BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:General-purpose representation learning from words to sentences - 
 Felix Hill\, University of Cambridge
DTSTART:20160329T083000Z
DTEND:20160329T093000Z
UID:TALK64602@talks.cam.ac.uk
CONTACT:44515
DESCRIPTION:Real-valued vector representations of words (i.e. embeddings) 
 that are trained on naturally occurring data by optimising general-purpose
  objectives are useful for a range of downstream language tasks. However\,
  the picture is less clear for larger linguistic units such as phrases or 
 sentences. Phrases and sentences typically encode the facts and propositio
 ns that constitute the 'general knowledge' missing from many NLP systems a
 t present\, so the potential benefit of making representation-learning wor
 k for these units is huge. I will present a systematic comparison of (both
  novel and existing) ways of inducing such representations with neural lan
 guage models. The results demonstrate clear and interesting differences be
 tween the representations learned by different methods\; in particular\, m
 ore elaborate or computationally expensive methods are not necessarily bes
 t. I'll also discuss a key challenge facing all research in unsupervised o
 r representation learning for NLP - the lack of robust evaluations.  
LOCATION:Auditorium\, Microsoft Research Ltd\, 21 Station Road\, Cambridge
 \, CB1 2FB
END:VEVENT
END:VCALENDAR