BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Analyzing and Summarizing Movies using Turning Points - Frank Kell
 er (University of Edinburgh)
DTSTART:20211119T120000Z
DTEND:20211119T130000Z
UID:TALK164458@talks.cam.ac.uk
CONTACT:Huiyuan Xie
DESCRIPTION:Join Zoom Meeting\nhttps://cl-cam-ac-uk.zoom.us/j/98526954309?
 pwd=UVl2TkJxN3hyMUtLTzlZQVhuOVFxdz09\n\nMeeting ID: 985 2695 4309\nPasscod
 e: 870201\n\nAccording to screenwriting theory\, turning points (e.g.\, ch
 ange of\nplans\, major setback\, climax) are crucial narrative moments in 
 a\nmovie: They define the plot structure\, determine its progression and\n
 segment the movie into thematic units. We propose the task of turning\npoi
 nt identification a means of analyzing the narrative structure of a\nmovie
 \; turning points and the segmentation they provide facilitate the\nproces
 sing long\, complex narratives. We introduce a dataset of movie\nsynopses 
 annotated with turning points\, and show how neural networks\ncan be train
 ed to identify turning points automatically. We then use\nthis the basis f
 or graph-based neural models which perform movie\nsummarization and traile
 r generation automatically.
LOCATION:Virtual (Zoom)
END:VEVENT
END:VCALENDAR