BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:A Weakly-supervised Approach to Argumentative Zoning of Scientific
  Documents - Yufan Guo\, University of Cambridge
DTSTART:20110718T110000Z
DTEND:20110718T120000Z
UID:TALK32129@talks.cam.ac.uk
CONTACT:Thomas Lippincott
DESCRIPTION:Argumentative Zoning (AZ) – analysis of the argumentative st
 ructure of a scientific paper – has proved useful for a number of inform
 ation access tasks. Current approaches to AZ rely on supervised machine le
 arning (ML). Requiring large amounts of annotated data\, these approaches 
 are expensive to develop and port to different domains and tasks. A potent
 ial solution to this problem is to use weaklysupervised ML instead. We inv
 estigate the performance of four weakly-supervised classifiers on scientif
 ic abstract data annotated for multiple AZ classes. Our best classifier ba
 sed on the combination of active learning and selftraining outperforms our
  best supervised classifier\, yielding a high accuracy of 81% when\nusing 
 just 10% of the labeled data. This result suggests that weakly-supervised 
 learning could be employed to improve the practical applicability and port
 ability of AZ across different information access tasks. 
LOCATION:FW09\, Computer Laboratory
END:VEVENT
END:VCALENDAR