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. Neoplasms NER is a Named Entity Recognition model that annotates text to find references to tumors. The only entity it annotates is MalignantNeoplasm. Neoplasms NER is trained with the ‘embeddings_scielowiki_300d’ word embeddings model, so be sure to use the same embeddings in the pipeline.
How to use
model = NerDLModel.pretrained("ner_neoplasms","es","clinical/models")\ .setInputCols("sentence","token","word_embeddings")\ .setOutputCol("ner")
val model = NerDLModel.pretrained("ner_neoplasms","es","clinical/models") .setInputCols("sentence","token","word_embeddings") .setOutputCol("ner")
|Compatibility:||Spark NLP 2.5.3+|
|Input labels:||[sentence, token, word_embeddings]|
Named Entity Recognition model for Neoplasic Morphology https://temu.bsc.es/cantemist/