Recent advances in neural language models

Date:

Colloquium talk.

Slides: neural-lms.pdf

Abstract: This will be a gentle introduction to the foundational problem of probabilistic language modeling. I’ll quickly review some of the traditional (non-neural) approaches and then discuss recent breakthroughs that use deep neural networks to obtain state of the art results for English. I’ll close with some of the challenges these developments present for more interesting languages.