Financial Controls procedures Item Binary Classifier

Description

This model is a Binary Classifier (True, False) for the controls_procedures item type of 10K Annual Reports. To use this model, make sure you provide enough context as an input. Adding Sentence Splitters to the pipeline will make the model see only sentences, not the whole text, so it’s better to skip it, unless you want to do Binary Classification as sentence level.

If you have big financial documents, and you want to look for clauses, we recommend you to split the documents using any of the techniques available in our Finance NLP Workshop Tokenization & Splitting Tutorial (link here), namely:

• Paragraph splitting (by multiline);
• Splitting by headers / subheaders;
• etc.

Take into consideration the embeddings of this model allows up to 512 tokens. If you have more than that, consider splitting in smaller pieces (you can also check the same tutorial link provided above).

Predicted Entities

other, controls_procedures

Live Demo Open in Colab Download Copy S3 URI

How to use

documentAssembler = nlp.DocumentAssembler() \
     .setInputCol("text") \
     .setOutputCol("document")

useEmbeddings = nlp.UniversalSentenceEncoder.pretrained() \
    .setInputCols("document") \
    .setOutputCol("sentence_embeddings")

docClassifier = nlp.ClassifierDLModel.pretrained("finclf_controls_procedures_item", "en", "finance/models")\
    .setInputCols(["sentence_embeddings"])\
    .setOutputCol("category")
    
nlpPipeline = nlp.Pipeline(stages=[
    documentAssembler, 
    useEmbeddings,
    docClassifier])
 
df = spark.createDataFrame([["YOUR TEXT HERE"]]).toDF("text")
model = nlpPipeline.fit(df)
result = model.transform(df)

Results

+-------+
| result|
+-------+
|[controls_procedures]|
|[other]|
|[other]|
|[controls_procedures]|

Model Information

References

Weak labelling on documents from Edgar database

Benchmarking

              label  precision    recall  f1-score   support
controls_procedures       0.94      0.93      0.94        86
              other       0.94      0.95      0.94        92
           accuracy          -         -      0.94       178
          macro-avg       0.94      0.94      0.94       178
       weighted-avg       0.94      0.94      0.94       178