This study introduces a pretrained large language model-based annotation methodology for the first de dency treebank in Ottoman Turkish. Our experimental results show that, iteratively, i) pseudo-annotating data using a multilingual BERT-based parsing model, ii) manually correcting the pseudo-annotations, and iii) fine-tuning the parsing model with the corrected annotations, we speed up and simplify the challenging dependency annotation process. The resulting treebank, that will be a part of the Universal Dependencies (UD) project, will facilitate automated analysis of Ottoman Turkish documents, unlocking the linguistic richness embedded in this historical heritage.
@article{arxiv.2402.14743,
title = {Dependency Annotation of Ottoman Turkish with Multilingual BERT},
author = {Şaziye Betül Özateş and Tarık Emre Tıraş and Efe Eren Genç and Esma Fatıma Bilgin Taşdemir},
journal= {arXiv preprint arXiv:2402.14743},
year = {2024}
}