Ner DL Model Clinical

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 diagnostics and procedures in spanish

Predicted Entities

Diagnostico, Procedimiento

Download

How to use

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

Model Information

Name: ner_diag_proc
Type: NerDLModel
Compatibility: 2.5.3
License: Licensed
Edition: Official
Input labels: [sentence, token, word_embeddings]
Output labels: [ner]
Language: es
Dependencies: embeddings_scielowiki_300d

Data Source

Trained on CodiEsp Challenge dataset trained with embeddings_scielowiki_300d https://temu.bsc.es/codiesp/