Downloads · 30 days
50
18% of all-time downloads
uk_ner_web_trf_best
dchaplinsky/uk_ner_web_trf_best
uk_ner_web_trf_best is a token classification model from dchaplinsky. Use it when you need labels on individual words, such as names. It is set up for spacy. The card lists the license as mit.
uknerwebtrfbest is a fine-tuned Roberta Large Ukrainian model that is ready to use for Named Entity Recognition and achieves a new SoA performance for the NER task for Ukrainian language. It outperforms another SpaCy…
All-time downloads
275
Public
Repo size
2.8 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
Other1.4 GB · 52%
At a glance
- Task
- Token Classification
- Library
- spacy
- License
- mit
- Access
- Public
- Created
- Apr 4, 2024
- Updated
- Apr 4, 2024
- SHA
- ecc737f3
Try a prompt
Datasets
Model card
From the Hugging Face model README
uk_ner_web_trf_best
Model description
uk_ner_web_trf_best is a fine-tuned Roberta Large Ukrainian model that is ready to use for Named Entity Recognition and achieves a new SoA performance for the NER task for Ukrainian language. It outperforms another SpaCy model, uk_core_news_trf on a NER task.
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 smaller transformer-based model for the SpaCy is available here.
Copyright: Dmytro Chaplynskyi, lang-uk project, 2023
- Task
- Token Classification
- Library
- spacy
- License
- mit
- Languages
- uk
- Created
- Apr 4, 2024
- Updated
- Apr 4, 2024