Description
This is a finance Pretrained pipeline aimed to extract entities from suspicious activity reports that are filed by financial institutions, and those associated with their business, with the Financial Crimes Enforcement Network.
Predicted Entities
ORG, ADDRESS, ROLE, DATE,SUSPICIOUS_ITEMS, PERSON_NAME, SUSPICIOUS_ACTION, SUSPICIOUS_KEYWORD
How to use
from johnsnowlabs import PretrainedPipeline
sar_pipeline = PretrainedPipeline("finpipe_suspicious_activity_reports", "en", "finance/models")
Results
+-------------------------+------------------+
|chunk |ner_label |
+-------------------------+------------------+
|SUSPICIOUS |SUSPICIOUS_KEYWORD|
|April 25, 2023 |DATE |
|John Doe |PERSON_NAME |
|Senior Compliance Officer|ROLE |
|SUSPICIOUS_ACTION |SUSPICIOUS_KEYWORD|
|Unusual |SUSPICIOUS_KEYWORD|
|SUSPICIOUS_KEYWORD |SUSPICIOUS_KEYWORD|
|Money Laundering |SUSPICIOUS_ACTION |
|SUSPICIOUS_ITEMS |SUSPICIOUS_KEYWORD|
|deposits |SUSPICIOUS_ITEMS |
|cash |SUSPICIOUS_ITEMS |
|Currency |SUSPICIOUS_ITEMS |
|sums of money |SUSPICIOUS_ITEMS |
|bank accounts |SUSPICIOUS_ITEMS |
|tax |SUSPICIOUS_ITEMS |
|April 24, 2023 |DATE |
|XYZ Bank |ORG |
+-------------------------+------------------+
Model Information
| Model Name: | finpipe_suspicious_activity_reports |
| Type: | pipeline |
| Compatibility: | Finance NLP 1.0.0+ |
| License: | Licensed |
| Edition: | Official |
| Language: | en |
| Size: | 1.2 GB |
Included Models
- DocumentAssembler
- SentenceDetectorDLModel
- TokenizerModel
- TokenizerModel
- BertEmbeddings
- BertEmbeddings
- FinanceNerModel
- FinanceNerModel
- FinanceBertForTokenClassification
- NerConverterInternalModel
- NerConverterInternalModel
- NerConverterInternalModel
- ContextualParserModel
- ChunkMergeModel