem and
Shportko, Andrii and
Fedorych, Andrii",
editor = "Romanyshyn, Mariana",
booktitle = "Proceedings of the Second Ukrainian Natural Language Processing Workshop (UNLP)",
month = may,
year = "2023",
address = "Dubrovnik, Croatia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.unlp-1.13",
doi = "10.18653/v1/2023.unlp-1.13",
pages = "103--113",
abstract = "The task of Grammatical Error Correction (GEC) has been extensively studied for the English language. However, its application to low-resource languages, such as Ukrainian, remains an open challenge. In this paper, we develop sequence tagging and neural machine translation models for the Ukrainian language as well as a set of algorithmic correction rules to augment those systems. We also develop synthetic data generation techniques for the Ukrainian language to create high-quality human-like errors. Finally, we determine the best combination of synthetically generated data to augment the existing UA-GEC corpus and achieve the state-of-the-art results of 0.663 F0.5 score on the newly established UA-GEC benchmark. The code and trained models will be made publicly available on GitHub and HuggingFace.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bondarenko-etal-2023-comparative">
<titleInfo>
<title>Comparative Study of Models Trained on Synthetic Data for Ukrainian Grammatical Error Correction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maksym</namePart>
<namePart type="family">Bondarenko</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Artem</namePart>
<namePart type="family">Yushko</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrii</namePart>
<namePart type="family">Shportko</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrii</namePart>
<namePart type="family">Fedorych</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Second Ukrainian Natural Language Processing Workshop (UNLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mariana</namePart>
<namePart type="family">Romanyshyn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dubrovnik, Croatia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The task of Grammatical Error Correction (GEC) has been extensively studied for the English language. However, its application to low-resource languages, such as Ukrainian, remains an open challenge. In this paper, we develop sequence tagging and neural machine translation models for the Ukrainian language as well as a set of algorithmic correction rules to augment those systems. We also develop synthetic data generation techniques for the Ukrainian language to create high-quality human-like errors. Finally, we determine the best combination of synthetically generated data to augment the existing UA-GEC corpus and achieve the state-of-the-art results of 0.663 F0.5 score on the newly established UA-GEC benchmark. The code and trained models will be made publicly available on GitHub and HuggingFace.</abstract>
<identifier type="citekey">bondarenko-etal-2023-comparative</identifier>
<identifier type="doi">10.18653/v1/2023.unlp-1.13</identifier>
<location>
<url>https://aclanthology.org/2023.unlp-1.13</url>
</location>
<part>
<date>2023-05</date>
<extent unit="page">
<start>103</start>
<end>113</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Comparative Study of Models Trained on Synthetic Data for Ukrainian Grammatical Error Correction
%A Bondarenko, Maksym
%A Yushko, Artem
%A Shportko, Andrii
%A Fedorych, Andrii
%Y Romanyshyn, Mariana
%S Proceedings of the Second Ukrainian Natural Language Processing Workshop (UNLP)
%D 2023
%8 May
%I Association for Computational Linguistics
%C Dubrovnik, Croatia
%F bondarenko-etal-2023-comparative
%X The task of Grammatical Error Correction (GEC) has been extensively studied for the English language. However, its application to low-resource languages, such as Ukrainian, remains an open challenge. In this paper, we develop sequence tagging and neural machine translation models for the Ukrainian language as well as a set of algorithmic correction rules to augment those systems. We also develop synthetic data generation techniques for the Ukrainian language to create high-quality human-like errors. Finally, we determine the best combination of synthetically generated data to augment the existing UA-GEC corpus and achieve the state-of-the-art results of 0.663 F0.5 score on the newly established UA-GEC benchmark. The code and trained models will be made publicly available on GitHub and HuggingFace.
%R 10.18653/v1/2023.unlp-1.13
%U https://aclanthology.org/2023.unlp-1.13
%U https://doi.org/10.18653/v1/2023.unlp-1.13
%P 103-113
Markdown (Informal)
[Comparative Study of Models Trained on Synthetic Data for Ukrainian Grammatical Error Correction](https://aclanthology.org/2023.unlp-1.13) (Bondarenko et al., UNLP 2023)
ACL