Brought to you by NumFOCUS Foundation and O’Reilly Media Inc.
The official Jupyter Conference
August 22-23, 2017: Training
August 23-25, 2017: Tutorials & Conference
New York, NY

Interactive natural language processing with SpaCy and Jupyter

Aaron Kramer (
1:30pm–5:00pm Wednesday, August 23, 2017
Usage and application
Location: Concourse F Level: Intermediate
Average rating: ***..
(3.00, 2 ratings)

Who is this presentation for?

  • Analysts and data scientists

Prerequisite knowledge

  • The ability to read generic code

Materials or downloads needed in advance

What you'll learn

  • Understand natural language processing basic concepts, including part-of-speech tagging, word embeddings/vector space models, and syntactic parsing
  • Explore examples of interacting with NetworkX graphs representing parse trees and visualizations with Matplotlib
  • Learn how to do interactive NLP with SpaCy within the Jupyter Notebook


Modern natural language processing (NLP) workflows often require interoperability between multiple tools, with components like SpaCy for stochastic parsing, TensorFlow for deep learning, and JavaScript or D3 for visualization. Aaron Kramer offers an introduction to interactive NLP with SpaCy within the Jupyter Notebook, covering core NLP concepts, core workflows in SpaCy, and examples of interacting with other tools like TensorFlow, NetworkX, LIME, and others as part of interactive NLP projects. Along the way, Aaron walks you through training a deep learning mode, loading it into SpaCy, and explaining your NLP models with LIME.

Photo of Aaron Kramer

Aaron Kramer

Aaron Kramer is a data scientist and engineer at, where he builds powerful language and engagement models using natural language processing, deep learning, Bayesian inference, and machine learning.

Comments on this page are now closed.


Picture of Aaron Kramer
08/22/2017 7:55am EDT

Hi everyone! Looking forward to our session tomorrow.

Please remember to have git and docker set up!

Setup instructions are here: