This paper advances NLP research for the low-resource Uzbek language by evaluating two previously untested monolingual Uzbek BERT models on the part-of-speech (POS) tagging task and introducing the first publicly available UPOS-tagged benchmark dataset for Uzbek. Our fine-tuned models achieve 91% average accuracy, outperforming the baseline multi-lingual BERT as well as the rule-based tagger. Notably, these models capture intermediate POS changes through affixes and demonstrate context sensitivity, unlike existing rule-based taggers.
@article{arxiv.2501.10107,
title = {BBPOS: BERT-based Part-of-Speech Tagging for Uzbek},
author = {Latofat Bobojonova and Arofat Akhundjanova and Phil Ostheimer and Sophie Fellenz},
journal= {arXiv preprint arXiv:2501.10107},
year = {2025}
}