@inproceedings{jo-etal-2023-k,
title = "K-{U}ni{M}orph: {K}orean {U}niversal {M}orphology and its Feature Schema",
author = "Jo, Eunkyul and
Kyuwon, Kim and
Wu, Xihan and
Lim, KyungTae and
Park, Jungyeul and
Park, Chulwoo",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2023",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-acl.414",
doi = "10.18653/v1/2023.findings-acl.414",
pages = "6613--6623",
abstract = "We present in this work a new Universal Morphology dataset for Korean. Previously, the Korean language has been underrepresented in the field of morphological paradigms amongst hundreds of diverse world languages. Hence, we propose this Universal Morphological paradigms for the Korean language that preserve its distinct characteristics. For our K-UniMorph dataset, we outline each grammatical criterion in detail for the verbal endings, clarify how to extract inflected forms, and demonstrate how we generate the morphological schemata. This dataset adopts morphological feature schema from CITATION and CITATION for the Korean language as we extract inflected verb forms from the Sejong morphologically analyzed corpus that is one of the largest annotated corpora for Korean. During the data creation, our methodology also includes investigating the correctness of the conversion from the Sejong corpus. Furthermore, we carry out the inflection task using three different Korean word forms: letters, syllables and morphemes. Finally, we discuss and describe future perspectives on Korean morphological paradigms and the dataset.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jo-etal-2023-k">
<titleInfo>
<title>K-UniMorph: Korean Universal Morphology and its Feature Schema</title>
</titleInfo>
<name type="personal">
<namePart type="given">Eunkyul</namePart>
<namePart type="family">Jo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kim</namePart>
<namePart type="family">Kyuwon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xihan</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">KyungTae</namePart>
<namePart type="family">Lim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jungyeul</namePart>
<namePart type="family">Park</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chulwoo</namePart>
<namePart type="family">Park</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="family">Boyd-Graber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present in this work a new Universal Morphology dataset for Korean. Previously, the Korean language has been underrepresented in the field of morphological paradigms amongst hundreds of diverse world languages. Hence, we propose this Universal Morphological paradigms for the Korean language that preserve its distinct characteristics. For our K-UniMorph dataset, we outline each grammatical criterion in detail for the verbal endings, clarify how to extract inflected forms, and demonstrate how we generate the morphological schemata. This dataset adopts morphological feature schema from CITATION and CITATION for the Korean language as we extract inflected verb forms from the Sejong morphologically analyzed corpus that is one of the largest annotated corpora for Korean. During the data creation, our methodology also includes investigating the correctness of the conversion from the Sejong corpus. Furthermore, we carry out the inflection task using three different Korean word forms: letters, syllables and morphemes. Finally, we discuss and describe future perspectives on Korean morphological paradigms and the dataset.</abstract>
<identifier type="citekey">jo-etal-2023-k</identifier>
<identifier type="doi">10.18653/v1/2023.findings-acl.414</identifier>
<location>
<url>https://aclanthology.org/2023.findings-acl.414</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>6613</start>
<end>6623</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T K-UniMorph: Korean Universal Morphology and its Feature Schema
%A Jo, Eunkyul
%A Kyuwon, Kim
%A Wu, Xihan
%A Lim, KyungTae
%A Park, Jungyeul
%A Park, Chulwoo
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%S Findings of the Association for Computational Linguistics: ACL 2023
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F jo-etal-2023-k
%X We present in this work a new Universal Morphology dataset for Korean. Previously, the Korean language has been underrepresented in the field of morphological paradigms amongst hundreds of diverse world languages. Hence, we propose this Universal Morphological paradigms for the Korean language that preserve its distinct characteristics. For our K-UniMorph dataset, we outline each grammatical criterion in detail for the verbal endings, clarify how to extract inflected forms, and demonstrate how we generate the morphological schemata. This dataset adopts morphological feature schema from CITATION and CITATION for the Korean language as we extract inflected verb forms from the Sejong morphologically analyzed corpus that is one of the largest annotated corpora for Korean. During the data creation, our methodology also includes investigating the correctness of the conversion from the Sejong corpus. Furthermore, we carry out the inflection task using three different Korean word forms: letters, syllables and morphemes. Finally, we discuss and describe future perspectives on Korean morphological paradigms and the dataset.
%R 10.18653/v1/2023.findings-acl.414
%U https://aclanthology.org/2023.findings-acl.414
%U https://doi.org/10.18653/v1/2023.findings-acl.414
%P 6613-6623
Markdown (Informal)
[K-UniMorph: Korean Universal Morphology and its Feature Schema](https://aclanthology.org/2023.findings-acl.414) (Jo et al., Findings 2023)
ACL