@inproceedings{taguchi-chiang-2023-introducing,
title = "Introducing Morphology in {U}niversal {D}ependencies {J}apanese",
author = "Taguchi, Chihiro and
Chiang, David",
editor = {Grobol, Lo{\"\i}c and
Tyers, Francis},
booktitle = "Proceedings of the Sixth Workshop on Universal Dependencies (UDW, GURT/SyntaxFest 2023)",
month = mar,
year = "2023",
address = "Washington, D.C.",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.udw-1.8",
pages = "65--72",
abstract = "This paper discusses the need for including morphological features in Japanese Universal Dependencies (UD). In the current version (v2.11) of the Japanese UD treebanks, sentences are tokenized at the morpheme level, and almost no morphological feature annotation is used. However, Japanese is not an isolating language that lacks morphological inflection but is an agglutinative language. Given this situation, we introduce a tentative scheme for retokenization and morphological feature annotation for Japanese UD. Then, we measure and compare the morphological complexity of Japanese with other languages to demonstrate that the proposed tokenizations show similarities to synthetic languages reflecting the linguistic typology.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="taguchi-chiang-2023-introducing">
<titleInfo>
<title>Introducing Morphology in Universal Dependencies Japanese</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chihiro</namePart>
<namePart type="family">Taguchi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Chiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth Workshop on Universal Dependencies (UDW, GURT/SyntaxFest 2023)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Loïc</namePart>
<namePart type="family">Grobol</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Francis</namePart>
<namePart type="family">Tyers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Washington, D.C.</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper discusses the need for including morphological features in Japanese Universal Dependencies (UD). In the current version (v2.11) of the Japanese UD treebanks, sentences are tokenized at the morpheme level, and almost no morphological feature annotation is used. However, Japanese is not an isolating language that lacks morphological inflection but is an agglutinative language. Given this situation, we introduce a tentative scheme for retokenization and morphological feature annotation for Japanese UD. Then, we measure and compare the morphological complexity of Japanese with other languages to demonstrate that the proposed tokenizations show similarities to synthetic languages reflecting the linguistic typology.</abstract>
<identifier type="citekey">taguchi-chiang-2023-introducing</identifier>
<location>
<url>https://aclanthology.org/2023.udw-1.8</url>
</location>
<part>
<date>2023-03</date>
<extent unit="page">
<start>65</start>
<end>72</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Introducing Morphology in Universal Dependencies Japanese
%A Taguchi, Chihiro
%A Chiang, David
%Y Grobol, Loïc
%Y Tyers, Francis
%S Proceedings of the Sixth Workshop on Universal Dependencies (UDW, GURT/SyntaxFest 2023)
%D 2023
%8 March
%I Association for Computational Linguistics
%C Washington, D.C.
%F taguchi-chiang-2023-introducing
%X This paper discusses the need for including morphological features in Japanese Universal Dependencies (UD). In the current version (v2.11) of the Japanese UD treebanks, sentences are tokenized at the morpheme level, and almost no morphological feature annotation is used. However, Japanese is not an isolating language that lacks morphological inflection but is an agglutinative language. Given this situation, we introduce a tentative scheme for retokenization and morphological feature annotation for Japanese UD. Then, we measure and compare the morphological complexity of Japanese with other languages to demonstrate that the proposed tokenizations show similarities to synthetic languages reflecting the linguistic typology.
%U https://aclanthology.org/2023.udw-1.8
%P 65-72
Markdown (Informal)
[Introducing Morphology in Universal Dependencies Japanese](https://aclanthology.org/2023.udw-1.8) (Taguchi & Chiang, UDW-SyntaxFest 2023)
ACL