<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yang-2025-shud">
    <titleInfo>
        <title>ShUD: the First Shanghainese Universal Dependency Treebank</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Qizhen</namePart>
        <namePart type="family">Yang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2025-08</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the Eighth Workshop on Universal Dependencies (UDW, SyntaxFest 2025)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Gosse</namePart>
            <namePart type="family">Bouma</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Çağrı</namePart>
            <namePart type="family">Çöltekin</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Ljubljana, Slovenia</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
        <identifier type="isbn">979-8-89176-292-3</identifier>
    </relatedItem>
    <abstract>This paper introduces ShUD, the first Universal Dependencies (UD) treebank for Shanghainese, a Wu Chinese variant spoken by approximately 14 million people but severely under-resourced in NLP. The treebank is built through a scalable annotation pipeline that exploits grammatical parallels between Shanghainese and Mandarin. Our pipeline also provides a practical strategy for bootstrapping resources for other Chinese dialects. We documented syntactic phenomena unique to Shanghainese within the UD framework and fine-tuned a dependency parser using our annotated treebank, contributing a foundation to both NLP tool development and cross-linguistic syntactic research.</abstract>
    <identifier type="citekey">yang-2025-shud</identifier>
    <location>
        <url>https://aclanthology.org/2025.udw-1.20/</url>
    </location>
    <part>
        <date>2025-08</date>
        <extent unit="page">
            <start>186</start>
            <end>193</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T ShUD: the First Shanghainese Universal Dependency Treebank
%A Yang, Qizhen
%Y Bouma, Gosse
%Y Çöltekin, Çağrı
%S Proceedings of the Eighth Workshop on Universal Dependencies (UDW, SyntaxFest 2025)
%D 2025
%8 August
%I Association for Computational Linguistics
%C Ljubljana, Slovenia
%@ 979-8-89176-292-3
%F yang-2025-shud
%X This paper introduces ShUD, the first Universal Dependencies (UD) treebank for Shanghainese, a Wu Chinese variant spoken by approximately 14 million people but severely under-resourced in NLP. The treebank is built through a scalable annotation pipeline that exploits grammatical parallels between Shanghainese and Mandarin. Our pipeline also provides a practical strategy for bootstrapping resources for other Chinese dialects. We documented syntactic phenomena unique to Shanghainese within the UD framework and fine-tuned a dependency parser using our annotated treebank, contributing a foundation to both NLP tool development and cross-linguistic syntactic research.
%U https://aclanthology.org/2025.udw-1.20/
%P 186-193

Markdown (Informal)

[ShUD: the First Shanghainese Universal Dependency Treebank](https://aclanthology.org/2025.udw-1.20/) (Yang, UDW-SyntaxFest 2025)

• ShUD: the First Shanghainese Universal Dependency Treebank (Yang, UDW-SyntaxFest 2025)

ACL

• Qizhen Yang. 2025. ShUD: the First Shanghainese Universal Dependency Treebank. In Proceedings of the Eighth Workshop on Universal Dependencies (UDW, SyntaxFest 2025), pages 186–193, Ljubljana, Slovenia. Association for Computational Linguistics.