Building Foundations for Natural Language Processing of Historical Turkish: Resources and Models

TL;DR

This paper develops foundational NLP resources and transformer models for historical Turkish, including datasets, a corpus, and benchmarks, to advance computational analysis of this underexplored language domain.

Contribution

It introduces the first NER dataset, Universal Dependencies treebank, and a transliterated corpus for historical Turkish, along with trained models for key NLP tasks.

Findings

Achieved 90.29% F1 in NER

Attained 73.79% LAS in dependency parsing

Reached 94.98% F1 in POS tagging

Abstract

This paper introduces foundational resources and models for natural language processing (NLP) of historical Turkish, a domain that has remained underexplored in computational linguistics. We present the first named entity recognition (NER) dataset, HisTR, and the first Universal Dependencies treebank, OTA-BOUN, for a historical form of the Turkish language along with transformer-based models trained using these datasets for named entity recognition, dependency parsing, and part-of-speech tagging tasks. Furthermore, we introduce the Ottoman Text Corpus (OTC), a clean corpus of transliterated historical Turkish texts that spans a wide range of historical periods. Our experimental results demonstrate prominent improvements in the computational analysis of historical Turkish, achieving strong performance on tasks that require understanding of historical linguistic structures -- specifically, 90.29% F1 in named entity recognition, 73.79% LAS for dependency parsing, and 94.98% F1 for part-of-speech tagging. They also highlight existing challenges, such as domain adaptation and language variations between time periods. All the resources and models presented are available at https://hf.co/bucolin to serve as a benchmark for future progress in historical Turkish NLP.