@inproceedings{syvokon-etal-2023-ua,
title = "{UA}-{GEC}: Grammatical Error Correction and Fluency Corpus for the {U}krainian Language",
author = "Syvokon, Oleksiy and
Nahorna, Olena and
Kuchmiichuk, Pavlo and
Osidach, Nastasiia",
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-1.12",
doi = "10.18653/v1/2023.unlp-1.12",
pages = "96--102",
abstract = "We present a corpus professionally annotated for grammatical error correction (GEC) and fluency edits in the Ukrainian language. We have built two versions of the corpus {--} GEC+Fluency and GEC-only {--} to differentiate the corpus application. To the best of our knowledge, this is the first GEC corpus for the Ukrainian language. We collected texts with errors (33,735 sentences) from a diverse pool of contributors, including both native and non-native speakers. The data cover a wide variety of writing domains, from text chats and essays to formal writing. Professional proofreaders corrected and annotated the corpus for errors relating to fluency, grammar, punctuation, and spelling. This corpus can be used for developing and evaluating GEC systems in Ukrainian. More generally, it can be used for researching multilingual and low-resource NLP, morphologically rich languages, document-level GEC, and fluency correction. The corpus is publicly available at \url{https://github.com/grammarly/ua-gec}",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="syvokon-etal-2023-ua">
<titleInfo>
<title>UA-GEC: Grammatical Error Correction and Fluency Corpus for the Ukrainian Language</title>
</titleInfo>
<name type="personal">
<namePart type="given">Oleksiy</namePart>
<namePart type="family">Syvokon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Olena</namePart>
<namePart type="family">Nahorna</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pavlo</namePart>
<namePart type="family">Kuchmiichuk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nastasiia</namePart>
<namePart type="family">Osidach</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>We present a corpus professionally annotated for grammatical error correction (GEC) and fluency edits in the Ukrainian language. We have built two versions of the corpus – GEC+Fluency and GEC-only – to differentiate the corpus application. To the best of our knowledge, this is the first GEC corpus for the Ukrainian language. We collected texts with errors (33,735 sentences) from a diverse pool of contributors, including both native and non-native speakers. The data cover a wide variety of writing domains, from text chats and essays to formal writing. Professional proofreaders corrected and annotated the corpus for errors relating to fluency, grammar, punctuation, and spelling. This corpus can be used for developing and evaluating GEC systems in Ukrainian. More generally, it can be used for researching multilingual and low-resource NLP, morphologically rich languages, document-level GEC, and fluency correction. The corpus is publicly available at https://github.com/grammarly/ua-gec</abstract>
<identifier type="citekey">syvokon-etal-2023-ua</identifier>
<identifier type="doi">10.18653/v1/2023.unlp-1.12</identifier>
<location>
<url>https://aclanthology.org/2023.unlp-1.12</url>
</location>
<part>
<date>2023-05</date>
<extent unit="page">
<start>96</start>
<end>102</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T UA-GEC: Grammatical Error Correction and Fluency Corpus for the Ukrainian Language
%A Syvokon, Oleksiy
%A Nahorna, Olena
%A Kuchmiichuk, Pavlo
%A Osidach, Nastasiia
%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 syvokon-etal-2023-ua
%X We present a corpus professionally annotated for grammatical error correction (GEC) and fluency edits in the Ukrainian language. We have built two versions of the corpus – GEC+Fluency and GEC-only – to differentiate the corpus application. To the best of our knowledge, this is the first GEC corpus for the Ukrainian language. We collected texts with errors (33,735 sentences) from a diverse pool of contributors, including both native and non-native speakers. The data cover a wide variety of writing domains, from text chats and essays to formal writing. Professional proofreaders corrected and annotated the corpus for errors relating to fluency, grammar, punctuation, and spelling. This corpus can be used for developing and evaluating GEC systems in Ukrainian. More generally, it can be used for researching multilingual and low-resource NLP, morphologically rich languages, document-level GEC, and fluency correction. The corpus is publicly available at https://github.com/grammarly/ua-gec
%R 10.18653/v1/2023.unlp-1.12
%U https://aclanthology.org/2023.unlp-1.12
%U https://doi.org/10.18653/v1/2023.unlp-1.12
%P 96-102
Markdown (Informal)
[UA-GEC: Grammatical Error Correction and Fluency Corpus for the Ukrainian Language](https://aclanthology.org/2023.unlp-1.12) (Syvokon et al., UNLP 2023)
ACL