English: Imagine a Chinese restaurant, in which customers enter. A new customer sits down at a table with a probability proportional to the number of customers already sitting there. Additionally, a customer opens a new table with a probability proportional to the scaling parameter a=0.5. This is indicated by a red pseudo-table with a fixed number of 0.5 customers. After infinitely many customers entered, one obtains a probability distribution over infinitely many categories, which together with samples from the base measure H yields a random sample of the Dirichlet process DP(0.5,H). (Tables are hidden once the customers of a table can not be displayed anymore; however, every table has infinitely many seats.)

Interactive animation available at: http://topicmodels.west.uni-koblenz.de/ckling/tmt/crp.html?parameters=0.5&dp=1#

Command used for recording the animation on a 1920x1200 monitor with byzanz: byzanz-record --duration=30 --delay=5 --x=0 --y=108 --width=800 --height=276 --cursor=0 test.gif