@inproceedings{matlatipov-aripov-2026-uzudt,
title = "{U}z{UDT}: {U}zbek {U}niversal {D}ependencies Treebank",
author = "Matlatipov, Sanatbek Gayratovich and
Aripov, Mersaid",
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.912/",
doi = "10.63317/2uedjqezjxn5",
pages = "11642--11649",
abstract = "In this paper, we present a new Universal Dependencies treebank for Uzbek language(UzUDT) developed as a gold-standard resource with full manual annotation. The treebank includes 684 sentences (7,582 tokens) from Uzbek literary texts, and is larger and more domain-diverse than the existing Uzbek UD treebank. The corpus was developed through rigorous multi-annotator adjudication, achieving very high inter-annotator agreement (multi-rater agreement coefficients {\ensuremath{>}}0.90) across lemmatization, PoS tagging, and morphological features. Alongside comprehensive corpus profiling, we establish robust computational baselines by evaluating graph-based (Stanza) and transition-based (spaCy) parsing architectures using both static and monolingual contextual embeddings. Our evaluations reveal a critical architectural trade-off for low-resource agglutinative parsing: joint transition-based models excel at morphosyntactic tagging, whereas graph-based models remain strictly superior for resolving complex structural dependencies. Furthermore, we demonstrate that cross-treebank data augmentation yields substantial, synergistic accuracy gains. The resource provides a much-needed high-quality treebank for Uzbek to assist in developing better NLP tools and to enable linguistic research in the low-resource language"
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="matlatipov-aripov-2026-uzudt">
<titleInfo>
<title>UzUDT: Uzbek Universal Dependencies Treebank</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sanatbek</namePart>
<namePart type="given">Gayratovich</namePart>
<namePart type="family">Matlatipov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mersaid</namePart>
<namePart type="family">Aripov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resource Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we present a new Universal Dependencies treebank for Uzbek language(UzUDT) developed as a gold-standard resource with full manual annotation. The treebank includes 684 sentences (7,582 tokens) from Uzbek literary texts, and is larger and more domain-diverse than the existing Uzbek UD treebank. The corpus was developed through rigorous multi-annotator adjudication, achieving very high inter-annotator agreement (multi-rater agreement coefficients \ensuremath>0.90) across lemmatization, PoS tagging, and morphological features. Alongside comprehensive corpus profiling, we establish robust computational baselines by evaluating graph-based (Stanza) and transition-based (spaCy) parsing architectures using both static and monolingual contextual embeddings. Our evaluations reveal a critical architectural trade-off for low-resource agglutinative parsing: joint transition-based models excel at morphosyntactic tagging, whereas graph-based models remain strictly superior for resolving complex structural dependencies. Furthermore, we demonstrate that cross-treebank data augmentation yields substantial, synergistic accuracy gains. The resource provides a much-needed high-quality treebank for Uzbek to assist in developing better NLP tools and to enable linguistic research in the low-resource language</abstract>
<identifier type="citekey">matlatipov-aripov-2026-uzudt</identifier>
<identifier type="doi">10.63317/2uedjqezjxn5</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.912/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>11642</start>
<end>11649</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T UzUDT: Uzbek Universal Dependencies Treebank
%A Matlatipov, Sanatbek Gayratovich
%A Aripov, Mersaid
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F matlatipov-aripov-2026-uzudt
%X In this paper, we present a new Universal Dependencies treebank for Uzbek language(UzUDT) developed as a gold-standard resource with full manual annotation. The treebank includes 684 sentences (7,582 tokens) from Uzbek literary texts, and is larger and more domain-diverse than the existing Uzbek UD treebank. The corpus was developed through rigorous multi-annotator adjudication, achieving very high inter-annotator agreement (multi-rater agreement coefficients \ensuremath>0.90) across lemmatization, PoS tagging, and morphological features. Alongside comprehensive corpus profiling, we establish robust computational baselines by evaluating graph-based (Stanza) and transition-based (spaCy) parsing architectures using both static and monolingual contextual embeddings. Our evaluations reveal a critical architectural trade-off for low-resource agglutinative parsing: joint transition-based models excel at morphosyntactic tagging, whereas graph-based models remain strictly superior for resolving complex structural dependencies. Furthermore, we demonstrate that cross-treebank data augmentation yields substantial, synergistic accuracy gains. The resource provides a much-needed high-quality treebank for Uzbek to assist in developing better NLP tools and to enable linguistic research in the low-resource language
%R 10.63317/2uedjqezjxn5
%U https://aclanthology.org/2026.lrec-1.912/
%U https://doi.org/10.63317/2uedjqezjxn5
%P 11642-11649
Markdown (Informal)
[UzUDT: Uzbek Universal Dependencies Treebank](https://aclanthology.org/2026.lrec-1.912/) (Matlatipov & Aripov, LREC 2026)
ACL
- Sanatbek Gayratovich Matlatipov and Mersaid Aripov. 2026. UzUDT: Uzbek Universal Dependencies Treebank. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 11642–11649, Palma de Mallorca, Spain. ELRA Language Resource Association.