Join us on Monday, August 21, for a data science study session with Bruno Gonçalves, Moore-Sloan Fellow at NYU's Center for Data Science, who will explain the intuition behind word embeddings and the word2vec family of algorithms.
Word2vec in Theory and Practice
Word embeddings have received a lot of attention ever since Google researchers published word2vec in 2013. Their work demonstrated that embeddings learned by neural networks after "reading" a large corpus of text are able to preserve semantic relationships between words. As a result, this type of embedding started being studied in more detail and applied to more serious NLP and IR tasks such as summarization, query expansion, etc. In this talk we will cover the intuitions and algorithms underlying the word2vec family of algoritms and analyze in detail Tensorflow's word2vec implementation. IMPORTANT: Please use your FULL REAL NAME to register and bring your ID.
Bruno Gonçalves is currently a Moore-Sloan Fellow at NYU's Center for Data Science. With a background in Physics and Computer Science his career has revolved around the use of datasets from sources as diverse as Apache web logs, Wikipedia edits, Twitter posts epidemiological reports and Census data to analyze and model Human Behavior and Mobility. More recently he has focused on the application of machine learning and neural network techniques to analyze large geolocated datasets. He is the editor of "Social Phenomena: From Data Analysis to Models" (Springer, 2015) and a co-author of the forthcoming "Twitterology: The Social Science of Twitter" (Springer, 2018).
Doors open at 6:45pm
Lifion Host: Patrick Conlon
Event Organizer: Eric Xu