In the third instalment of the ANU Humanising Machine Intelligence (HMI) Data, AI and Society public seminar series, Maria De-Arteaga will discuss her work 'What's in a name? Understanding and mitigating semantic representation bias'.
Maria De-Arteaga is an Assistant Professor at the Information, Risk and Operation Management Department at the University of Texas, Austin. She received her PhD in Machine Learning and Public Policy from Carnegie Mellon University. She holds a M.Sc. in Machine Learning from Carnegie Mellon University and a B.Sc. in Mathematics from Universidad Nacional de Colombia. Her research focuses on the risks and opportunities of using machine learning for decision support in high-stakes settings. Her work has been awarded the Best Thematic Paper Award at NAACL’19, the Innovation Award on Data Science at Data for Policy’16, and has been featured by UN Women and Global Pulse in their report Gender Equality and Big Data: Making Gender Data Visible. She is a recipient of a 2018 Microsoft Research Dissertation Grant, and was named an EECS 2019 Rising Star. In 2017 she co-founded the Machine Learning for the Developing World (ML4D) Workshop series.
In this talk, Maria will characterize how societal biases encoded in data may be compounded by machine learning models. She will relate this to the political philosophy notion of compounding injustices and illustrate it in the context of automated recruiting. Finally, Maria will propose novel methodology that leverages biases in word embeddings to mitigate the compounding effect without assuming access to protected attributes.