Elamur Research⌕
☰
home / papers / 2026 / RuznamceNER: A Named Entity Recognition Dataset for Ottoman Turkish

RuznamceNER: A Named Entity Recognition Dataset for Ottoman Turkish

Summary

Detecting names in historical documents is difficult because older forms of a language differ from modern ones in spelling, vocabulary and orthography, and annotated historical data are rare. This paper addresses the problem for Ottoman Turkish. It focuses on kazasker ruznamçe registers, which are handwritten Ottoman records of the appointment, dismissal and promotion of judges (kadı) and scholars (müderris). Historians have so far studied these registers mostly by hand, and NLP work on them is almost absent. The authors build RuznamceNER, a manually labeled NER corpus drawn from ruznamçe documents covering about two hundred years. It marks persons, locations and organizations. As a baseline, they fine-tune a BERT-CRF model pre-trained on modern Turkish and compare several training setups on the dataset's test split. The experiments show that in-domain supervision is decisive. Even a modest amount of annotated ruznamçe text lets the model perform robustly on these fairly formulaic records, despite the large lexical and spelling gap from modern Turkish. The resource enables automated, large-scale processing of hundreds of register volumes and other unprocessed historical Turkish texts.

Key points

  • Dataset size: RuznamceNER has 2,138 sentences with 8,730 annotated entities. The three entity types are PERSON, LOCATION and ORGANIZATION.
  • Source material: The texts come from the Anatolian and Rumelian chief-judge registers. About 167 Anatolian and 261 Rumelian volumes are known, and the earliest surviving register dates to 1544. The originals are handwritten in Arabic-based Ottoman script.
  • Baseline model: The baseline is a BERT-CRF model with modern Turkish pre-training, tested under several training configurations. The main finding is that a small amount of in-domain labeled data yields strong results on well-structured text. Exact per-configuration scores are in the paper's results section, which was not included in the provided text.
  • Availability: The dataset and the trained model are public at huggingface.co/datasets/BUCOLIN/RuznamceNER.
  • Prior work: The earlier historical Turkish NER dataset (Özateş et al., 2025) had 660 sentences, and a fine-tuned model reached 91.21% F1 on it. RuznamceNER is substantially larger and specific to one domain.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

Fields: Linguistics & languages

Topics: Named entity recognition

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.63317/24exq9vqk5qx

@inproceedings{tasdemir2026ruznamcener,
  title = {{RuznamceNER: A Named Entity Recognition Dataset for Ottoman Turkish}},
  author = {Tasdemir, Esma Fatıma Bilgin and Gürer, Dilara Zeynep and Ozates, Saziye Betul},
  booktitle = {Proceedings of the Fifteenth Language Resources and Evaluation Conference},
  year = {2026},
  doi = {10.63317/24exq9vqk5qx},
  url = {https://doi.org/10.63317/24exq9vqk5qx}
}

