Edit on GitHub
  • John Snow Labs
  • Dec 18, 2022

Legal Warrant Agreement Document Binary Classifier (Longformer)

  • en
  • legal
  • classification
  • licensed
  • document
  • longformer
  • warrant
  • agreement
  • tensorflow

Description

The legclf_warrant_agreement model is a Longformer Document Classifier used to classify if the document belongs to the class warrant-agreement or not (Binary Classification).

Longformers have a restriction on 4096 tokens, so only the first 4096 tokens will be taken into account. We have realised that for the big majority of the documents in legal corpora, if they are clean and only contain the legal document without any extra information before, 4096 is enough to perform Document Classification.

If your document needs to process more than 4096 tokens, you can try the following: getting chunks of 4096 tokens and average the embeddings, training with the averaged version, what means all document will be taken into account.

Predicted Entities

warrant-agreement, other

Copy S3 URI

How to use


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

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

embeddings = nlp.LongformerEmbeddings.pretrained("legal_longformer_base", "en")\
      .setInputCols("document", "token")\
      .setOutputCol("embeddings")

sentence_embeddings = nlp.SentenceEmbeddings()\
    .setInputCols(["document", "embeddings"])\
    .setOutputCol("sentence_embeddings")\
    .setPoolingStrategy("AVERAGE")

doc_classifier = legal.ClassifierDLModel.pretrained("legclf_warrant_agreement", "en", "legal/models")\
    .setInputCols(["sentence_embeddings"])\
    .setOutputCol("category")

nlpPipeline = nlp.Pipeline(stages=[
    document_assembler,
    tokenizer,
    embeddings,
    sentence_embeddings,
    doc_classifier])

df = spark.createDataFrame([["YOUR TEXT HERE"]]).toDF("text")

model = nlpPipeline.fit(df)

result = model.transform(df)

Results


+-------+
|result|
+-------+
|[warrant-agreement]|
|[other]|
|[other]|
|[warrant-agreement]|

Model Information

Model Name: legclf_warrant_agreement
Compatibility: Legal NLP 1.0.0+
License: Licensed
Edition: Official
Input Labels: [sentence_embeddings]
Output Labels: [class]
Language: en
Size: 21.5 MB

References

Legal documents, scrapped from the Internet, and classified in-house + SEC documents

Benchmarking


            label precision recall  f1-score  support
            other      1.00   0.98      0.99      230
warrant-agreement      0.96   1.00      0.98       99
         accuracy         -      -      0.99      329
        macro-avg      0.98   0.99      0.99      329
     weighted-avg      0.99   0.99      0.99      329