Sentence Embeddings - sbiobert (tuned)

Description

This model is trained to generate contextual sentence embeddings of input sentences.

Download

How to use

sbiobert_embeddings = BertSentenceEmbeddings\
.pretrained("sbiobert_jsl_umls_cased","en","clinical/models")\
.setInputCols(["sentence"])\
.setOutputCol("sbert_embeddings")
val sbiobert_embeddings = BertSentenceEmbeddings
.pretrained("sbiobert_jsl_umls_cased","en","clinical/models")
.setInputCols(Array("sentence"))
.setOutputCol("sbert_embeddings")
import nlu
nlu.load("en.embed_sentence.biobert.jsl_umls_cased").predict("""Put your text here.""")

Results

Gives a 768 dimensional vector representation of the sentence.

Model Information

Model Name: sbiobert_jsl_umls_cased
Compatibility: Spark NLP for Healthcare 3.0.3+
License: Licensed
Edition: Official
Language: en
Case sensitive: true

Data Source

Tuned on MedNLI dataset

Benchmarking

MedNLI   Score
Acc      0.758 
STS(cos) 0.651