daniel shiffman

Programming from A to Z

(Everything you wanted to know about text but were afraid to ask.)

Spring 2008 syllabus: http://itp.nyu.edu/varwiki/Syllabus/A2Z-S08

The beginning

Regular Expressions

The Concordance

Bayesian Text Analysis

Spiders

Mining

WordNet

Generative Text

Threads

Course Description

There are 16,000 free books in the Project Gutenberg digital catalog. Google print is scanning millions. With all this digitized text, what can we do with it beyond simply search and browse? This course will focus on programming strategies and techniques behind procedural analysis and generation of text. We’ll explore topics ranging from evaluating text according to its statistical properties to the automated production of text via artificial intelligence. Student will be encouraged to develop their own systems and methods, from poetry machines to intelligent spiders to evolutionary language generators, etc. Examples will be demonstrated using Java and Processing with a focus on advanced data structures (linked lists, hash tables, binary trees) associated with storing and manipulating text. Prerequisite: H79.2233 Introduction to Computational Media or equivalent programming experience.

Some links:

comments powered by Disqus