English Legal BERT Embedding Large Cased model

Description

Pretrained BERT Embedding model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP. legalbert-large-1.7M-1 is a English model originally trained by pile-of-law.

Download Copy S3 URI

How to use

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

tokenizer = Tokenizer() \
    .setInputCols("document") \
    .setOutputCol("token")
  
embeddings = BertEmbeddings.pretrained("bert_embeddings_legalbert_large_1.7M_1","en") \
    .setInputCols(["document", "token"]) \
    .setOutputCol("embeddings")
    
pipeline = Pipeline(stages=[documentAssembler, tokenizer, embeddings])

data = spark.createDataFrame([["I love Spark NLP"]]).toDF("text")

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

Model Information

Model Name:	bert_embeddings_legalbert_large_1.7M_1
Compatibility:	Spark NLP 4.2.7+
License:	Open Source
Edition:	Official
Input Labels:	[sentence]
Output Labels:	[bert_sentence]
Language:	en
Size:	646.5 MB
Case sensitive:	true
Max sentence length:	128

References

https://huggingface.co/pile-of-law/legalbert-large-1.7M-1
https://github.com/LexPredict/lexpredict-lexnlp
https://arxiv.org/abs/2110.00976
https://arxiv.org/abs/1907.11692
https://arxiv.org/abs/1810.04805

PREVIOUSEnglish Legal BERT Embedding Cased model

NEXTEnglish Legal BERT Embedding Large Cased model