BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Entity-based Models for Discourse Structure - Micha Elsner\, Unive
 rsity of Edinburgh
DTSTART:20120316T140000Z
DTEND:20120316T150000Z
UID:TALK36957@talks.cam.ac.uk
CONTACT:Ekaterina Kochmar
DESCRIPTION:A well-written text follows an overall structure\, with each s
 entence following naturally from the ones before and leading into the ones
  which come afterwards. We call this structure 'coherence'\; without it\, 
 a document becomes a confusing series of non sequiturs. Understanding the 
 principles that make a text coherent is an important goal of natural langu
 age processing. These principles can be applied to the design of systems t
 hat create new documents\, like summaries\, or evaluate the writing style 
 of existing documents.\n\nIn this talk\, I focus on entity-based coherence
 \, the structural principles dictating the way a text refers to objects in
  the world. I will present models that describe the way important entities
  are introduced to the discourse and subsequently referred to\, and that a
 utomatically determine which phrases refer to important entities and which
  do not. I will also discuss several methods for evaluating models of cohe
 rence\, showing in particular that conversational language poses a challen
 ge for several models that work well on text.\n\nI will also present some 
 new work on the high-level plot structure of novels. Plot is a higher-leve
 l structure than coherence\, and cannot be modeled purely in terms of sent
 ences\; I will present a system that represents novels in terms of charact
 ers and their emotions over time. Finally\, I will discuss the lessons we 
 can learn from sentence-level models when designing such a high-level syst
 em. 
LOCATION:FW26\, Computer Laboratory
END:VEVENT
END:VCALENDAR