Working with humans is incredibly difficult for robots. This project aims to develop new ways for robots and intelligent agents to understand, interact with, and adapt to the complex and collaborative ways we humans work together to get through our everyday lives.

With massive amounts of personal data being generated, privacy has become a great challenge. This project studies how machine learning can be used for sharing language models without risking to share information that may identify individuals.

Electronic health records are full of important information about diagnoses and treatments of patients. Sharing this information in a federated health data network, across hospitals in the Nordic countries, will improve the quality of health care.

The aim of this project is to enable the practical use of methods for de-identification of clinical free text written in Swedish. The HB Deid tool will be tested on textual patient data from Region Stockholm and not only in a laboratory environment at Stockholm University.

How can technical solutions help medical doctors make more accurate diagnoses, generate prognoses and estimate the probability of various outcomes? In this project, we use machine learning and language technology to develop prediction models for sepsis and COVID-19.

Recent breakthroughs in AI have been driven mainly by large language models. While they can be very useful, they also threaten privacy – they leak private information. This project aims to identify these risks and develop privacy-preserving techniques.

Empower Your Text Analysis: Annotate and Analyze Swedish and English Texts with SWEGRAM