The COMPRISE Text Transformer is part of the COMPRISE SDK. It allows users in various application domains to mask out critical information in a text that would otherwise threaten the privacy of third parties, while preserving the sentence structure. It:
replaces words and expressions carrying personal information by random alternatives, focusing on persons’ names, organisations, locations, dates and times;
is applicable to all kinds of text documents in addition to spoken dialogues;
leverages cutting-edge deep learning and natural language processing technology;
provides formal differential privacy guarantees.
It has been trained on English and evaluated on Engish and Latvian.
