uk_ner_web_trf_base
Model description
uk_ner_web_trf_base is a fine-tuned XLM-Roberta model that is ready to use for Named Entity Recognition and achieves a performance close to SoA for the NER task for Ukrainian language. 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. A bigger model, trained on xlm-roberta-large with the State-of-the-Art performance is available here.
Copyright: Dmytro Chaplynskyi, lang-uk project, 2022
- Downloads last month
- 14
Evaluation results
- NER Precisionself-reported0.899
- NER Recallself-reported0.881
- NER F Scoreself-reported0.890
!pip install https://huggingface.co/dchaplinsky/uk_ner_web_trf_base/resolve/main/uk_ner_web_trf_base-any-py3-none-any.whl # Using spacy.load(). import spacy nlp = spacy.load("uk_ner_web_trf_base") # Importing as module. import uk_ner_web_trf_base nlp = uk_ner_web_trf_base.load()