BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:First Step toward Neural Machine Translation - Kyunghyun Cho\, Uni
 versity of Montreal
DTSTART:20141023T110000Z
DTEND:20141023T120000Z
UID:TALK54326@talks.cam.ac.uk
CONTACT:Tamara Polajnar
DESCRIPTION:Neural machine translation is a recently introduced approach t
 o tackling machine translation. Unlike the conventional approach\, neural 
 machine translation aims to build a translation system that consists of a 
 single neural network\, where the whole system is jointly trained to maxim
 ize the conditional probability of a translation given a source sentence. 
 In this talk\, I will first introduce a basic concept of neural machine tr
 anslation and demonstrate the working neural translation system. Then\, I 
 will describe how we incorporated attention mechanism into an encoder-deco
 der model to achieve translation performance comparable to the conventiona
 l phrase-based machine translation system (http://arxiv.org/abs/1409.0473)
 \n
LOCATION:FW26\, Computer Laboratory
END:VEVENT
END:VCALENDAR