Legal Warrant Agreement Document Binary Classifier (Bert Sentence Embeddings)

Description

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

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

Predicted Entities

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

Model Information

Model Name: legclf_warrant_agreement_bert
Compatibility: Legal NLP 1.0.0+
License: Licensed
Edition: Official
Input Labels: [sentence_embeddings]
Output Labels: [class]
Language: en
Size: 22.8 MB

References

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

Benchmarking


            label precision recall  f1-score  support
            other      0.98   0.99      0.98      204
warrant-agreement      0.96   0.95      0.96       83
         accuracy         -      -      0.98      287
        macro-avg      0.97   0.97      0.97      287
     weighted-avg      0.98   0.98      0.98      287