Pretrained language models based on the Transformer architecture have achieved state-of-the-art results in various natural language processing tasks such as part-of-speech tagging, named entity recognition, and question answering. However, no such monolingual model for the Uzbek language is publicly available. In this paper, we introduce UzBERT, a pretrained Uzbek language model based on the BERT architecture. Our model greatly outperforms multilingual BERT on masked language model accuracy. We make the model publicly available under the MIT open-source license.
@article{arxiv.2108.09814,
title = {UzBERT: pretraining a BERT model for Uzbek},
author = {B. Mansurov and A. Mansurov},
journal= {arXiv preprint arXiv:2108.09814},
year = {2021}
}