Abstract: People express themselves in different ways - due to their individual characteristics, communication goals, cultural background, affinity to various sociodemographic groups, or just as a matter of personal style. Leveraging these differences can be beneficial for NLP applications. In this talk, I explore methods for interpreting the language together with its user-dependent aspects - personal history, beliefs, and social environment - and their effect on social NLP tasks. I further discuss implications of this research for conversational agents, and reflect on ethical risks of social prototyping.

Bio: Lucie Flek is a Professor of Computer Science at University of Bonn, Germany, and a renown researcher on machine learning applications in the field of Natural Language Processing (NLP), with a core expertise in the area of user modeling and stylistic variation. She investigates how individuals and sociodemographic groups differ in their language usage, and how this variation can be in return used in machine learning tasks to predict in-group behavior. Her broader expertise covers bias and mitigation techniques for the NLP field with respect to stereotype exaggeration, ethics issues, and the performance of machine learning models on underrepresented groups.