German Medical Bert Embeddings

Description

Pretrained German Medical Bert Embeddings model, uploaded to Hugging Face, adapted and imported into Spark NLP. German-MedBERT is a German model orginally trained by smanjil.

Download Copy S3 URI

How to use

documentAssembler = DocumentAssembler() \
.setInputCol("text") \
.setOutputCol("document")

tokenizer = Tokenizer() \
.setInputCols("document") \
.setOutputCol("token")

embeddings = BertEmbeddings.pretrained("bert_embeddings_German_MedBERT","de") \
.setInputCols(["document", "token"]) \
.setOutputCol("embeddings")

pipeline = Pipeline(stages=[documentAssembler, tokenizer, embeddings])

data = spark.createDataFrame([["Ich liebe Funken NLP"]]).toDF("text")

result = pipeline.fit(data).transform(data)
val documentAssembler = new DocumentAssembler() 
.setInputCol("text") 
.setOutputCol("document")

val tokenizer = new Tokenizer() 
.setInputCols(Array("document"))
.setOutputCol("token")

val embeddings = BertEmbeddings.pretrained("bert_embeddings_German_MedBERT","de") 
.setInputCols(Array("document", "token")) 
.setOutputCol("embeddings")

val pipeline = new Pipeline().setStages(Array(documentAssembler, tokenizer, embeddings))

val data = Seq("Ich liebe Funken NLP").toDF("text")

val result = pipeline.fit(data).transform(data)
import nlu
nlu.load("de.embed.medbert").predict("""Ich liebe Funken NLP""")

Model Information

Model Name: bert_embeddings_German_MedBERT
Compatibility: Spark NLP 3.4.2+
License: Open Source
Edition: Official
Input Labels: [sentence, token]
Output Labels: [bert]
Language: de
Size: 409.8 MB
Case sensitive: true

References

  • https://huggingface.co/smanjil/German-MedBERT
  • https://opus4.kobv.de/opus4-rhein-waal/frontdoor/index/index/searchtype/collection/id/16225/start/0/rows/10/doctypefq/masterthesis/docId/740
  • https://www.linkedin.com/in/manjil-shrestha-038527b4/