A BERT pre-trained language model for an ancient greek language.

We used GreekBERT from @nlpaueb and fine-tuned it with the MLM objective on several corpora of ancient greek texts. Later, we used it to train several classifiers to assist an author and style attribution of a couple of recently discovered texts.

If you use the model, please cite the following:

@inproceedings{Yamshchikov-etal-2022-plutarch,
    title = "BERT in Plutarch’s Shadows",
    author = "Ivan P. Yamshchikov and
      Alexey Tikhonov  and
      Yorgos Pantis  and
      Charlotte Schubert  and
      J{\"u}rgen Jost",
    booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing",
    year = "2022",
}