Legal Registration Rights Agreement Document Binary Classifier (Bert Sentence Embeddings)

Description

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

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

Predicted Entities

registration-rights-agreement, other

Download 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_registration_rights_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|
+-------+
|[registration-rights-agreement]|
|[other]|
|[other]|
|[registration-rights-agreement]|

Model Information

Model Name:	legclf_registration_rights_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 + SEC documents

Benchmarking

                         label    precision    recall    f1-score    support 
                         other         0.95      0.98        0.96        204 
 registration-rights-agreement         0.96      0.90        0.93        113 
                      accuracy            -         -        0.95        317 
                     macro-avg         0.96      0.94        0.95        317 
                  weighted-avg         0.95      0.95        0.95        317

PREVIOUSLegal Management Agreement Document Binary Classifier (Longformer)

NEXTLegal Registration Rights Agreement Document Binary Classifier (Longformer)