This is a roBERTa model for Named Entity Recognition, fine-tuned on OntoNotes v5 using Spacy in coNLL-2003 format and BIO tagged.
For more details: https://github.com/nicoladisabato/ner-with-transformers
| Feature |
Description |
| Name |
en_roberta_fine_tuned_ner |
| Version |
0.0.0 |
| spaCy |
>=3.5.0,<3.6.0 |
| Default Pipeline |
transformer, ner |
| Components |
transformer, ner |
| Vectors |
0 keys, 0 unique vectors (0 dimensions) |
| Sources |
n/a |
| License |
n/a |
| Author |
Nicola Disabato |
Label Scheme
View label scheme (18 labels for 1 components)
| Component |
Labels |
ner |
CARDINAL, DATE, EVENT, FAC, GPE, LANGUAGE, LAW, LOC, MONEY, NORP, ORDINAL, ORG, PERCENT, PERSON, PRODUCT, QUANTITY, TIME, WORK_OF_ART |
Accuracy
| Type |
Score |
ENTS_F |
89.44 |
ENTS_P |
89.37 |
ENTS_R |
89.50 |
TRANSFORMER_LOSS |
294822.05 |
NER_LOSS |
316133.78 |
