metadata
tags:
- spacy
- token-classification
language:
- he
model-index:
- name: he_subref_ner
results:
- task:
name: NER
type: token-classification
metrics:
- name: NER Precision
type: precision
value: 0.9611848825
- name: NER Recall
type: recall
value: 0.9651282051
- name: NER F Score
type: f_score
value: 0.9631525077
Description
This model is designed to be used in conjunction with the he-ref-ner model. See the README there for how to integrate them.
The model takes citaitons as input and tags the parts of the citation as entities. This is very useful for parsing the citation.
Technical details
| Feature | Description |
|---|---|
| Name | he_subref_ner |
| Version | 1.0.0 |
| spaCy | >=3.4.1,<3.5.0 |
| Default Pipeline | tok2vec, ner |
| Components | tok2vec, ner |
| Vectors | 394654 keys, 394654 unique vectors (50 dimensions) |
| Sources | n/a |
| License | n/a |
| Author | n/a |
Label Scheme
View label scheme (7 labels for 1 components)
| Component | Labels |
|---|---|
ner |
讚讛, 讻讜转专转, 诇讗-专爪讬祝, 诇拽诪谉-诇讛诇谉, 诪住驻专, 住讬诪谉-讟讜讜讞, 砖诐 |
Accuracy
| Type | Score |
|---|---|
ENTS_F |
96.32 |
ENTS_P |
96.12 |
ENTS_R |
96.51 |
TOK2VEC_LOSS |
11226.82 |
NER_LOSS |
2452.62 |