Detect Problems, Tests and Treatments (ner_crf)

Description

Named Entity recognition annotator allows for a generic model to be trained by CRF model Clinical NER (Large) is a Named Entity Recognition model that annotates text to find references to clinical events. The entities it annotates are Problem, Treatment, and Test. Clinical NER is trained with the ‘embeddings_clinical’ word embeddings model, so be sure to use the same embeddings in the pipeline.

Predicted Entities

Problem, Test, Treatment

Copy S3 URI

How to use

model = NerCrfModel.pretrained("ner_crf","en","clinical/models")\
	.setInputCols("sentence","token","pos","word_embeddings")\
	.setOutputCol("ner")
val model = NerCrfModel.pretrained("ner_crf","en","clinical/models")
	.setInputCols("sentence","token","pos","word_embeddings")
	.setOutputCol("ner")

Model Information

Name: ner_crf
Type: NerCrfModel
Compatibility: Spark NLP 2.4.0+
License: Licensed
Edition: Official
Input labels: [sentence, token, pos, word_embeddings]
Output labels: [ner]
Language: en
Dependencies: embeddings_clinical

Data Source

Trained with augmented version of i2b2 dataset withclinical_embeddings FILLUP