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