metadata
tags:
- spacy
- token-classification
language:
- en
model-index:
- name: en_nerry_rel_trf_sentBert
results:
- task:
name: NER
type: token-classification
metrics:
- name: NER Precision
type: precision
value: 0.9259259259
- name: NER Recall
type: recall
value: 1
- name: NER F Score
type: f_score
value: 0.9615384615
RE with transformer (sentence bert)
| Feature | Description |
|---|---|
| Name | en_nerry_rel_trf_sentBert |
| Version | 2.1.0 |
| spaCy | >=3.6.1,<3.7.0 |
| Default Pipeline | transformer, ner, relation_extractor |
| Components | transformer, ner, relation_extractor |
| Vectors | 0 keys, 0 unique vectors (0 dimensions) |
| Sources | n/a |
| License | n/a |
| Author | HjAnthony |
Label Scheme
View label scheme (4 labels for 2 components)
| Component | Labels |
|---|---|
ner |
CRIME, PERSON, PROCECUTION |
relation_extractor |
INVOVLED_IN |
Accuracy
| Type | Score |
|---|---|
ENTS_F |
96.15 |
ENTS_P |
92.59 |
ENTS_R |
100.00 |
REL_MICRO_P |
88.24 |
REL_MICRO_R |
100.00 |
REL_MICRO_F |
93.75 |
TRANSFORMER_LOSS |
0.00 |
RELATION_EXTRACTOR_LOSS |
366.91 |