NER Model Finder

Description

This pretrained pipeline is trained with bert embeddings and can be used to find the most appropriate NER model given the entity name.

Open in Colab Copy S3 URI

How to use

from sparknlp.pretrained import PretrainedPipeline
ner_pipeline = PretrainedPipeline("ner_model_finder", "en", "clinical/models")

result = ner_pipeline.annotate("medication")
import com.johnsnowlabs.nlp.pretrained.PretrainedPipeline
val ner_pipeline = PretrainedPipeline("ner_model_finder","en","clinical/models")

val result = ner_pipeline.annotate("medication")
import nlu
nlu.load("en.ner.model_finder.pipeline").predict("""Put your text here.""")

Results

{'model_names': ["['ner_posology', 'ner_posology_large', 'ner_posology_small', 'ner_posology_greedy', 'ner_drugs_large',  'ner_posology_experimental', 'ner_drugs_greedy', 'ner_ade_clinical', 'ner_jsl_slim', 'ner_posology_healthcare', 'ner_ade_healthcare', 'jsl_ner_wip_modifier_clinical', 'ner_ade_clinical', 'ner_jsl_greedy', 'ner_risk_factors']"]}

Model Information

Model Name: ner_model_finder
Type: pipeline
Compatibility: Healthcare NLP 3.3.2+
License: Licensed
Edition: Official
Language: en

Included Models

  • DocumentAssembler
  • BertSentenceEmbeddings
  • SentenceEntityResolverModel
  • Finisher