Named Entity Linking model for Serbian language
| Feature | Description |
|---|---|
| Name | sr_SRPCNNEL |
| Version | 1.0.0 |
| spaCy | >=3.5.2,<3.6.0 |
| Default Pipeline | tok2vec, tagger, ner, sentencizer, entity_linker |
| Components | tok2vec, tagger, ner, sentencizer, entity_linker |
| Vectors | 0 keys, 0 unique vectors (0 dimensions) |
| Sources | n/a |
| License | n/a |
| Author | Milica Ikonić Nešić, Saša Petalinkar, Ranka Stanković, Miloš Utvić, Olivera Kitanović |
Label Scheme
View label scheme (23 labels for 2 components)
| Component | Labels |
|---|---|
tagger |
ADJ, ADP, ADV, AUX, CCONJ, DET, INTJ, NOUN, NUM, PART, PRON, PROPN, PUNCT, SCONJ, VERB, X |
ner |
DEMO, EVENT, LOC, ORG, PERS, ROLE, WORK |
Accuracy
| Type | Score |
|---|---|
TAG_ACC |
96.49 |
ENTS_F |
93.38 |
ENTS_P |
93.35 |
ENTS_R |
93.40 |
TOK2VEC_LOSS |
205472.21 |
TAGGER_LOSS |
502844.65 |
NER_LOSS |
148170.50 |
- Downloads last month
- 22
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.
Evaluation results
- NER Precisionself-reported0.933
- NER Recallself-reported0.934
- NER F Scoreself-reported0.934
- TAG (XPOS) Accuracyself-reported0.965