metadata
tags:
- spacy
- token-classification
language:
- en
model-index:
- name: en_kyc_nerre
results:
- task:
name: NER
type: token-classification
metrics:
- name: NER Precision
type: precision
value: 0.6862745098
- name: NER Recall
type: recall
value: 0.7954545455
- name: NER F Score
type: f_score
value: 0.7368421053
Feature | Description | Note |
---|---|---|
Name | en_kyc_nerre |
|
Version | 0.0.0 |
test run, official version will start from 1.xx.xx |
spaCy | >=3.6.1,<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 | hjiangAnthony |
Purpose
Identifying PERSON, CRIME, and PROCECUTION entities; supporting relation extraction for the next step
Label Scheme
View label scheme (3 labels for 1 components)
Component | Labels |
---|---|
ner |
CRIME , PERSON , PROCECUTION |
Accuracy
Type | Score |
---|---|
ENTS_F |
73.68 |
ENTS_P |
68.63 |
ENTS_R |
79.55 |
TRANSFORMER_LOSS |
12977.28 |
NER_LOSS |
94024.87 |