README.md

metadata

language:
  - pl
license: mit
tags:
  - token-classification
  - named-entity-recognition
  - polish
  - anonymization
  - privacy
  - gdpr
datasets:
  - custom
metrics:
  - f1
  - precision
  - recall
base_model: allegro/herbert-base-cased
model-index:
  - name: AnonBERT-ENR
    results:
      - task:
          type: token-classification
          name: Named Entity Recognition
        metrics:
          - type: f1
            value: 0.84
            name: F1 Score
widget:
  - text: >-
      Nazywam się Jan Kowalski i mieszkam w Warszawie przy ulicy Marszałkowskiej
      1. Mój email to [email protected], a numer telefonu +48 123 456
      789.
    example_title: Personal Data Example
  - text: 'PESEL: 12345678901, dowód osobisty: ABC123456. Data urodzenia: 1990-05-20.'
    example_title: ID Numbers Example

AnonBERT-ENR: Polish Personal Data Anonymization Model

Fine-tuned HerBERT model for Named Entity Recognition and anonymization of sensitive personal information in Polish text.

Achieves 84% F1 score on test set for identifying and anonymizing 25+ types of personal data entities.

Model Description

AnonBERT-ENR is a specialized NER model fine-tuned on allegro/herbert-base-cased for detecting and anonymizing personal data in Polish documents. The model is designed to help organizations comply with GDPR and other privacy regulations by automatically identifying sensitive information.

Key Features

• ✅ High Accuracy: 84% F1 score on diverse test data
• 🇵🇱 Polish Language: Optimized for Polish text and naming conventions
• 🔒 Privacy-Focused: Detects 25+ types of sensitive personal information
• 🚀 Production Ready: Includes complete anonymization pipeline
• 📊 Comprehensive Coverage: Names, IDs, contact info, health data, political views, and more

Supported Entity Types

The model can identify the following types of personal information:

Entity Type	Description	Example
NAME	First name	Jan
SURNAME	Last name	Kowalski
EMAIL	Email address	[email protected]
PHONE	Phone number	+48 123 456 789
PESEL	National ID number	12345678901
DOCUMENT	ID document number	ABC123456
ADDRESS	Street address	ul. Marszałkowska 1
CITY	City name	Warszawa
BANK_ACCOUNT	Bank account number	PL61109010140000071219812874
CREDIT_CARD	Credit card number	1234-5678-9012-3456
DATE_BIRTH	Date of birth	1990-05-20
DATE	General date	2024-01-15
AGE	Age	25 lat
SEX	Gender/sex	Mężczyzna, Kobieta
COMPANY	Company name	Allegro
SCHOOL	School name	Uniwersytet Warszawski
JOB	Job title	Dyrektor
USERNAME	Username/login	jan.kowalski
HEALTH	Health information	cukrzyca
RELIGION	Religious affiliation	katolik
POLITICAL	Political views	liberalny
ETHNICITY	Ethnicity	polska
ORIENTATION	Sexual orientation	heteroseksualny
RELATIVE	Family relation	matka
SECRET	Secret/confidential info	hasło: abc123