Legal Custody Agreement Clause Binary Classifier (Bert)

Description

The legclf_custody_agreement_bert model is a Bert Sentence Embeddings Document Classifier used to classify if the document belongs to the class custody-agreement or not (Binary Classification).

Unlike the Longformer model, this model is lighter in terms of inference time.

Predicted Entities

custody-agreement, other

Copy S3 URI

How to use

 
document_assembler = nlp.DocumentAssembler()\
    .setInputCol("text")\
    .setOutputCol("document")
  
embeddings = nlp.BertSentenceEmbeddings.pretrained("sent_bert_base_cased", "en")\
    .setInputCols("document")\
    .setOutputCol("sentence_embeddings")
    
doc_classifier = legal.ClassifierDLModel.pretrained("legclf_custody_agreement_bert", "en", "legal/models")\
    .setInputCols(["sentence_embeddings"])\
    .setOutputCol("category")
    
nlpPipeline = nlp.Pipeline(stages=[
    document_assembler, 
    embeddings,
    doc_classifier])
 
df = spark.createDataFrame([["YOUR TEXT HERE"]]).toDF("text")

model = nlpPipeline.fit(df)

result = model.transform(df)

Model Information

Model Name: legclf_custody_agreement_bert
Compatibility: Legal NLP 1.0.0+
License: Licensed
Edition: Official
Input Labels: [sentence_embeddings]
Output Labels: [class]
Language: en
Size: 22.7 MB

References

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

Benchmarking

            label  precision    recall  f1-score   support
custody-agreement       0.95      0.97      0.96        37
            other       0.97      0.94      0.96        35
         accuracy          -         -      0.96        72
        macro-avg       0.96      0.96      0.96        72
     weighted-avg       0.96      0.96      0.96        72