Description
This pretrained pipeline is built on the top of bert_token_classifier_ner_ade model.
Live Demo Open in Colab Copy S3 URI
How to use
pipeline = PretrainedPipeline("bert_token_classifier_ner_ade_pipeline", "en", "clinical/models")
pipeline.annotate("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 pipeline = new PretrainedPipeline("bert_token_classifier_ner_ade_pipeline", "en", "clinical/models")
pipeline.annotate("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.")
import nlu
nlu.load("en.classify.token_bert.ade_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
+--------------+---------+
|chunk |ner_label|
+--------------+---------+
|Lipitor |DRUG |
|severe fatigue|ADE |
|voltaren |DRUG |
|cramps |ADE |
+--------------+---------+
Model Information
| Model Name: | bert_token_classifier_ner_ade_pipeline |
| Type: | pipeline |
| Compatibility: | Healthcare NLP 3.4.1+ |
| License: | Licensed |
| Edition: | Official |
| Language: | en |
| Size: | 404.7 MB |
Included Models
- DocumentAssembler
- SentenceDetectorDLModel
- TokenizerModel
- MedicalBertForTokenClassifier
- NerConverter