Sie haben Javascript deaktiviert!
Sie haben versucht eine Funktion zu nutzen, die nur mit Javascript möglich ist. Um sämtliche Funktionalitäten unserer Internetseite zu nutzen, aktivieren Sie bitte Javascript in Ihrem Browser.

Studierende in den Seminarräumen des O-Gebäudes, Foto: Universität Paderborn, Fotografin: Judith Kraft Show image information

Studierende in den Seminarräumen des O-Gebäudes, Foto: Universität Paderborn, Fotografin: Judith Kraft


"All Day Research" Podcast: Fifth episode with Jun.-Prof. Dr. Henning Wachsmuth online

In the fifth episode of the "All Day Research" podcast, this time we welcome Jun.-Prof. Dr. Henning Wachsmuth. With our host Lukas Ostermann, he talks about social biases - also called social bias - in AI systems.

How do computers understand human reasoning and how might the advantages each of us has be analysed in language? These were the questions Jun.-Prof. Henning Wachsmuth dealt with at the beginning of his research career. In the meantime, he has specialized in the field of "Digital Future" and is essentially concerned with the processing of natural language in computers and AI systems. In this context, he is particularly interested in social bias in AI systems. This refers to prejudices or unfair behaviour towards certain social groups, which are reflected in the language or in data sets.

"In general, of course, we want to protect the social groups that are affected by bias. That's really the starting point of how you design datasets. [...] In the best case, of course, we want to develop an AI that is as free of prejudice as possible, because then it can also support us better in reverse," Wachsmuth said of the goals of his research. However, he said, it is not that easy to solve these problems completely and overnight. "Some features are very subtle and are not easily detected." In addition, he said, the first step is to try to reduce the bias as much as possible.

What is special about addressing social biases in AI systems is the strong interdisciplinarity. Since the main focus is on human behaviour, the exchange between other scientific fields such as linguistics, psychology and the social sciences is particularly important and at the same time enormously exciting.

The podcast was produced in cooperation with the Institute of Computer Science and the Computer Science Student Council. The aim is to give more insights into science and thereby bring students - especially those in the first semester - closer to the study, to arouse interest and to show how much fun research and the study of computer science at the University of Paderborn can be.

Listen now to the fourth episode of the "All Day Research" podcast. Find it everywhere podcast is available or here on the institute page.

Missed the last episodes? Don't worry, all episodes can also be found on the institute page.

The University for the Information Society