spacy-models
Collection
German spaCy models trained on German UD-HDT and on a collection of gold and silver standard NER corpora
•
6 items
•
Updated
| Feature | Description |
|---|---|
| Name | de_wikiner_lg |
| Version | 1.0.0 |
| spaCy | >=3.8.7,<3.9.0 |
| Default Pipeline | tok2vec, ner |
| Components | tok2vec, ner |
| Vectors | 500000 keys, 500000 unique vectors (300 dimensions) |
| Sources | n/a |
| License | n/a |
| Author | n/a |
Label Scheme
View label scheme (4 labels for 1 components)
| Component | Labels |
|---|---|
ner |
LOC, MISC, ORG, PER |
Accuracy
| Type | Score |
|---|---|
ENTS_F |
82.22 |
ENTS_P |
83.11 |
ENTS_R |
81.35 |
TOK2VEC_LOSS |
330192.79 |
NER_LOSS |
1052233.81 |
- Downloads last month
- 27
Collection including zentrum-lexikographie/de_wikiner_lg
Evaluation results
- NER Precisionself-reported0.831
- NER Recallself-reported0.813
- NER F Scoreself-reported0.822