Anoppi: A Pseudonymization Service For Finnish Court Documents

To comply with the EU General Data Protection Regulation (GDPR) publishing court judgments online requires that personal data contained in them must be disguised. However, anonymizing the documents manually is a costly and time-consuming procedure. This paper presents ANOPPI service for automatic and semi-automatic pseudonymization of Finnish court judgments. Utilizing both statistics-and rule-based named entity recognition methods and morphological analysis, ANOPPI is able to automatically pseudonymize documents written in Finnish preserving their readability and layout. The service is currently still in development but pilot tests are going to be carried out in Finnish courts in 2020.