Gender and Bias in Natural Language Processing
This talk presents an introduction to the subject of gender bias in Natural Language Processing (NLP). It will explore some common definitions and measurements of biases, how they manifest in NLP, ways to mitigate the harms they cause, and knowledge gaps within the research field.
Hannah is a PhD candidate at Umeå University, in the Department of Computing Science and Umeå Centre for Gender Studies. They hold a bachelor’s degree in Computer Science, Linguistics, and French from Trinity College Dublin, and an MSc in Speech and Language Processing from the University of Edinburgh. Their current research focuses on understanding the power structures and biases at play in the types of language data used to train NLP tools, and developing methods to identify and mitigate these patterns in order to reduce algorithmic harms.