BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//talks.cam.ac.uk//v3//EN
BEGIN:VTIMEZONE
TZID:Europe/London
BEGIN:DAYLIGHT
TZOFFSETFROM:+0000
TZOFFSETTO:+0100
TZNAME:BST
DTSTART:19700329T010000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=-1SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0100
TZOFFSETTO:+0000
TZNAME:GMT
DTSTART:19701025T020000
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=-1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
CATEGORIES:NLIP Seminar Series
SUMMARY:Entity-based Models for Discourse Structure - Mich
 a Elsner\, University of Edinburgh
DTSTART;TZID=Europe/London:20120316T140000
DTEND;TZID=Europe/London:20120316T150000
UID:TALK36957AThttp://talks.cam.ac.uk
URL:http://talks.cam.ac.uk/talk/index/36957
DESCRIPTION:A well-written text follows an overall structure\,
  with each sentence following naturally from the o
 nes before and leading into the ones which come af
 terwards. We call this structure 'coherence'\; wit
 hout it\, a document becomes a confusing series of
  non sequiturs. Understanding the principles that 
 make a text coherent is an important goal of natur
 al language processing. These principles can be ap
 plied to the design of systems that create new doc
 uments\, like summaries\, or evaluate the writing 
 style of existing documents.\n\nIn this talk\, I f
 ocus on entity-based coherence\, the structural pr
 inciples dictating the way a text refers to object
 s in the world. I will present models that describ
 e the way important entities are introduced to the
  discourse and subsequently referred to\, and that
  automatically determine which phrases refer to im
 portant entities and which do not. I will also dis
 cuss several methods for evaluating models of cohe
 rence\, showing in particular that conversational 
 language poses a challenge for several models that
  work well on text.\n\nI will also present some ne
 w work on the high-level plot structure of novels.
  Plot is a higher-level structure than coherence\,
  and cannot be modeled purely in terms of sentence
 s\; I will present a system that represents novels
  in terms of characters and their emotions over ti
 me. Finally\, I will discuss the lessons we can le
 arn from sentence-level models when designing such
  a high-level system. 
LOCATION:FW26\, Computer Laboratory
CONTACT:Ekaterina Kochmar
END:VEVENT
END:VCALENDAR