Description
This pretrained pipeline is built on the top of bert_token_classifier_ner_bionlp model.
Predicted Entities
Amino_acid, Anatomical_system, Cancer, Cell, Cellular_component, Developing_anatomical_structure, Gene_or_gene_product, Immaterial_anatomical_entity, Multi-tissue_structure, Organ, Organism, Organism_subdivision, Organism_substance, Pathological_formation, Simple_chemical, Tissue
How to use
from sparknlp.pretrained import PretrainedPipeline
pipeline = PretrainedPipeline("bert_token_classifier_ner_bionlp_pipeline", "en", "clinical/models")
text = '''Both the erbA IRES and the erbA/myb virus constructs transformed erythroid cells after infection of bone marrow or blastoderm cultures. The erbA/myb IRES virus exhibited a 5-10-fold higher transformed colony forming efficiency than the erbA IRES virus in the blastoderm assay.'''
result = pipeline.fullAnnotate(text)
import com.johnsnowlabs.nlp.pretrained.PretrainedPipeline
val pipeline = new PretrainedPipeline("bert_token_classifier_ner_bionlp_pipeline", "en", "clinical/models")
val text = "Both the erbA IRES and the erbA/myb virus constructs transformed erythroid cells after infection of bone marrow or blastoderm cultures. The erbA/myb IRES virus exhibited a 5-10-fold higher transformed colony forming efficiency than the erbA IRES virus in the blastoderm assay."
val result = pipeline.fullAnnotate(text)
import nlu
nlu.load("en.classify.token_bert.biolp.pipeline").predict("""Both the erbA IRES and the erbA/myb virus constructs transformed erythroid cells after infection of bone marrow or blastoderm cultures. The erbA/myb IRES virus exhibited a 5-10-fold higher transformed colony forming efficiency than the erbA IRES virus in the blastoderm assay.""")
Results
| | ner_chunk | begin | end | ner_label | confidence |
|---:|:--------------------|--------:|------:|:-----------------------|-------------:|
| 0 | erbA IRES | 9 | 17 | Organism | 0.999188 |
| 1 | erbA/myb virus | 27 | 40 | Organism | 0.999434 |
| 2 | erythroid cells | 65 | 79 | Cell | 0.999837 |
| 3 | bone | 100 | 103 | Multi-tissue_structure | 0.999846 |
| 4 | marrow | 105 | 110 | Multi-tissue_structure | 0.999876 |
| 5 | blastoderm cultures | 115 | 133 | Cell | 0.999823 |
| 6 | erbA/myb IRES virus | 140 | 158 | Organism | 0.999751 |
| 7 | erbA IRES virus | 236 | 250 | Organism | 0.999749 |
| 8 | blastoderm | 259 | 268 | Cell | 0.999897 |
Model Information
| Model Name: | bert_token_classifier_ner_bionlp_pipeline |
| Type: | pipeline |
| Compatibility: | Healthcare NLP 4.3.0+ |
| License: | Licensed |
| Edition: | Official |
| Language: | en |
| Size: | 405.0 MB |
Included Models
- DocumentAssembler
- SentenceDetectorDLModel
- TokenizerModel
- MedicalBertForTokenClassifier
- NerConverterInternalModel