Artificial neural networks play an important role in machine learning and cognitive sciences. Recent research in the field of natural language processing has shown that deep neural network models are quite brittle and can only model linguistic principles to a limited degree. To build NLP systems that can generalise and work well in practice, it is important to integrate linguistic knowledge into such systems, as well as investigate the ability of current models to capture linguistic phenomena. Ke Tran addresses those two aspects from different angles.
M.K. Tran: Predicting and Discovering Linguistic Structure with Neural Networks.
Dr C. Monz
Dr A. Bisazza
This event is open to the public.