| Feature | Description |
|---|---|
| Name | de_APIS_OEBL_NER_trf |
| Version | 1.0 |
| spaCy | >=3.6.0,<3.7.0 |
| Default Pipeline | transformer, ner |
| Components | transformer, ner |
| Vectors | 0 keys, 0 unique vectors (0 dimensions) |
| Sources | n/a |
| License | n/a |
| Author | n/a |
Label Scheme
View label scheme (3 labels for 1 components)
| Component | Labels |
|---|---|
ner |
LOC, ORG, PER |
Accuracy
| Type | Score |
|---|---|
ENTS_F |
82.45 |
ENTS_P |
80.18 |
ENTS_R |
84.84 |
TRANSFORMER_LOSS |
52932.36 |
NER_LOSS |
52005.98 |
Sources
Trained on data originating from the APIS project and the Austrian Biographical Lexicon (ÖBL).
Reproducible training context (model m3): https://github.com/acdh-oeaw/veld_chain_7_train/
Dataset available here: https://huggingface.co/datasets/SteffRhes/APIS_OEBL__Named_Entity_Recognition
- Downloads last month
- 3
Dataset used to train SteffRhes/de_APIS_OEBL_NER_trf
Evaluation results
- NER Precisionself-reported0.802
- NER Recallself-reported0.848
- NER F Scoreself-reported0.824