Relation Extraction Model Clinical

Description

Relation Extraction model based on syntactic features using deep learning

Predicted Entities

TrIP (improved), TrWP (worsened), TrCP (caused problem), TrAP (administered), TrNAP (avoided), TeRP (revealed problem), TeCP (investigate problem), PIP (problems related)

Open in ColabDownload

How to use

model = RelationExtractionModel.pretrained("re_temporal_events_clinical","en","clinical/models")\
	.setInputCols("word_embeddings","chunk","pos","dependency")\
	.setOutputCol("category")
val model = RelationExtractionModel.pretrained("re_temporal_events_clinical","en","clinical/models")
	.setInputCols("word_embeddings","chunk","pos","dependency")
	.setOutputCol("category")

Model Information

Name: re_temporal_events_clinical  
Type: RelationExtractionModel  
Compatibility: Spark NLP 2.5.5+  
License: Licensed  
Edition: Official  
Input labels: [word_embeddings, chunk, pos, dependency]  
Output labels: [category]  
Language: en  
Case sensitive: False  
Dependencies: embeddings_clinical  

Data Source

Trained on data gathered and manually annotated by John Snow Labs https://portal.dbmi.hms.harvard.edu/projects/n2c2-nlp/