Critical AI & Crisis Interrogatives (CRAI-CIS) Seminar
Monthly dialogues and critical perspectives on artificial intelligence, Human Computer Interaction (HCI), participatory design, and crisis-related research for societal impact.
The CRAI-CIS Seminars engage emerging work across critical AI, Human Computer Interaction (HCI), participatory design, and crisis-related research. The seminars seek to invoke dialogues on how computational, human-centred, and social sciences perspectives can offer new insights and methods for inclusive approaches and critical inquiry with societal impact.
Each event features invited speakers who share distinct perspectives, ongoing research, methods, and challenges for future work in a 45 minute talk, followed by Q&A and space for mingling and networking. The talks will be recorded for open access in the future.
Lear more about the seminar series →
IVAN habernal: Towards Privacy-Preserving Natural Language Processing
Time: March 15, 2023, 16:00–17:30
Venue: Event is hybrid. Participants may attend in person (T2, Computer Science Building, Aalto University) or online on Zoom.
Abstract:
In this talk, I will explore the challenges and concerns surrounding privacy in natural language processing (NLP) and present potential solutions to address them. I will discuss the use of anonymization and differential privacy techniques to protect sensitive information while still enabling the training of accurate NLP models. Additionally, I will emphasize the importance of considering legal and ethical implications when implementing privacy-preserving solutions in NLP.
Speaker Bio:
Ivan Habernal leads the independent research group “Trustworthy Human Language Technologies” at the Department of Computer Science, Technische Universität Darmstadt, Germany. In winter term 2022/23 he also holds an interim professorship in Computational Linguistics at Ludwig Maximilian University of Munich. His current research areas include privacy-preserving NLP, legal argument mining, and explainable and trustworthy models. His research track covers argument mining and computational argumentation, crowdsourcing, and serious games, among others. More information can be found at https://www.trusthlt.org