BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Text Data Mining using Topic Modeling - Ioana Bica\, Churchill Col
 lege
DTSTART:20161102T190000Z
DTEND:20161102T193000Z
UID:TALK68948@talks.cam.ac.uk
CONTACT:Matthew Ireland
DESCRIPTION:As we gather more and more data\, it is becoming increasingly 
 difficult to find the information that we need. However\, text data mining
  tools can provide us with ways of organizing all this information in a us
 eful and accessible way. In particular\, discovering the patterns in a doc
 ument using topic modeling can help us annotate and search through documen
 ts based on their themes. My talk will present how the Latent Dirichlet Al
 location performs the task of extracting a certain number of topics from a
  document by utilising a probabilistic model which assumes that each docum
 ent is arising from a generative process. Furthermore\, we shall also inve
 stigate how a Bayesian nonparametric model\, namely the Chinese Restaurant
  Process\, can  be employed when the number of topics in a document is not
  known in advance.  Finally\, we shall see how topic hierarchies can be bu
 ilt by exploiting the Nested Chinese Restaurant Process.
LOCATION:Club Room\, Churchill College
END:VEVENT
END:VCALENDAR