References

28 references, 0 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Gizem Aras, Didem Makaroğlu, Seniz Demir, and Altan Cakir. 2021. An evaluation of recent neural sequence tagging models in Turkish named entity recognition. Expert systems with applications, 182:115049. find
  2. Baptiste Blouin, Cécile Armand, and Christian Henriot. 2024. A dataset for named entity recognition and entity linking in Chinese historical newspapers. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation, LREC/COLING 2024, 20-25… find
  3. Buse Çarık and Reyyan Yeniterzi. 2022. A twitter corpus for named entity recognition in Turkish. In Proceedings of the Thirteenth Language Resources and Evaluation Conference, LREC 2022, Marseille, France, 20-25 June 2022, pages 4546–4551. European Language Resources Association. find
  4. Yuan Chang, Lei Kong, Kejia Jia, and Qinglei Meng. 2021. Chinese named entity recognition method based on BERT. In 2021 IEEE International Conference on Data Science and Computer Application (ICDSCA), pages 294–299. find
  5. Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies,… find
  6. Maud Ehrmann, Ahmed Hamdi, Elvys Linhares Pontes, Matteo Romanello, and Antoine Doucet. 2024. Named entity recognition and classification in historical documents: A survey. ACM Computing Surveys, 56(2):27:1–27:47. find
  7. İsmail Gündoğdu. 2009. The daybooks of chief justice’s as a historical sources of the Ottoman empire and their significance. Journal of Human Sciences, 6(2):697–722. find
  8. 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. find
  9. Levent Kuru. 2020. XVIII. yüzyılın İlk yarısında Rumeli kazaları ve statüleri (kazasker ruz-namçelerine göre). Turkish Studies – Historical Analysis, 15(1):161–191. find
  10. Büşra Aktaş Kütükçü. 2022. 1 Numaralı Anadolu Kazaskerliği Ruznamçesi. Yeditepe Akademi, İstanbul. find
  11. John D. Lafferty, Andrew McCallum, and Fernando C. N. Pereira. 2001. Conditional random fields: Probabilistic models for segmenting and labeling sequence data. In Proceedings of the Eighteenth International Conference on Machine Learning, ICML ’01, page 282–289, San Francisco, CA, USA. Morgan Kaufma… find
  12. Hongli Mao, Xian-Ling Mao, Hanlin Tang, Yu-Ming Shang, and Heyan Huang. 2024. Span graph transformer for document-level named entity recognition. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 38, pages 18769–18777. find
  13. Binling Nie, Ruixue Ding, Pengjun Xie, Fei Huang, Chen Qian, and Luo Si. 2021. Knowledge-aware named entity recognition with alleviating heterogeneity. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 35, pages 13595–13603. find
  14. Siim Orasmaa, Kadri Muischnek, Kristjan Poska, and Anna Edela. 2022. Named entity recognition in Estonian 19th century parish court records. In Proceedings of the Thirteenth Language Resources and Evaluation Conference, pages 5304–5313. find
  15. Şaziye Betül Özateş, Tarık Tıraş, Efe Genç, and Esma Bilgin Tasdemir. 2024. Dependency annotation of Ottoman Turkish with multilingual BERT. In Proceedings of the 18th Linguistic Annotation Workshop (LAW-XVIII), pages 188–196, St. Julians, Malta. Association for Computational Linguistics. find
  16. Saziye Betül Özates, Tarik Emre Tiras, Ece Elif Adak, Berat Dogan, Fatih Burak Karagöz, Efe Eren Genç, and Esma F. Bilgin Tasdemir. 2025. Building foundations for natural language processing of historical Turkish: Resources and models. CoRR, abs/2501.04828. — [arXiv:2501.04828](https://arxiv.org/abs/2501.04828) find
  17. Oguzhan Ozcelik and Cagri Toraman. 2022. Named entity recognition in Turkish: A comparative study with detailed error analysis. Information Processing and Management, 59(6):103065. find
  18. Nita Patil, Ajay S Patil, and BV Pawar. 2016. Survey of named entity recognition systems with respect to Indian and foreign languages. International Journal of Computer Applications, 134(16). find
  19. Yunfei Qiu, Libo Dong, Wenwen Zhang, Haoran Xing, and Junwei Huang. 2025. A diffusion enhanced crf and bilstm framework for accurate entity recognition. Scientific Reports, 15(1):19670. find
  20. Ahmed Cheikh Rouhou, Marwa Dhiaf, Yousri Kessentini, and Sinda Ben Salem. 2022. Transformer-based approach for joint handwriting and named entity recognition in historical document. Pattern Recognition Letters, 155:128– 134. find
  21. Stefan Schweter. 2020. BERTurk - BERT models for Turkish. find
  22. Khaled Shaalan. 2014. A survey of Arabic named entity recognition and classification. Computational Linguistics, 40(2):469–510. find
  23. Fábio Souza, Rodrigo Nogueira, and Roberto Lotufo. 2019. Portuguese named entity recognition using BERT-CRF. find
  24. Rachele Sprugnoli. 2018. Arretium or arezzo? A neural approach to the identification of place names in historical texts. In Proceedings of the Fifth Italian Conference on Computational Linguistics (CLiC-it 2018), Torino, Italy, December 10-12, 2018, volume 2253 of CEUR Workshop Proceedings. CEUR-WS.… find
  25. Konstantin Todorov and Giovanni Colavizza. 2020. Transfer learning for named entity recognition in historical corpora. In Working Notes of CLEF 2020 - Conference and Labs of the Evaluation Forum, Thessaloniki, Greece, September 22-25, 2020, volume 2696 of CEUR Workshop Proceedings. CEUR-WS.org. find
  26. Gökhan Tür, Dilek Hakkani-Tür, and Kemal Oflazer. 2003. A statistical information extraction system for Turkish. Natural Language Engineering, 9(2):181–210. find
  27. Gökçe Uludoğan, Zeynep Balal, Furkan Akkurt, Meliksah Turker, Onur Gungor, and Susan Üsküdarlı. 2024. TURNA: A Turkish encoder-decoder language model for enhanced understanding and generation. In Findings of the Association for Computational Linguistics: ACL 2024, pages 10103–10117, Bangkok, Thailan… find
  28. Arda Uzunoglu and Gözde Şahin. 2023. Benchmarking procedural language understanding for low-resource languages: A case study on Turkish. In Proceedings of the 13th International Joint Conference on Natural Language Processing and the 3rd Conference of the Asia-Pacific Chapter of the Association for… find

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/tasdemir-2026-ruznamcener-named-entity-recognition-dataset/