BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Topic Modeling: Beyond Bag-of-Words - Hanna Wallach\, Inference Gr
 oup
DTSTART:20060222T150000Z
DTEND:20060222T160000Z
UID:TALK4804@talks.cam.ac.uk
CONTACT:Phil Cowans
DESCRIPTION:Some models of textual corpora employ text generation methods 
 involving n-gram statistics\, while others use latent topic variables infe
 rred using the ``bag-of-words'' assumption\, in which word order is ignore
 d. Previously\, these methods have not been combined. In this talk\, I pre
 sent a hierarchical generative probabilistic model that incorporates both 
 $n$-gram statistics and latent topic variables\, by extending a unigram to
 pic model to include properties of a hierarchical Dirichlet bigram languag
 e model.
LOCATION:Ryle Seminar Room\, Cavendish Laboratory
END:VEVENT
END:VCALENDAR