@inproceedings{plum-etal-2024-luxbank,
title = "{L}ux{B}ank: The First {U}niversal {D}ependency Treebank for {L}uxembourgish",
author = {Plum, Alistair and
D{\"o}hmer, Caroline and
Milano, Emilia and
Lutgen, Anne-Marie and
Purschke, Christoph},
editor = {Dakota, Daniel and
Jablotschkin, Sarah and
K{\"u}bler, Sandra and
Zinsmeister, Heike},
booktitle = "Proceedings of the 22nd Workshop on Treebanks and Linguistic Theories (TLT 2024)",
month = dec,
year = "2024",
address = "Hamburg,Germany",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.tlt-1.4/",
pages = "30--39",
abstract = "The Universal Dependencies (UD) project has significantly expanded linguistic coverage across 161 languages, yet Luxembourgish, a West Germanic language spoken by approximately 400,000 people, has remained absent until now. In this paper, we introduce LuxBank, the first UD Treebank for Luxembourgish, addressing the gap in syntactic annotation and analysis for this {\textquoteleft}low-research' language. We establish formal guidelines for Luxembourgish language annotation, providing the foundation for the first large-scale quantitative analysis ofits syntax. LuxBank serves not only as a resource for linguists and language learners but also as a tool for developing spell checkers and grammar checkers, organising existing text archives and even training large language models. By incorporating Luxembourgish into the UD framework, we aim to enhance the understanding of syntactic variation within West Germanic languages and offer a model for documenting smaller, semi-standardised languages. This work positions Luxembourgish as a valuable resource in the broader linguistic and NLP communities, contributing to the study of languages with limited research and resources."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="plum-etal-2024-luxbank">
<titleInfo>
<title>LuxBank: The First Universal Dependency Treebank for Luxembourgish</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alistair</namePart>
<namePart type="family">Plum</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Caroline</namePart>
<namePart type="family">Döhmer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Emilia</namePart>
<namePart type="family">Milano</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anne-Marie</namePart>
<namePart type="family">Lutgen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christoph</namePart>
<namePart type="family">Purschke</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 22nd Workshop on Treebanks and Linguistic Theories (TLT 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Dakota</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sarah</namePart>
<namePart type="family">Jablotschkin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sandra</namePart>
<namePart type="family">Kübler</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Heike</namePart>
<namePart type="family">Zinsmeister</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hamburg,Germany</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The Universal Dependencies (UD) project has significantly expanded linguistic coverage across 161 languages, yet Luxembourgish, a West Germanic language spoken by approximately 400,000 people, has remained absent until now. In this paper, we introduce LuxBank, the first UD Treebank for Luxembourgish, addressing the gap in syntactic annotation and analysis for this ‘low-research’ language. We establish formal guidelines for Luxembourgish language annotation, providing the foundation for the first large-scale quantitative analysis ofits syntax. LuxBank serves not only as a resource for linguists and language learners but also as a tool for developing spell checkers and grammar checkers, organising existing text archives and even training large language models. By incorporating Luxembourgish into the UD framework, we aim to enhance the understanding of syntactic variation within West Germanic languages and offer a model for documenting smaller, semi-standardised languages. This work positions Luxembourgish as a valuable resource in the broader linguistic and NLP communities, contributing to the study of languages with limited research and resources.</abstract>
<identifier type="citekey">plum-etal-2024-luxbank</identifier>
<location>
<url>https://aclanthology.org/2024.tlt-1.4/</url>
</location>
<part>
<date>2024-12</date>
<extent unit="page">
<start>30</start>
<end>39</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T LuxBank: The First Universal Dependency Treebank for Luxembourgish
%A Plum, Alistair
%A Döhmer, Caroline
%A Milano, Emilia
%A Lutgen, Anne-Marie
%A Purschke, Christoph
%Y Dakota, Daniel
%Y Jablotschkin, Sarah
%Y Kübler, Sandra
%Y Zinsmeister, Heike
%S Proceedings of the 22nd Workshop on Treebanks and Linguistic Theories (TLT 2024)
%D 2024
%8 December
%I Association for Computational Linguistics
%C Hamburg,Germany
%F plum-etal-2024-luxbank
%X The Universal Dependencies (UD) project has significantly expanded linguistic coverage across 161 languages, yet Luxembourgish, a West Germanic language spoken by approximately 400,000 people, has remained absent until now. In this paper, we introduce LuxBank, the first UD Treebank for Luxembourgish, addressing the gap in syntactic annotation and analysis for this ‘low-research’ language. We establish formal guidelines for Luxembourgish language annotation, providing the foundation for the first large-scale quantitative analysis ofits syntax. LuxBank serves not only as a resource for linguists and language learners but also as a tool for developing spell checkers and grammar checkers, organising existing text archives and even training large language models. By incorporating Luxembourgish into the UD framework, we aim to enhance the understanding of syntactic variation within West Germanic languages and offer a model for documenting smaller, semi-standardised languages. This work positions Luxembourgish as a valuable resource in the broader linguistic and NLP communities, contributing to the study of languages with limited research and resources.
%U https://aclanthology.org/2024.tlt-1.4/
%P 30-39
Markdown (Informal)
[LuxBank: The First Universal Dependency Treebank for Luxembourgish](https://aclanthology.org/2024.tlt-1.4/) (Plum et al., TLT 2024)
ACL