metadata
tags:
- spacy
- token-classification
language:
- en
model-index:
- name: en_spacy_pii_distilbert
results:
- task:
name: NER
type: token-classification
metrics:
- name: NER Precision
type: precision
value: 0.9530385872
- name: NER Recall
type: recall
value: 0.9554103008
- name: NER F Score
type: f_score
value: 0.9542229703
widget:
- text: >-
SELECT shipping FROM users WHERE shipping = '201 Thayer St Providence RI
02912'
datasets:
- beki/privy
| Feature | Description |
|---|---|
| Name | en_spacy_pii_distilbert |
| Version | 0.0.1 |
| spaCy | >=3.4.1,<=3.8.2 |
| Default Pipeline | transformer, ner |
| Components | transformer, ner |
| Vectors | 0 keys, 0 unique vectors (0 dimensions) |
| Sources | Trained on a new dataset for structured PII generated by Privy. For more details, see this blog post |
| License | MIT |
| Author | Benjamin Kilimnik |
Label Scheme
View label scheme (5 labels for 1 components)
| Component | Labels |
|---|---|
ner |
DATE_TIME, LOC, NRP, ORG, PER |
Accuracy
| Type | Score |
|---|---|
ENTS_F |
95.42 |
ENTS_P |
95.30 |
ENTS_R |
95.54 |
TRANSFORMER_LOSS |
61154.85 |
NER_LOSS |
56001.88 |