@inproceedings{tiras-etal-2026-ota,
title = "{OTA}-{BOUN}: A Historical {T}urkish Dependency Treebank",
author = {T{\i}ra{\c{s}}, Tar{\i}k Emre and
{\"U}nal, Nureddin C{\"u}neyd and
Cengiz, Ada and
Yurtseven, Ece and
Ta{\c{s}}demir, Esma F. Bilgin and
Ozates, Saziye Betul},
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-1.551/",
doi = "10.63317/3d985kzhy84r",
pages = "6929--6938",
abstract = "We present OTA-BOUN v2.0, the largest Universal Dependencies treebank for historical Turkish, consisting of 1,742 manually verified sentences sampled from late Ottoman texts. The annotation process followed a semi-automatic methodology: initial pre-annotation by the UDPipe 2.0 pipeline was refined through manual annotation of dependency relations, part-of-speech tags, and lemmas. A distinctive feature of OTA-BOUN is its dual-script representation: each sentence is provided both in the original Perso-Arabic script and its Latinized transcription, while tokens include aligned forms in both scripts. This dual-layer design enables research on script conversion, cross-lingual transfer, and historical{--}modern Turkish comparisons. Through detailed analyses on the aforementioned treebank, this study presents a unique and scalable resource, advancing computational studies of historical Turkish and supporting broader efforts in multilingual and diachronic NLP."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tiras-etal-2026-ota">
<titleInfo>
<title>OTA-BOUN: A Historical Turkish Dependency Treebank</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tarık</namePart>
<namePart type="given">Emre</namePart>
<namePart type="family">Tıraş</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nureddin</namePart>
<namePart type="given">Cüneyd</namePart>
<namePart type="family">Ünal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ada</namePart>
<namePart type="family">Cengiz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ece</namePart>
<namePart type="family">Yurtseven</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Esma</namePart>
<namePart type="given">F</namePart>
<namePart type="given">Bilgin</namePart>
<namePart type="family">Taşdemir</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Saziye</namePart>
<namePart type="given">Betul</namePart>
<namePart type="family">Ozates</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>We present OTA-BOUN v2.0, the largest Universal Dependencies treebank for historical Turkish, consisting of 1,742 manually verified sentences sampled from late Ottoman texts. The annotation process followed a semi-automatic methodology: initial pre-annotation by the UDPipe 2.0 pipeline was refined through manual annotation of dependency relations, part-of-speech tags, and lemmas. A distinctive feature of OTA-BOUN is its dual-script representation: each sentence is provided both in the original Perso-Arabic script and its Latinized transcription, while tokens include aligned forms in both scripts. This dual-layer design enables research on script conversion, cross-lingual transfer, and historical–modern Turkish comparisons. Through detailed analyses on the aforementioned treebank, this study presents a unique and scalable resource, advancing computational studies of historical Turkish and supporting broader efforts in multilingual and diachronic NLP.</abstract>
<identifier type="citekey">tiras-etal-2026-ota</identifier>
<identifier type="doi">10.63317/3d985kzhy84r</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.551/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>6929</start>
<end>6938</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T OTA-BOUN: A Historical Turkish Dependency Treebank
%A Tıraş, Tarık Emre
%A Ünal, Nureddin Cüneyd
%A Cengiz, Ada
%A Yurtseven, Ece
%A Taşdemir, Esma F. Bilgin
%A Ozates, Saziye Betul
%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 tiras-etal-2026-ota
%X We present OTA-BOUN v2.0, the largest Universal Dependencies treebank for historical Turkish, consisting of 1,742 manually verified sentences sampled from late Ottoman texts. The annotation process followed a semi-automatic methodology: initial pre-annotation by the UDPipe 2.0 pipeline was refined through manual annotation of dependency relations, part-of-speech tags, and lemmas. A distinctive feature of OTA-BOUN is its dual-script representation: each sentence is provided both in the original Perso-Arabic script and its Latinized transcription, while tokens include aligned forms in both scripts. This dual-layer design enables research on script conversion, cross-lingual transfer, and historical–modern Turkish comparisons. Through detailed analyses on the aforementioned treebank, this study presents a unique and scalable resource, advancing computational studies of historical Turkish and supporting broader efforts in multilingual and diachronic NLP.
%R 10.63317/3d985kzhy84r
%U https://aclanthology.org/2026.lrec-1.551/
%U https://doi.org/10.63317/3d985kzhy84r
%P 6929-6938
Markdown (Informal)
[OTA-BOUN: A Historical Turkish Dependency Treebank](https://aclanthology.org/2026.lrec-1.551/) (Tıraş et al., LREC 2026)
ACL
- Tarık Emre Tıraş, Nureddin Cüneyd Ünal, Ada Cengiz, Ece Yurtseven, Esma F. Bilgin Taşdemir, and Saziye Betul Ozates. 2026. OTA-BOUN: A Historical Turkish Dependency Treebank. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 6929–6938, Palma de Mallorca, Spain. ELRA Language Resource Association.