BEGIN:VCALENDAR
PRODID:-//eluceo/ical//2.0/EN
VERSION:2.0
CALSCALE:GREGORIAN
BEGIN:VEVENT
UID:www.tcs.tifr.res.in/event/145
DTSTAMP:20230914T125912Z
SUMMARY:Latent Dirichlet Allocation forText Segmentation
DESCRIPTION:Speaker: Hemant Misra\nXerox Research Center Europe\nFrance\nht
 tp://www.dcs.gla.ac.uk/~hemant\n\nAbstract: \nIn this presentation\, first
  we visit latent Dirichlet allocation (LDA)\, an unsupervised topic model\
 , and propose its application for the task of text segmentation. The propo
 sed methodology has state-of-the-art performance on a benchmark database\,
  is able to perform segmentation in an online manner\, and assigns a meani
 ngful topic distribution to each segment. The last point is particularly i
 nteresting for information retrieval at segment level. Another important d
 iscussion will be on how the computational cost associated with the dynami
 c programming (DP) algorithm typically used for the search can be reduced 
 by a factor of more than 95%\, and the usability of this result to the ent
 ire domain of text segmentation.\n
URL:https://www.tcs.tifr.res.in/web/events/145
DTSTART;VALUE=DATE:20101228
LOCATION:A-212 (STCS Seminar Room)
END:VEVENT
END:VCALENDAR