O'Reilly logo
live online training icon Live Online training

NLP with Deep Learning for Everyone

Implementing Text Classification, Sequence to Sequence Models and Word Embedding Approaches with Keras

Topic: Data
Bruno Gonçalves

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 and 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.

What you'll learn-and how you can apply it

  • Text representation
  • Sentiment analysis
  • Text Generation
  • Text classification
  • Word Embeddings
  • Neural Networks
  • Deep Networks

This training course is for you because...

  • You need to learn how to process text data
  • You want to understand how Keras can be used for NLP
  • You want to apply deep learning approaches to text processing, understanding and generation


  • Python
  • Basic Neural Networks

Course Set-up

  • Python
  • Pandas
  • Keras
  • Tensorflow

Recommended Preparation

  • Live Online Training: Natural Language Processing (NLP) For Everyone by Bruno Gonçalves on the O'Reilly Learning Platform

  • Live Online Training: Deep Learning For Everyone by Bruno Gonçalves on the O'Reilly Learning Platform

About your instructor

  • Bruno Gonçalves is currently a Senior Data Scientist working at the intersection of Data Science and Finance. Previously, he was a Data Science fellow at NYU's Center for Data Science while on leave from a tenured faculty position at Aix-Marseille Université. Since completing his PhD in the Physics of Complex Systems in 2008 he has been pursuing the use of Data Science and Machine Learning to study Human Behavior. Using large datasets from Twitter, Wikipedia, web access logs, and Yahoo! Meme he studied how we can observe both large scale and individual human behavior in an obtrusive and widespread manner. The main applications have been to the study of Computational Linguistics, Information Diffusion, Behavioral Change and Epidemic Spreading. In 2015 he was awarded the Complex Systems Society's 2015 Junior Scientific Award for "outstanding contributions in Complex Systems Science" and in 2018 is was named a Science Fellow of the Institute for Scientific Interchange in Turin, Italy.


The timeframes are only estimates and may vary according to how the class is progressing

Segment 1: Foundations of NLP
Length: 50 mins

  • One-Hot Encoding
  • TF/IDF and Stemming
  • Stopwords
  • N-grams
  • Working with Word Embeddings

Break (length: 10 mins)

Segment 2: Neural Networks with Keras Length: 60 mins

  • Activation Functions
  • Loss Functions
  • Training procedures
  • Network Architectures

Break (length: 10 mins)

Segment 3: Text classification Length: 30 mins

  • Feed Forward Networks
  • Convolutional Neural Networks
  • Applications

Break (length: 5 mins)

Segment: 4 Word Embeddings Length: 30 mins

  • Motivations
  • Skip-gram and Continuous Bag of words
  • Transfer Learning

Break (length: 5 mins)

Segment 5: Sequence Modeling Length: 40 mins

  • Recurrent Network Networks
  • Gated Recurrent Unit
  • Long-Short Term Memory
  • Encoder-Decoder Models
  • Text Generation