@inproceedings{chaplynskyi-2023-introducing,
title = "Introducing {U}ber{T}ext 2.0: A Corpus of {M}odern {U}krainian at Scale",
author = "Chaplynskyi, Dmytro",
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-1.1",
doi = "10.18653/v1/2023.unlp-1.1",
pages = "1--10",
abstract = "This paper addresses the need for massive corpora for a low-resource language and presents the publicly available UberText 2.0 corpus for the Ukrainian language and discusses the methodology of its construction. While the collection and maintenance of such a corpus is more of a data extraction and data engineering task, the corpus itself provides a solid foundation for natural language processing tasks. It can enable the creation of contemporary language models and word embeddings, resulting in a better performance of numerous downstream tasks for the Ukrainian language. In addition, the paper and software developed can be used as a guidance and model solution for other low-resource languages. The resulting corpus is available for download on the project page. It has 3.274 billion tokens, consists of 8.59 million texts and takes up 32 gigabytes of space.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chaplynskyi-2023-introducing">
<titleInfo>
<title>Introducing UberText 2.0: A Corpus of Modern Ukrainian at Scale</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dmytro</namePart>
<namePart type="family">Chaplynskyi</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>This paper addresses the need for massive corpora for a low-resource language and presents the publicly available UberText 2.0 corpus for the Ukrainian language and discusses the methodology of its construction. While the collection and maintenance of such a corpus is more of a data extraction and data engineering task, the corpus itself provides a solid foundation for natural language processing tasks. It can enable the creation of contemporary language models and word embeddings, resulting in a better performance of numerous downstream tasks for the Ukrainian language. In addition, the paper and software developed can be used as a guidance and model solution for other low-resource languages. The resulting corpus is available for download on the project page. It has 3.274 billion tokens, consists of 8.59 million texts and takes up 32 gigabytes of space.</abstract>
<identifier type="citekey">chaplynskyi-2023-introducing</identifier>
<identifier type="doi">10.18653/v1/2023.unlp-1.1</identifier>
<location>
<url>https://aclanthology.org/2023.unlp-1.1</url>
</location>
<part>
<date>2023-05</date>
<extent unit="page">
<start>1</start>
<end>10</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Introducing UberText 2.0: A Corpus of Modern Ukrainian at Scale
%A Chaplynskyi, Dmytro
%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 chaplynskyi-2023-introducing
%X This paper addresses the need for massive corpora for a low-resource language and presents the publicly available UberText 2.0 corpus for the Ukrainian language and discusses the methodology of its construction. While the collection and maintenance of such a corpus is more of a data extraction and data engineering task, the corpus itself provides a solid foundation for natural language processing tasks. It can enable the creation of contemporary language models and word embeddings, resulting in a better performance of numerous downstream tasks for the Ukrainian language. In addition, the paper and software developed can be used as a guidance and model solution for other low-resource languages. The resulting corpus is available for download on the project page. It has 3.274 billion tokens, consists of 8.59 million texts and takes up 32 gigabytes of space.
%R 10.18653/v1/2023.unlp-1.1
%U https://aclanthology.org/2023.unlp-1.1
%U https://doi.org/10.18653/v1/2023.unlp-1.1
%P 1-10
Markdown (Informal)
[Introducing UberText 2.0: A Corpus of Modern Ukrainian at Scale](https://aclanthology.org/2023.unlp-1.1) (Chaplynskyi, UNLP 2023)
ACL