Legal Letter Agreement Document Classifier (Bert Sentence Embeddings)

Description

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

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

Predicted Entities

letter-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_letter_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|
+-------+
|[letter-agreement]|
|[other]|
|[other]|
|[letter-agreement]|

Model Information

Model Name:	legclf_letter_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
letter-agreement      0.94   0.87      0.90       38
           other      0.93   0.97      0.95       65
        accuracy         -      -      0.93      103
       macro-avg      0.93   0.92      0.93      103
    weighted-avg      0.93   0.93      0.93      103

PREVIOUSLegal Lease Agreement Document Classifier (Bert Sentence Embeddings)

NEXTLegal Letter Agreement Document Classifier (Longformer)