BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Open Problems for Literary Text Generation in the WASP System - Pa
 blo Gervas - Universidad Complutense de Madrid
DTSTART:20101015T110000Z
DTEND:20101015T120000Z
UID:TALK27506@talks.cam.ac.uk
CONTACT:Thomas Lippincott
DESCRIPTION:For a large portion of its now substantial life\, natural lang
 uage processing (NLP) has developed under two restricting assumptions: tha
 t research should focus on subtasks until these are mature enough to be in
 tegrated\, and that research should concentrate on easy texts before addre
 ssing more complex ones. These restrictions are based on sound engineering
  principles and they have allowed NLP as a research field to survive in sp
 ite of the difficulty of the overall task. The current level of maturity o
 f some of these subtasks\, and the glass ceilings that many of them appear
  to have reached suggest that it may be time to venture a little beyond. R
 esearch on the generation of literary texts provides the opportunity to do
  so. It forces the consideration of several of these subtasks in cooperati
 on\, and it requires the analysis of complex phenomena\, such as narrative
 \, figurative language\, or linguistic creativity that are usually avoided
  in NLP. This talk will address some of these open problems and outline th
 eir potential and their difficulties. It will show how engineering conside
 rations suggest that language analysis and language generation should be c
 onsidered in tandem to address these problems\, and how some currently acc
 epted architectures may need to be revised to accommodate some of these ph
 enomena. To illustrate these points\, the current scope and architecture o
 f the WASP poetry generation system will be described and discussed. Over 
 the last ten years\, the WASP system has been substantially overhauled bot
 h to expand the range of phenomena it considers and to integrate as many a
 s possible of the available NLP technologies. Although this is work in pro
 gress\, it already shows some interesting insights concerning system archi
 tecture and knowledge representation. These insights will be described\, a
 nd open lines of future work will be discussed.
LOCATION:FW26\, Computer Laboratory
END:VEVENT
END:VCALENDAR