BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Multilingual Image Description with Neural Sequence Models - Eva H
 asler\, University of Cambridge
DTSTART:20160205T120000Z
DTEND:20160205T130000Z
UID:TALK62971@talks.cam.ac.uk
CONTACT:Kris Cao
DESCRIPTION:We introduce multilingual image description\, the task of gene
 rating descriptions of images given data in multiple languages. This can b
 e viewed as visually-grounded machine translation\, allowing the image to 
 play a role in disambiguating language. We present models for this task th
 at are inspired by neural models for image description and machine transla
 tion. Our multilingual image description models generate target-language s
 entences using features transferred from separate models: multimodal featu
 res from a monolingual source-language image description model and visual 
 features from an object recognition model. In experiments on a dataset of 
 images paired with English and German sentences\, using BLEU and Meteor as
  a metric\, our models substantially improve upon existing monolingual ima
 ge description models.
LOCATION:FW26\, Computer Laboratory
END:VEVENT
END:VCALENDAR