Description
The finclf_capital_call_notices model is a Bert Sentence Embeddings Document Classifier used to classify if the document belongs to the class capital_call_notices or not (Binary Classification).
Predicted Entities
capital_call_notices, other
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 = finance.ClassifierDLModel.pretrained("finclf_capital_call_notices", "en", "finance/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|
+-------+
|[capital_call_notices]|
|[other]|
|[other]|
|[capital_call_notices]|
Model Information
| Model Name: | finclf_capital_call_notices |
| Compatibility: | Finance NLP 1.0.0+ |
| License: | Licensed |
| Edition: | Official |
| Input Labels: | [sentence_embeddings] |
| Output Labels: | [class] |
| Language: | en |
| Size: | 22.4 MB |
References
Financial documents and classified in-house + SEC documents
Benchmarking
label precision recall f1-score support
capital_call_notices 1.00 1.00 1.00 12
other 1.00 1.00 1.00 23
accuracy - - 1.00 35
macro-avg 1.00 1.00 1.00 35
weighted-avg 1.00 1.00 1.00 35