# Historical text mining

LatinBERT is a Latin language pre-trained model based on BERT architecture

The first and only available subword BERT model for Ancient Greek, achieving state-of-the-art fine-tuned performance in part-of-speech tagging and morphological analysis tasks.

NB-BERT Base is a general-purpose BERT base model built on the extensive digital collections of the National Library of Norway, supporting Norwegian text processing.