Sentence Embeddings - sbert tiny (tuned)

Description

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

Live Demo Open in Colab Download Copy S3 URI

How to use

sbiobert_embeddings = BertSentenceEmbeddings.pretrained("sbert_jsl_tiny_uncased","en","clinical/models").setInputCols(["sentence"]).setOutputCol("sbert_embeddings")

val sbiobert_embeddings = BertSentenceEmbeddings
.pretrained("sbert_jsl_tiny_uncased","en","clinical/models")
.setInputCols(Array("sentence"))
.setOutputCol("sbert_embeddings")

import nlu
nlu.load("en.embed_sentence.bert.jsl_tiny_uncased").predict("""Put your text here.""")

Results

Gives a 768 dimensional vector representation of the sentence.

Model Information

Data Source

Tuned on MedNLI dataset

Benchmarking

MedNLI    Score
Acc       0.625
STS(cos)  0.682