BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Unsupervised learning of rhetorical structure with un-topic models
  - Diarmuid Ó Séaghdha\, University of Cambridge
DTSTART:20140815T110000Z
DTEND:20140815T113000Z
UID:TALK53642@talks.cam.ac.uk
CONTACT:Ekaterina Kochmar
DESCRIPTION:In this paper we investigate whether unsupervised models can b
 e used to induce conventional aspects of rhetorical language in scientific
  writing. We rely on the intuition that the rhetorical language used in a 
 document is general in nature and independent of the document’s topic. W
 e describe a Bayesian latent-variable model that implements this intuition
 . In two empirical evaluations based on the task of argumentative zoning (
 AZ)\, we demonstrate that our generality hypothesis is crucial for disting
 uishing between rhetorical and topical language and that features provided
  by our unsupervised model trained on a large corpus can improve the perfo
 rmance of a supervised AZ classifier.
LOCATION:FW26\, Computer Laboratory
END:VEVENT
END:VCALENDAR