We currently have indexed 37 BERT-based models,
21 Languages and 33 Tasks.
We have a total of 212 entries in this table; we also show
Multilingual Bert (mBERT) results if available! (see our paper)
Curious which BERT model is the best for named entity recognition in Italian? Just type "Italian NER" in the search bar!
Do you want to add your model or update some rows? Click Here
What the [MASK]? Making Sense of Language-Specific BERT Models
@article{nozza2020what, title={What the [MASK]? Making Sense of Language-Specific BERT Models}, author={Nozza, Debora and Bianchi, Federico and Hovy, Dirk}, journal={arXiv preprint arXiv:2003.02912}, year={2020} }
This is a collaborative resource to help researchers understand and find the best BERT model for a given dataset, task and language. The numbers here rely on self reported performance (we can give no guarantees for their accuracy. In the future, we hope to independently verify each of the models).
Do you want to add your model? Click Here