PII Grammars

In Named Entity Recognition, PII (personally identifiable information) refers to the personal information that is governed by Data Protection legislation around the world, such as the GDPR regulations in the European Union, CCPA or CPRA in the United States, or PIPL in China, among many others.

It is imperative for organizations to be able to identify and take action on documents that contain personal information. The PII grammars allow you to create applications that tag, redact, or route the documents as appropriate.

PII regulations define certain types as data as personal, and the grammars are designed to reflect this. The PII grammars identify entities such as: 

• Address

• Date of Birth

• Driving License

• Medical

• Name

• National ID

• Passport

• Telephone numbers

• Tax Identification Number (TIN)

These grammars identify entities specific to a particular country, other than Date of Birth and Medical, which find entities for a particular language. Country and language coverage is extensive and coverage is extended frequently. For more information, refer to the Named Entity Recognition Grammars User Guide.