Skip to Main Content

Data Services Class Descriptions

Information, materials, and schedules for all currently offered Data Services classes.

Introduction to Natural Language Processing (NLP)

Natural language processing is an unsupervised method to process unstructured texts, such as research papers, newspapers, tweets, etc. Various algorithms, with examples, will be introduced. Hands-on component is optional, but for those who want to participate, basic knowledge of Linux and python is a plus.
Software: Python, Gensim, Scikit-learn
Duration: 120 min

Room description:

Some tutorials are held remotely and require NYU sign on to access, while others are held in person, without a remote component. Please note the correct modality and location of the tutorial when registering

Prerequisites:
  • Basic knowledge of Linux
  • Basic knowledge of Python
Skills Taught / Learning Outcomes:
  • command the basic concepts of natural language processing and machine learning
  • develop introductory hands-on experience in natural language processing
Class Materials:
  1. https://en.wikipedia.org/wiki/Natural_language_processing
  2. http://mccormickml.com/2016/04/19/word2vec-tutorial-the-skip-gram-model/
  3. http://mccormickml.com/2017/01/11/word2vec-tutorial-part-2-negative-sampling
Related Classes:

Introduction to Unix/Linux and the Shell

Introduction to Python

Additional Training Materials:

https://github.com/peizong/alloy2vec

Feedback: bit.ly/feedbackds

Upcoming sessions for this tutorial