Edit on GitHub
  • John Snow Labs
  • Jan 12, 2023

English Legal BERT Embedding Small Uncased model

  • en
  • open_source
  • embeddings
  • bert

Description

Pretrained BERT Embedding model, adapted from Hugging Face and curated to provide scalability and production-readiness using Spark NLP. legal-bert-small-uncased is a English model originally trained by nlpaueb.

Download Copy S3 URI

How to use

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

tokenizer = Tokenizer() \
    .setInputCols("document") \
    .setOutputCol("token")
  
embeddings = BertEmbeddings.pretrained("bert_embeddings_legal_bert_small_uncased","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)

import nlu
nlu.load("en.embed.legal_bert_small_uncased").predict("""I love Spark NLP""")

Model Information

Model Name: bert_embeddings_legal_bert_small_uncased
Compatibility: Spark NLP 4.2.7+
License: Open Source
Edition: Official
Input Labels: [sentence]
Output Labels: [bert_sentence]
Language: en
Size: 131.8 MB
Case sensitive: false
Max sentence length: 128

References

  • https://huggingface.co/nlpaueb/legal-bert-small-uncased
  • https://www.sec.gov/edgar.shtml
  • https://twitter.com/KiddoThe2B
  • http://nlp.cs.aueb.gr
  • https://archive.org/details/legal_bert_fp
  • https://aclanthology.org/2020.findings-emnlp.261
  • http://hudoc.echr.coe.int/eng
  • http://www.legislation.gov.uk
  • https://www.tensorflow.org/tfrc
  • https://edu.google.com/programs/credits/research
  • https://case.law
  • https://iliaschalkidis.github.io
  • https://github.com/iliaschalkidis
  • https://github.com/google-research/bert
  • http://eur-lex.europa.eu