@inproceedings{yilandiloglu-siewert-2025-dudu,
title = "{DUDU}: A Treebank for {O}ttoman {T}urkish in {UD} Style",
author = "Y{\i}landilo{\u{g}}lu, Enes and
Siewert, Janine",
editor = "Holdt, {\v{S}}pela Arhar and
Ilinykh, Nikolai and
Scalvini, Barbara and
Bruton, Micaella and
Debess, Iben Nyholm and
Tudor, Crina Madalina",
booktitle = "Proceedings of the Third Workshop on Resources and Representations for Under-Resourced Languages and Domains (RESOURCEFUL-2025)",
month = mar,
year = "2025",
address = "Tallinn, Estonia",
publisher = "University of Tartu Library, Estonia",
url = "https://aclanthology.org/2025.resourceful-1.16/",
pages = "74--79",
ISBN = "978-9908-53-121-2",
abstract = "This paper introduces a recently released Ottoman Turkish (ota) treebank in Universal Dependencies (UD) style, DUDU. The DUDU Treebank consists of 1,064 automatically annotated and manually corrected sentences. The texts were manually collected from various academic or literary sources available on the Internet. Following preprocessing, the sentences were annotated using a MaCHAMP-based neural network model utilizing the large language model (LLM) architecture and manually corrected. The treebank became publicly available with the 2.14 release, and future steps involve expanding the treebank with more data and refining the annotation scheme. The treebank is the first and only treebank that utilizes the IJMES transliteration alphabet. The treebank not only gives insight on Ottoman Turkish lexically, morphologically, and syntactically, but also provides a small but robust test set for future computational models for Ottoman Turkish."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yilandiloglu-siewert-2025-dudu">
<titleInfo>
<title>DUDU: A Treebank for Ottoman Turkish in UD Style</title>
</titleInfo>
<name type="personal">
<namePart type="given">Enes</namePart>
<namePart type="family">Yılandiloğlu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Janine</namePart>
<namePart type="family">Siewert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Third Workshop on Resources and Representations for Under-Resourced Languages and Domains (RESOURCEFUL-2025)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Špela</namePart>
<namePart type="given">Arhar</namePart>
<namePart type="family">Holdt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nikolai</namePart>
<namePart type="family">Ilinykh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="family">Scalvini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Micaella</namePart>
<namePart type="family">Bruton</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iben</namePart>
<namePart type="given">Nyholm</namePart>
<namePart type="family">Debess</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Crina</namePart>
<namePart type="given">Madalina</namePart>
<namePart type="family">Tudor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>University of Tartu Library, Estonia</publisher>
<place>
<placeTerm type="text">Tallinn, Estonia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">978-9908-53-121-2</identifier>
</relatedItem>
<abstract>This paper introduces a recently released Ottoman Turkish (ota) treebank in Universal Dependencies (UD) style, DUDU. The DUDU Treebank consists of 1,064 automatically annotated and manually corrected sentences. The texts were manually collected from various academic or literary sources available on the Internet. Following preprocessing, the sentences were annotated using a MaCHAMP-based neural network model utilizing the large language model (LLM) architecture and manually corrected. The treebank became publicly available with the 2.14 release, and future steps involve expanding the treebank with more data and refining the annotation scheme. The treebank is the first and only treebank that utilizes the IJMES transliteration alphabet. The treebank not only gives insight on Ottoman Turkish lexically, morphologically, and syntactically, but also provides a small but robust test set for future computational models for Ottoman Turkish.</abstract>
<identifier type="citekey">yilandiloglu-siewert-2025-dudu</identifier>
<location>
<url>https://aclanthology.org/2025.resourceful-1.16/</url>
</location>
<part>
<date>2025-03</date>
<extent unit="page">
<start>74</start>
<end>79</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DUDU: A Treebank for Ottoman Turkish in UD Style
%A Yılandiloğlu, Enes
%A Siewert, Janine
%Y Holdt, Špela Arhar
%Y Ilinykh, Nikolai
%Y Scalvini, Barbara
%Y Bruton, Micaella
%Y Debess, Iben Nyholm
%Y Tudor, Crina Madalina
%S Proceedings of the Third Workshop on Resources and Representations for Under-Resourced Languages and Domains (RESOURCEFUL-2025)
%D 2025
%8 March
%I University of Tartu Library, Estonia
%C Tallinn, Estonia
%@ 978-9908-53-121-2
%F yilandiloglu-siewert-2025-dudu
%X This paper introduces a recently released Ottoman Turkish (ota) treebank in Universal Dependencies (UD) style, DUDU. The DUDU Treebank consists of 1,064 automatically annotated and manually corrected sentences. The texts were manually collected from various academic or literary sources available on the Internet. Following preprocessing, the sentences were annotated using a MaCHAMP-based neural network model utilizing the large language model (LLM) architecture and manually corrected. The treebank became publicly available with the 2.14 release, and future steps involve expanding the treebank with more data and refining the annotation scheme. The treebank is the first and only treebank that utilizes the IJMES transliteration alphabet. The treebank not only gives insight on Ottoman Turkish lexically, morphologically, and syntactically, but also provides a small but robust test set for future computational models for Ottoman Turkish.
%U https://aclanthology.org/2025.resourceful-1.16/
%P 74-79
Markdown (Informal)
[DUDU: A Treebank for Ottoman Turkish in UD Style](https://aclanthology.org/2025.resourceful-1.16/) (Yılandiloğlu & Siewert, RESOURCEFUL 2025)
ACL
- Enes Yılandiloğlu and Janine Siewert. 2025. DUDU: A Treebank for Ottoman Turkish in UD Style. In Proceedings of the Third Workshop on Resources and Representations for Under-Resourced Languages and Domains (RESOURCEFUL-2025), pages 74–79, Tallinn, Estonia. University of Tartu Library, Estonia.