@inproceedings{shvedova-lukashevskyi-2024-creating,
title = "Creating Parallel Corpora for {U}krainian: A {G}erman-{U}krainian Parallel Corpus ({P}ara{R}ook||{DE}-{UK})",
author = "Shvedova, Maria and
Lukashevskyi, Arsenii",
editor = "Romanyshyn, Mariana and
Romanyshyn, Nataliia and
Hlybovets, Andrii and
Ignatenko, Oleksii",
booktitle = "Proceedings of the Third Ukrainian Natural Language Processing Workshop (UNLP) @ LREC-COLING 2024",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.unlp-1.3",
pages = "14--22",
abstract = "Parallel corpora are currently a popular and vibrantly developing category of linguistic resources, used both in literature and translation studies, as well as in the field of NLP. For Ukrainian, though, there are still not enough significant parallel corpora compiled within a single roof project and made available to the research community. In this paper we present a newly developed resource, the German-Ukrainian Parallel Corpus {---} ParaRook||DE-UK, searchable online. We describe various issues related to its compilation, text selection, and annotation. The paper also features several examples of how the corpus can be used in linguistic research and translation studies. Using the experience of the German-Ukrainian parallel corpus, parallel corpora for other languages with Ukrainian can be developed.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="shvedova-lukashevskyi-2024-creating">
<titleInfo>
<title>Creating Parallel Corpora for Ukrainian: A German-Ukrainian Parallel Corpus (ParaRook||DE-UK)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Shvedova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arsenii</namePart>
<namePart type="family">Lukashevskyi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Third Ukrainian Natural Language Processing Workshop (UNLP) @ LREC-COLING 2024</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>
<name type="personal">
<namePart type="given">Nataliia</namePart>
<namePart type="family">Romanyshyn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrii</namePart>
<namePart type="family">Hlybovets</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Oleksii</namePart>
<namePart type="family">Ignatenko</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Parallel corpora are currently a popular and vibrantly developing category of linguistic resources, used both in literature and translation studies, as well as in the field of NLP. For Ukrainian, though, there are still not enough significant parallel corpora compiled within a single roof project and made available to the research community. In this paper we present a newly developed resource, the German-Ukrainian Parallel Corpus — ParaRook||DE-UK, searchable online. We describe various issues related to its compilation, text selection, and annotation. The paper also features several examples of how the corpus can be used in linguistic research and translation studies. Using the experience of the German-Ukrainian parallel corpus, parallel corpora for other languages with Ukrainian can be developed.</abstract>
<identifier type="citekey">shvedova-lukashevskyi-2024-creating</identifier>
<location>
<url>https://aclanthology.org/2024.unlp-1.3</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>14</start>
<end>22</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Creating Parallel Corpora for Ukrainian: A German-Ukrainian Parallel Corpus (ParaRook||DE-UK)
%A Shvedova, Maria
%A Lukashevskyi, Arsenii
%Y Romanyshyn, Mariana
%Y Romanyshyn, Nataliia
%Y Hlybovets, Andrii
%Y Ignatenko, Oleksii
%S Proceedings of the Third Ukrainian Natural Language Processing Workshop (UNLP) @ LREC-COLING 2024
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F shvedova-lukashevskyi-2024-creating
%X Parallel corpora are currently a popular and vibrantly developing category of linguistic resources, used both in literature and translation studies, as well as in the field of NLP. For Ukrainian, though, there are still not enough significant parallel corpora compiled within a single roof project and made available to the research community. In this paper we present a newly developed resource, the German-Ukrainian Parallel Corpus — ParaRook||DE-UK, searchable online. We describe various issues related to its compilation, text selection, and annotation. The paper also features several examples of how the corpus can be used in linguistic research and translation studies. Using the experience of the German-Ukrainian parallel corpus, parallel corpora for other languages with Ukrainian can be developed.
%U https://aclanthology.org/2024.unlp-1.3
%P 14-22
Markdown (Informal)
[Creating Parallel Corpora for Ukrainian: A German-Ukrainian Parallel Corpus (ParaRook||DE-UK)](https://aclanthology.org/2024.unlp-1.3) (Shvedova & Lukashevskyi, UNLP 2024)
ACL