Abstract: In this session, you will gain a conceptual understanding of Natural Language Processing (NLP) techniques and learn how to apply them through hands-on projects. You will begin with preprocessing steps necessary for parsing unstructured text data. You will then transform text using basic representations such as bag-of-words and TF-IDF, and train a Naive Bayes classifier to detect spam emails. Finally, you will learn to transform text using more advanced representations such as Word2Vec, tSNE and LDA, and explore how you can use them for topic modeling. The projects will be implemented in Python, and libraries like Scikit-Learn and NLTK, and starter code will be provided through GitHub.
Bio: Arpan likes to find computing solutions to everyday problems. He obtained his PhD from North Carolina State University, focusing on biologically-inspired computer vision, and applying it to research areas ranging from robotics to cognitive science. At Udacity, he works with partners from both academia and industry to build practical artificial intelligence and machine learning courses. Arpan enjoys exploring the outdoors through hiking and backpacking.