Description
Entity Resolution model Based on KNN using Word Embeddings + Word Movers Distance
Predicted Entities
Snomed Codes and their normalized definition with clinical_embeddings
How to use
model = ChunkEntityResolverModel.pretrained("chunkresolve_snomed_findings_clinical","en","clinical/models")\
.setInputCols("token","chunk_embeddings")\
.setOutputCol("entity")
val model = ChunkEntityResolverModel.pretrained("chunkresolve_snomed_findings_clinical","en","clinical/models")
.setInputCols("token","chunk_embeddings")
.setOutputCol("entity")
Model Information
| Name: | chunkresolve_snomed_findings_clinical | |
| Type: | ChunkEntityResolverModel | |
| Compatibility: | Spark NLP 2.5.1+ | |
| License: | Licensed | |
| Edition: | Official | |
| Input labels: | [token, chunk_embeddings ] | |
| Output labels: | [entity] | |
| Language: | en | |
| Case sensitive: | True | |
| Dependencies: | embeddings_clinical |
Data Source
Trained on SNOMED CT Findings http://www.snomed.org/