Department of Mathematical Sciences
|Thursday, September 14, 2017
|1:15pm – 2:15pm
|Wenbo Wang, Binghamton University
|Vector representation of words from very large data sets
Tomas Mikolov et al. proposed two novel model architectures for computing continuous vector representation of words from very large data sets. Recent years, it has become a very hot field in the industry known as 'word2vec'. In this talk we will go over the two models (Skip-gram Model and Continuous Bag-of-Words Model) and some tricks used to implement them.