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. 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.
Problem, Test, Treatment
How to use
model = NerDLModel.pretrained("ner_clinical_large","en","clinical/models")\ .setInputCols("sentence","token","word_embeddings")\ .setOutputCol("ner")
val model = NerDLModel.pretrained("ner_clinical_large","en","clinical/models") .setInputCols("sentence","token","word_embeddings") .setOutputCol("ner")
|Compatibility:||Spark NLP 2.5.0+|
|Input labels:||[sentence, token, word_embeddings]|
Trained on i2b2 augmented data with