Posology Extractor Small

Description

Named Entity recognition annotator allows for a generic model to be trained by utilizing a deep learning algorithm (Char CNNs - BiLSTM - CRF - word embeddings) inspired on a former state of the art model for NER: Chiu & Nicols, Named Entity Recognition with Bidirectional LSTM,CNN. Pretrained named entity recognition deep learning model for posology, this NER is trained with the ‘embeddings_clinical’ word embeddings model, so be sure to use the same embeddings in the pipeline

Predicted Entities

DOSAGE,DRUG,DURATION,FORM,FREQUENCY,ROUTE,STRENGTH

Live Demo Open in ColabDownload

How to use

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

Model Information

Name: ner_posology_small  
Type: NerDLModel  
Compatibility: Spark NLP 2.4.2+  
License: Licensed  
Edition: Official  
Input labels: sentence, token, word_embeddings  
Output labels: ner  
Language: en  
Case sensitive: False  
Dependencies: embeddings_clinical  

Data Source

Trained on the 2018 i2b2 dataset (no FDA) with embeddings_clinical. https://www.i2b2.org/NLP/Medication