Summary

Natural Language lies at the heart of current developments in Artificial Intelligence, User Interaction and Information Processing. The combination of unprecedented corpora of written text provided by Social Media and the massification of computational power has led to increased interest in the development of modern NLP tools based on state-of-the-art Deep Learning tools.

In this lecture, we will introduce participants to the fundamental concepts’ algorithms used for Natural Language Processing through an in-depth exploration of different examples built using the Keras Python framework for Deep Learning. Applications to real datasets will be explored in detail.


Program

  • Foundations of NLP

    • One-Hot Encoding

    • TF/IDF and Stemming

    • Stopwords

    • N-grams

    • Working with Word Embeddings

  • Neural Networks with Keras

    • Activation Functions

    • Loss Functions

    • Training procedures

    • Network Architectures

  • Text classification

    • Feed Forward Networks

    • Convolutional Neural Networks

    • Applications

  • Word Embeddings

    • Motivations

    • Skip-gram and Continuous Bag of words

    • Transfer Learning

  • Sequence Modeling

    • Recurrent Network Networks

    • Gated Recurrent Unit

    • Long-Short Term Memory

    • Encoder-Decoder Models

    • Text Generation


Resources