BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Identifying Deixis to Communicative Artifacts in Text - Shomir Wil
 son\, University of Edinburgh and Carnegie Mellon University
DTSTART:20140509T110000Z
DTEND:20140509T120000Z
UID:TALK52402@talks.cam.ac.uk
CONTACT:Tamara Polajnar
DESCRIPTION:Text written to inform often contains deixis to communicative 
 artifacts such as textual structures (e.g.\, sections and lists)\, discour
 se entities\, and illustrations. By relating such artifacts to the prose\,
  "artifact deixis" plays an essential role in structuring the flow of info
 rmation. In this talk I will describe ongoing work toward the goal of auto
 matically detecting artifact deixis and its referents. First I will situat
 e the phenomenon with related metalinguistic phenomena\, applying prior wo
 rk to its characterization. Next\, I will describe recent results of a stu
 dy of artifact deixis using a corpus rich in determiner-established instan
 ces of the phenomenon (e.g.\, “this section”\, “these equations”\,
  “those reasons”) sourced from Wikibooks\, a collection of learning te
 xts. This corpus is used in combination with WordNet to determine a set of
  word senses that are characteristic of the phenomenon\, showing its diver
 sity and validating intuitions about its qualities. The results motivate f
 urther research to extract the connections encoded by such deixis\, with t
 he goals of enhancing tools to present pedagogical e-texts to readers and\
 , more broadly\, improving language technologies that rely on deictic phen
 omena.
LOCATION:FW26\, Computer Laboratory
END:VEVENT
END:VCALENDAR