Megan is a Customer Data Scientist at H2O. Prior to working at H2O, she worked as a Data Scientist building products driven by machine learning for B2B customers. She has experience working with customers across multiple industries, identifying common problems, and designing robust and automated solutions. Megan is based in New York City and holds a degree in Applied Mathematics. In her free time, she enjoys hiking and yoga.
NLP with H2O
The focus of this talk is to provide an introduction to Natural Language Processing with a focus on the Word2Vec algorithm. Word2Vec is an algorithm that trains a shallow neural network model to learn vector representations of words. These vector representations are able to capture the meanings of words. During the talk, we will use H2O's Word2Vec implementation to understand relationships between words in our text data. We will use the model results to find similar words, synonyms, and analogies. We will also use it to showcase how to effectively represent text data for machine learning problems where we will highlight the impact this representation can have on accuracy. The talk will cover the theory behind Word2Vec as well as a demo of a machine learning workflow with text data.