At this week’s lab meeting, Alain Tapp will be presenting on word representations.

  • Wednesday, October 14, at 13:30 (Montreal time, UTC-4).
  • Meetings are via Zoom. If you would like to attend and have not already signed up for the MCQLL mailing list, please fill out this google form.

Abstract

In this talk, Prof. Tapp will present some recent breakthroughs in discrete word representations based on language models. He will show that using an appropriate cost function minimisation in deep learning, one can learn word embeddings with discrete features that have impressive semantic relevance.

Bio

Alain Tapp is a professor in the Department of Computer Science and Operations Research (DIRO) at the Université de Montréal. He is a multidisciplinary researcher with contributions to quantum mechanics, computational complexity, cryptography, information theory, algorithms, ethics of algorithms, machine learning and recently, computational linguistics. He is a member of the Centre de Recherche Mathématique and associate to MILA.