@inproceedings{yilandiloglu-2026-llms,
title = "{LLM}s in {O}ttoman {T}urkish: From {MLM} to {NER}",
author = "Y{\i}landilo{\u{g}}lu, Enes",
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-1.281/",
doi = "10.63317/2ttbxopqx25z",
pages = "3517--3522",
abstract = "This paper introduces three foundational contributions to Digital Ottoman Turkish Studies. It presents: (1) three masked language models (MLMs) trained on over 11 million words from 144 works spanning from the 15th to 20th century, (2) a state-of-the-art Named Entity Recognition (NER) model (F1 = 89.94{\%}) trained on 9,960 manually annotated entities, and (3) a state-of-the-art Universal Dependency (UD) parsing model for Ottoman Turkish. This work differs from others by deploying IJMES-transliterated documents for training and evaluation in order to prevent loss of information due to the change of the script from Perso-Arabic to Latin. The paper further explores probabilistic manuscript reconstruction in preliminary experiments, showing that MLMs can recover unread sections in historical documents with 77.8{\%} top-1 accuracy when a list of candidate words is provided. Followed by a discussion, the paper outlines the future directions as building century-aware MLMs and expanding the training data across genres to enhance model generalization."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yilandiloglu-2026-llms">
<titleInfo>
<title>LLMs in Ottoman Turkish: From MLM to NER</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>
<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>This paper introduces three foundational contributions to Digital Ottoman Turkish Studies. It presents: (1) three masked language models (MLMs) trained on over 11 million words from 144 works spanning from the 15th to 20th century, (2) a state-of-the-art Named Entity Recognition (NER) model (F1 = 89.94%) trained on 9,960 manually annotated entities, and (3) a state-of-the-art Universal Dependency (UD) parsing model for Ottoman Turkish. This work differs from others by deploying IJMES-transliterated documents for training and evaluation in order to prevent loss of information due to the change of the script from Perso-Arabic to Latin. The paper further explores probabilistic manuscript reconstruction in preliminary experiments, showing that MLMs can recover unread sections in historical documents with 77.8% top-1 accuracy when a list of candidate words is provided. Followed by a discussion, the paper outlines the future directions as building century-aware MLMs and expanding the training data across genres to enhance model generalization.</abstract>
<identifier type="citekey">yilandiloglu-2026-llms</identifier>
<identifier type="doi">10.63317/2ttbxopqx25z</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.281/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>3517</start>
<end>3522</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T LLMs in Ottoman Turkish: From MLM to NER
%A Yılandiloğlu, Enes
%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 yilandiloglu-2026-llms
%X This paper introduces three foundational contributions to Digital Ottoman Turkish Studies. It presents: (1) three masked language models (MLMs) trained on over 11 million words from 144 works spanning from the 15th to 20th century, (2) a state-of-the-art Named Entity Recognition (NER) model (F1 = 89.94%) trained on 9,960 manually annotated entities, and (3) a state-of-the-art Universal Dependency (UD) parsing model for Ottoman Turkish. This work differs from others by deploying IJMES-transliterated documents for training and evaluation in order to prevent loss of information due to the change of the script from Perso-Arabic to Latin. The paper further explores probabilistic manuscript reconstruction in preliminary experiments, showing that MLMs can recover unread sections in historical documents with 77.8% top-1 accuracy when a list of candidate words is provided. Followed by a discussion, the paper outlines the future directions as building century-aware MLMs and expanding the training data across genres to enhance model generalization.
%R 10.63317/2ttbxopqx25z
%U https://aclanthology.org/2026.lrec-1.281/
%U https://doi.org/10.63317/2ttbxopqx25z
%P 3517-3522
Markdown (Informal)
[LLMs in Ottoman Turkish: From MLM to NER](https://aclanthology.org/2026.lrec-1.281/) (Yılandiloğlu, LREC 2026)
ACL
- Enes Yılandiloğlu. 2026. LLMs in Ottoman Turkish: From MLM to NER. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 3517–3522, Palma de Mallorca, Spain. ELRA Language Resource Association.