The models were trained with COMBO boosted with either FastText embeddings or BERT models (english-bert-base, polish-herbert-base, and polish-herbert-large).
We list here only models trained on the Universal Dependencies version 2.7 dataset, check [COMBO models spreadsheet](https://docs.google.com/spreadsheets/d/1WFYc2aLRa1jw7le030HOacv9fc4zmtqiZtRQY6gl5mc/edit?usp=sharing)
for more.
|Treebank |Model name |UPOS |XPOS |UFeats|AllTags|Lemmas|UAS |LAS |CLAS |MLAS |BLEX |Language model |LICENSE |