Deep Learning in NLP and Beyond – Tomas Mikolov (Facebook)

October 13, 2015 @ 4:00 pm – 5:15 pm
3400 N Charles St
Baltimore, MD 21218

I will provide a short overview of some of the success stories in NLP that involve advanced machine learning techniques, such as recurrent neural networks. Then, I will try to explain what is the main motivation for researchers to be interested in the techniques and approaches currently known as Deep learning. Following this motivation, I will present some novel ideas and possible directions for future research that would bring us closer to development of machines that can understand natural language and communicate with us.

Tomas Mikolov is a research scientist at Facebook AI Research lab located in NY. His most influential work includes development of recurrent neural network language models and discovery of semantic regularities in distributed word representations. These projects have been published as open-source tools RNNLM and word2vec which have been since widely used both in academia and industry. His main research interest is to develop intelligent machines.

Center for Language and Speech Processing