Edit on GitHub
  • John Snow Labs
  • Dec 06, 2022

Legal Option Agreement Document Classifier (Bert Sentence Embeddings)

  • en
  • legal
  • classification
  • agreement
  • option
  • licensed
  • bert
  • tensorflow

Description

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

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

Predicted Entities

option-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_option_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)

Results


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

Model Information

Model Name: legclf_option_agreement_bert
Compatibility: Legal NLP 1.0.0+
License: Licensed
Edition: Official
Input Labels: [sentence_embeddings]
Output Labels: [class]
Language: en
Size: 22.6 MB

References

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

Benchmarking


           label    precision   recall  f1-score   support
option-agreement       0.94      0.82      0.88        39
           other       0.90      0.97      0.93        65
        accuracy         -          -      0.91       104
       macro-avg       0.92      0.89      0.91       104
    weighted-avg       0.92      0.91      0.91       104