Date and time: 11.30 - 12.30, Friday 27th March, 2009
Venue: 10.08.04 (Building 10, Level 8, Room 4)
Abstract:
Topic models, a class of Bayesian statistical models for discrete data, have recently gained popularity in applications ranging from document modeling to computer vision. Since the 2003 introduction of Latent Dirichlet Allocation (the original topic model), there have been numerous extensions to this model. I will review the theory behind topic modelling and show some recent results of algorithmic improvements. I will then discuss an array of application domains from improving search in digital libraries to understanding scientific disciplines using topic maps.
About the speaker:
David Newman is a Research
Scientist at NICTA VRL, currently on leave from his Research Faculty position
in the Department of Computer Science at the
Seminar Organisation
Seminars are free and open to the general public. No booking is necessary. If you are interested in giving a presentation in this seminar series, or to make suggestions for speakers, please contact Xiaodong Li, the seminar co-ordinator.