Building Fair Natural Language Processing Technologies
Building Fair Natural Language Processing Technologies
Automatic models of human language often exhibit unfairness, typically through capturing or even amplifying problematic biases in the training corpora. Biases include racism, sexism, ageism, among others. This talk will cover a range of algorithmic methods for mitigating bias arising from training, based around techniques to remove protected information, such as user demographics, from learned representations or models' predictive outputs. I will initially cover some supervised methods, which require protected labels during training or inference, and then present an unsupervised method. Experiments over a range of NLP classification tasks show that our methods can substantially improve fairness over benchmark approaches.
Speaker
Prof. Trevor Cohn
Dr. Trevor Cohn is a Professor at the University of Melbourne, and, just recently, a Research Scientist at Google Deepmind. His research focuses on probabilistic and statistical machine learning for natural language processing, with applications ranging from machine translation and multilingual learning to parsing and information extraction. Current projects include measuring and countering demographic biases in text corpora and NLP systems, adversarial attacks on machine translation, and developing corpora and tools for low resource languages.
Dr. Cohn has more than 150 research publications, and his research has been recognised by awards at AACL-IJCNLP (2022), ACL (2020, 2017) and EMNLP (2016). He served as a local chair for ACL 2018, and as a programme chair for EMNLP in 2020. He received Bachelor degrees in Software Engineering and Commerce, and a PhD degree in Engineering from the University of Melbourne. He was previously based at the University of Sheffield, and before this worked as a Research Fellow at the University of Edinburgh.
Monash University values the privacy of every individual's personal information and is committed to the protection of that information from unauthorised use and disclosure except where permitted by law. For information about the handling of your personal information please see Data Protection and Privacy Procedure and the relevant Data Protection and Privacy Collection Statement that applies to you depending on the nature of your interaction with us.
If you have any questions about how Monash University is collecting and handling your personal information, please contact our Data Protection and Privacy Office at dataprotectionofficer@monash.edu.