| Feature | Description | 
|---|---|
| Name | en_roberta_base_leetspeak_ner | 
| Version | 0.0.0 | 
| spaCy | >=3.2.1,<3.3.0 | 
| Default Pipeline | transformer, ner | 
| Components | transformer, ner | 
| Vectors | 0 keys, 0 unique vectors (0 dimensions) | 
| Sources | roberta-base pre-trained model on English language using a masked language modeling (MLM) objective by Yinhan Liu et al.  LeetSpeak-NER app where this model is in production for countering information disorders  | 
| License | Apache 2.0 | 
| Author | Álvaro Huertas García at AI+DA | 
Label Scheme
View label scheme (4 labels for 1 components)
| Component | Labels | 
|---|---|
ner | 
INV_CAMO, LEETSPEAK, MIX, PUNCT_CAMO | 
Accuracy
| Type | Score | 
|---|---|
ENTS_F | 
82.80 | 
ENTS_P | 
79.66 | 
ENTS_R | 
86.20 | 
TRANSFORMER_LOSS | 
177808.42 | 
NER_LOSS | 
608427.31 | 
- Downloads last month
 - 18
 
Evaluation results
- NER Precisionself-reported0.797
 - NER Recallself-reported0.862
 - NER F Scoreself-reported0.828