Bio literature Named Entity Recognition using microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext transformer model. The model recognises the following entities:
CD: Chemical/Drugs, DS: Diseases, GP: Gene/Protein and OG: Organism
| Feature |
Description |
| Name |
en_BiomedNER_EuropePMC |
| Version |
1.0.0 |
| spaCy |
>=3.2.4,<3.3.0 |
| Default Pipeline |
transformer, ner |
| Components |
transformer, ner |
| Vectors |
0 keys, 0 unique vectors (0 dimensions) |
| Sources |
n/a |
| License |
n/a |
| Author |
Santosh Tirunagari |
Label Scheme
View label scheme (4 labels for 1 components)
| Component |
Labels |
ner |
CD, DS, GP, OG |
Accuracy
| Type |
Score |
ENTS_F |
88.82 |
ENTS_P |
87.14 |
ENTS_R |
90.57 |
TRANSFORMER_LOSS |
92291.81 |
NER_LOSS |
109755.03 |
