BERT fine-tuned for Named Entity Recognition in Danish

The model tags tokens (in Danish sentences) with named entity tags (BIO format) [PER, ORG, LOC, MISC]. The pretrained language model used for fine-tuning is the Danish BERT by BotXO.

See the DaNLP documentation for more details.

Here is how to use the model:

from transformers import BertTokenizer, BertForTokenClassification

model = BertForTokenClassification.from_pretrained("alexandrainst/da-ner-base")
tokenizer = BertTokenizer.from_pretrained("alexandrainst/da-ner-base")

Training Data

The model has been trained on the DaNE .