Anoppi — Finland's AI Tool for Anonymising Court and Authority Decisions Before Publication

Under Finland's GDPR obligations, court decisions and other official rulings that authorities publish for research and public scrutiny must first have personal data removed — traditionally a slow, manual redaction task. The Anoppi project (2018–2020), led by the Ministry of Justice with the University of Helsinki's Helsinki Centre for Digital Humanities, Aalto University's Semantic Computing Research Group, Statistics Finland and publisher Edita, built a language-technology tool to automate the task for Finnish-language documents.
Anoppi combines statistical and rule-based named-entity recognition with morphological analysis to detect and replace names and other identifiers with neutral placeholders (e.g. "Person A") while preserving a document's structure and readability, offered as both a web application and a REST API. It was demonstrated publicly at the Council of Europe's AI conference in Helsinki in February 2019 and published as open-source code so other authorities could reuse it beyond court decisions.
The project's own peer-reviewed evaluation found Anoppi "performs well with different types of documents" but flagged that its named-entity recognition and disambiguation still produce errors that "further improving... would enhance the usefulness of the software" — an honest acknowledgment that automated pseudonymisation is not yet error-free, so publishers using it should keep human review in the loop for highly sensitive documents.

Read the full analysis: https://seco.cs.aalto.fi/projects/anoppi/en/