@inproceedings{karagoz-etal-2024-towards,
title = "Towards a Clean Text Corpus for {O}ttoman {T}urkish",
author = {Karag{\"o}z, Fatih and
Do{\u{g}}an, Berat and
{\"O}zate{\c{s}}, {\c{S}}aziye Betül},
editor = {Ataman, Duygu and
Derin, Mehmet Oguz and
Ivanova, Sardana and
K{\"o}ksal, Abdullatif and
S{\"a}lev{\"a}, Jonne and
Zeyrek, Deniz},
booktitle = "Proceedings of the First Workshop on Natural Language Processing for Turkic Languages (SIGTURK 2024)",
month = aug,
year = "2024",
address = "Bangkok, Thailand and Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.sigturk-1.6",
pages = "62--70",
abstract = "Ottoman Turkish, as a historical variant of modern Turkish, suffers from a scarcity of available corpora and NLP models. This paper outlines our pioneering endeavors to address this gap by constructing a clean text corpus of Ottoman Turkish materials. We detail the challenges encountered in this process and offer potential solutions. Additionally, we present a case study wherein the created corpus is employed in continual pre-training of BERTurk, followed by evaluation of the model{'}s performance on the named entity recognition task for Ottoman Turkish. Preliminary experimental results suggest the effectiveness of our corpus in adapting existing models developed for modern Turkish to historical Turkish.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="karagoz-etal-2024-towards">
<titleInfo>
<title>Towards a Clean Text Corpus for Ottoman Turkish</title>
</titleInfo>
<name type="personal">
<namePart type="given">Fatih</namePart>
<namePart type="family">Karagöz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Berat</namePart>
<namePart type="family">Doğan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Şaziye</namePart>
<namePart type="given">Betül</namePart>
<namePart type="family">Özateş</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the First Workshop on Natural Language Processing for Turkic Languages (SIGTURK 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Duygu</namePart>
<namePart type="family">Ataman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mehmet</namePart>
<namePart type="given">Oguz</namePart>
<namePart type="family">Derin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sardana</namePart>
<namePart type="family">Ivanova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abdullatif</namePart>
<namePart type="family">Köksal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jonne</namePart>
<namePart type="family">Sälevä</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Deniz</namePart>
<namePart type="family">Zeyrek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand and Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Ottoman Turkish, as a historical variant of modern Turkish, suffers from a scarcity of available corpora and NLP models. This paper outlines our pioneering endeavors to address this gap by constructing a clean text corpus of Ottoman Turkish materials. We detail the challenges encountered in this process and offer potential solutions. Additionally, we present a case study wherein the created corpus is employed in continual pre-training of BERTurk, followed by evaluation of the model’s performance on the named entity recognition task for Ottoman Turkish. Preliminary experimental results suggest the effectiveness of our corpus in adapting existing models developed for modern Turkish to historical Turkish.</abstract>
<identifier type="citekey">karagoz-etal-2024-towards</identifier>
<location>
<url>https://aclanthology.org/2024.sigturk-1.6</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>62</start>
<end>70</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Towards a Clean Text Corpus for Ottoman Turkish
%A Karagöz, Fatih
%A Doğan, Berat
%A Özateş, Şaziye Betül
%Y Ataman, Duygu
%Y Derin, Mehmet Oguz
%Y Ivanova, Sardana
%Y Köksal, Abdullatif
%Y Sälevä, Jonne
%Y Zeyrek, Deniz
%S Proceedings of the First Workshop on Natural Language Processing for Turkic Languages (SIGTURK 2024)
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand and Online
%F karagoz-etal-2024-towards
%X Ottoman Turkish, as a historical variant of modern Turkish, suffers from a scarcity of available corpora and NLP models. This paper outlines our pioneering endeavors to address this gap by constructing a clean text corpus of Ottoman Turkish materials. We detail the challenges encountered in this process and offer potential solutions. Additionally, we present a case study wherein the created corpus is employed in continual pre-training of BERTurk, followed by evaluation of the model’s performance on the named entity recognition task for Ottoman Turkish. Preliminary experimental results suggest the effectiveness of our corpus in adapting existing models developed for modern Turkish to historical Turkish.
%U https://aclanthology.org/2024.sigturk-1.6
%P 62-70
Markdown (Informal)
[Towards a Clean Text Corpus for Ottoman Turkish](https://aclanthology.org/2024.sigturk-1.6) (Karagöz et al., SIGTURK-WS 2024)
ACL
- Fatih Karagöz, Berat Doğan, and Şaziye Betül Özateş. 2024. Towards a Clean Text Corpus for Ottoman Turkish. In Proceedings of the First Workshop on Natural Language Processing for Turkic Languages (SIGTURK 2024), pages 62–70, Bangkok, Thailand and Online. Association for Computational Linguistics.