SpaCy NER models
Collection
5 items • Updated
| Feature | Description |
|---|---|
| Name | fr_ner4archives_v3_with_vectors |
| Version | 0.0.0 |
| spaCy | >=3.4.1,<3.5.0 |
| Default Pipeline | tok2vec, ner |
| Components | tok2vec, ner |
| Vectors | 500000 keys, 500000 unique vectors (300 dimensions) |
| Sources | French corpus for the NER task composed of finding aids in XML-EAD from the National Archives of France (v. 3.0) - Check corpus version on GitHub |
| License | CC-BY-4.0 license |
| Author | Archives nationales / Inria-Almanach |
Label Scheme
View label scheme (5 labels for 1 components)
| Component | Labels |
|---|---|
ner |
EVENT, LOCATION, ORGANISATION, PERSON, TITLE |
Accuracy
| Type | Score |
|---|---|
ENTS_F |
86.56 |
ENTS_P |
88.30 |
ENTS_R |
84.90 |
TOK2VEC_LOSS |
13527.63 |
NER_LOSS |
58805.82 |
- Downloads last month
- 12
Collection including ner4archives/fr_ner4archives_v3_with_vectors
Evaluation results
- NER Precisionself-reported0.883
- NER Recallself-reported0.849
- NER F Scoreself-reported0.866