At this week’s MCQLL meeting (Wednesday, October 14th, 1:30-2:30pm), we will hear from Alain Tapp, a professor in the Department of Computer Science and Operations Research (DIRO) at the Université de Montréal. Professor Tapp is a multidisciplinary researcher with contributions to quantum mechanics, computational complexity, cryptography, information theory, algorithms, ethics of algorithm, machine learning, and recently computational linguistics. He is a member of the Centre de Recherche Mathématique and an associate member of MILA. Abstract below.
If you would like to attend and have not already signed up for the MCQLL mailing list, please fill out this google form to do so.
Talk: In this lecture I will present some recent breakthroughs in discrete word representation based on language models. I will show that using an appropriate cost function minimization in deep learning, one can learn word embedding with discrete features that have impressive semantic relevance.