The School of Computer Science Presents...
Identifying BIAS in NLP Models-Part 2
Presenter: Reem Al-Saidi
Date: Wednesday, March 6th, 2024
Time: 4:30-5:30 PM
Location: 4th Floor (Workshop space) at 300 Ouellette Avenue (School of Computer Science Advanced Computing Hub)
Abstract:
This engaging workshop gives participants the knowledge and resources they need to successfully negotiate the challenges of bias in AI-driven applications by fusing theoretical insights with real-world activities.
Participants will tour the basic ideas of pre-trained language models using Google Colab. They will work through practical coding exercises, loading pre-trained BERT models and completing simple text-processing tasks.
Workshop Outline:
Review of the BERT Model
Review of measuring BIAS
Hand on exercises
Prerequisites:
Familiarity with natural language processing (NLP) concepts:
Basic to intermediate Python programming:
Interest in emerging technologies and fairness in NLP models
Biography:
Reem is a Ph.D. student at the University of Windsor in the Computer Science department. She focuses on applying different privacy and security techniques in AI tools, providing trust and reputation in various AI applications, and assessing bias and fairness in NLP models.