# Domain-specific BERT

The first transformer model trained on historical texts from Denmark's Absolute Monarchy period (1660-1849), developed by researchers at Aalborg University for processing historical texts with significant differences from modern Danish.

A BERT sentence vector transformation model optimized for the financial and regulatory domain, trained on SEC documents

A pre-trained BERT model for Korean medical NLP, based on the KR-BERT architecture, pre-trained on a 116-million-word Korean medical corpus

This is a BERT model optimized for the agricultural domain, trained using MLM (Masked Language Model) self-supervised learning methods.

Legalbert-pt is a language model specialized for the Portuguese legal domain through pre-training, which can be fine-tuned for specific tasks.

BiomedBERT is a biomedical domain-specific language model pretrained on PubMed abstracts and PubMedCentral full-text articles, achieving state-of-the-art performance in multiple biomedical NLP tasks.