Description
This pretrained pipeline is built on the top of bert_token_classifier_ner_chemicals model.
Predicted Entities
CHEM
How to use
from sparknlp.pretrained import PretrainedPipeline
pipeline = PretrainedPipeline("bert_token_classifier_ner_chemicals_pipeline", "en", "clinical/models")
text = '''The results have shown that the product p - choloroaniline is not a significant factor in chlorhexidine - digluconate associated erosive cystitis. "A high percentage of kanamycin - colistin and povidone - iodine irrigations were associated with erosive cystitis.'''
result = pipeline.fullAnnotate(text)
import com.johnsnowlabs.nlp.pretrained.PretrainedPipeline
val pipeline = new PretrainedPipeline("bert_token_classifier_ner_chemicals_pipeline", "en", "clinical/models")
val text = "The results have shown that the product p - choloroaniline is not a significant factor in chlorhexidine - digluconate associated erosive cystitis. "A high percentage of kanamycin - colistin and povidone - iodine irrigations were associated with erosive cystitis."
val result = pipeline.fullAnnotate(text)
import nlu
nlu.load("en.classify.token_bert.chemicals_pipeline").predict("""The results have shown that the product p - choloroaniline is not a significant factor in chlorhexidine - digluconate associated erosive cystitis. "A high percentage of kanamycin - colistin and povidone - iodine irrigations were associated with erosive cystitis.""")
Results
| | ner_chunk | begin | end | ner_label | confidence |
|---:|:----------------------------|--------:|------:|:------------|-------------:|
| 0 | p - choloroaniline | 40 | 57 | CHEM | 0.999986 |
| 1 | chlorhexidine - digluconate | 90 | 116 | CHEM | 0.999989 |
| 2 | kanamycin | 169 | 177 | CHEM | 0.999985 |
| 3 | colistin | 181 | 188 | CHEM | 0.999982 |
| 4 | povidone - iodine | 194 | 210 | CHEM | 0.99998 |
Model Information
| Model Name: | bert_token_classifier_ner_chemicals_pipeline |
| Type: | pipeline |
| Compatibility: | Healthcare NLP 4.3.0+ |
| License: | Licensed |
| Edition: | Official |
| Language: | en |
| Size: | 404.9 MB |
Included Models
- DocumentAssembler
- SentenceDetectorDLModel
- TokenizerModel
- MedicalBertForTokenClassifier
- NerConverterInternalModel