BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Imitation learning for language generation - Gerasimos Lampouras (
 Sheffield)
DTSTART:20180531T100000Z
DTEND:20180531T110000Z
UID:TALK106441@talks.cam.ac.uk
CONTACT:Dimitri Kartsaklis
DESCRIPTION:Natural language generation (NLG) is the task of generating na
 tural language from a meaning representation. Rule-based approaches requir
 e domain-specific and manually constructed linguistic resources\, while mo
 st corpus based approaches rely on aligned training data and/or phrase tem
 plates. The latter are needed to restrict the search space for the structu
 red prediction task defined by the unaligned datasets.  In this talk we wi
 ll discuss the use of imitation learning for structured prediction which l
 earns an incremental model that handles the large search space while avoid
 ing explicitly enumerating it. We will show how we adapted the Locally Opt
 imal Learning to Search (Chang et al.\, 2015) framework which allows us to
  train against non-decomposable loss functions such as the BLEU or ROUGE s
 cores while not assuming gold standard alignments. Furthermore\, we will p
 resent an analysis of the datasets which examines common issues with NLG e
 valuation.
LOCATION:Boardroom\, Faculty of English\, West Road
END:VEVENT
END:VCALENDAR