Abstract: 

Text classification is one of the most commonly studied tasks in natural language processing. In addition to its theoretical importance, the classification task is widely used in various applications including spam detection, sentiment analysis, language identification.

FastText is an open-source library developed by Facebook AI Research (FAIR), that has the purpose of simplifying text classification.

As often, the "secret sauce" is in the details. This tutorial will give participants more insights about these details, helping them to understand the subtleties of the model.

● fastText library;
● python;
● numpy;
● terminal;

https://docs.google.com/document/d/11OldLO8XXJPD2GoFto7myGSdweSI0MRvK_-zpsJF7Xc/edit?usp=sharing
https://drive.google.com/open?id=1zQPz-e4RnI6vU_5yZ0gPgBYUY4SO4yu-

Bio: 

I am a research engineer at Facebook AI Research in Paris. Before that I worked as a financial software engineer on the default correlation models in the credit derivatives market.

I am mainly interested in linear/convex optimization, machine learning, and algorithms.