Op dinsdag 26 september tussen 14-15 uur zal Germans Savcisens, Ph.D. fellow aan de Technische Universiteit van Denemarken, een online lezing geven over over hoe natural language processing (NLP) helpt om voorspelbaarheid van mensenlevens te voorspellen. Na de lezing is er ruimte voor vragen en discussie. Meer informatie over de lezing hieronder (Engels).
About this Lunch Lecture
Over the past decade, machine learning has revolutionized text analysis through flexible computational models. Beyond text, emerging transformer-based architectures have shown promise as tools to explore multi-variate sequences from protein structures to weather forecasts due to their structural similarity to written language.Human life trajectories are another type of process that has a strong structural resemblance to language. From one perspective, lives are simply sequences of events. We present a life2vec model that uses this similarity to adapt innovations from natural language processing to examine the evolution and predictability of human lives based on day-to-day event sequences.
About Germans Savcisens
Germans is a third-year PhD student at the Technical University of Denmark (Section for Cognitive Systems), a member of the Social Complexity Lab and Copenhagen Center for Social Data Science at the University of Copenhagen. His areas of interest include Natural Language Processing, Foundation Models, Human Behaviour and Algorithmic Fairness & Interpretability.
In his research, Germans primarily explores the Representation of Human Behavior (part of the Nation-Scale Social Networks project). Germans is interested in the development of tools that provide deeper insights into the evolution of one’s life as well as the spread of ideas in communities. Currently, he explores the capabilities of Transformer-based models to analyze sequences of socio-economic data, encompassing aspects such as labour, health, and education under the supervision of Professor Sune Lehmann and Professor Lars Kai Hansen.
THE ODISSEI LECTURE SERIES
The ODISSEI Lunch Lectures highlight methodological issues and innovations in Social Science.
Photo by Glenn Carstens-Peters on Unsplash