English Legal BERT Embeddings

Description

Pretrained BERT Embeddings model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP. legalbert-adept is a English model originally trained by hatemestinbejaia.

Download Copy S3 URI

How to use

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

tokenizer = nlp.Tokenizer() \
    .setInputCols("document") \
    .setOutputCol("token")
  
embeddings = nlp.BertEmbeddings.pretrained("bert_embeddings_legalbert_adept","en") \
    .setInputCols(["document", "token"]) \
    .setOutputCol("embeddings")
    
pipeline = nlp.Pipeline(stages=[documentAssembler, tokenizer, embeddings])

data = spark.createDataFrame([["I love Spark 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_legalbert_adept","en") 
    .setInputCols(Array("document", "token")) 
    .setOutputCol("embeddings")

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

val data = Seq("I love Spark NLP").toDF("text")

val result = pipeline.fit(data).transform(data)

Model Information

Model Name: bert_embeddings_legalbert_adept
Compatibility: Spark NLP 4.3.0+
License: Open Source
Edition: Official
Input Labels: [sentence, token]
Output Labels: [bert]
Language: en
Size: 410.1 MB
Case sensitive: true

References

https://huggingface.co/hatemestinbejaia/legalbert-adept