uk_ner_wechsel-minixhofer-roberta-large
Model description
uk_ner_wechsel-minixhofer-roberta-large is a fine-tuned Roberta-Large model by @benjamin that is ready to use for Named Entity Recognition and achieves a SoA performance for the NER task for Ukrainian language. That's the best I have for NER so far
It has been trained to recognize four types of entities: location (LOC), organizations (ORG), person (PERS) and Miscellaneous (MISC).
The model was fine-tuned on the NER-UK dataset, released by the lang-uk. Smaller transformer based model for the SpaCy is available here.
Copyright: Dmytro Chaplynskyi, lang-uk project, 2023
- Downloads last month
- -
Evaluation results
- NER Precisionself-reported0.928
- NER Recallself-reported0.913
- NER F Scoreself-reported0.920