BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//talks.cam.ac.uk//v3//EN
BEGIN:VTIMEZONE
TZID:Europe/London
BEGIN:DAYLIGHT
TZOFFSETFROM:+0000
TZOFFSETTO:+0100
TZNAME:BST
DTSTART:19700329T010000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=-1SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0100
TZOFFSETTO:+0000
TZNAME:GMT
DTSTART:19701025T020000
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=-1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
CATEGORIES:Machine Learning Reading Group @ CUED
SUMMARY:Topics in Statistical Machine Translation - Matt S
hannon and Sebastien Bratieres
DTSTART;TZID=Europe/London:20100520T140000
DTEND;TZID=Europe/London:20100520T153000
UID:TALK24003AThttp://talks.cam.ac.uk
URL:http://talks.cam.ac.uk/talk/index/24003
DESCRIPTION:We're going to talk about statistical machine tran
slation (SMT). We'll cover some basic SMT models\
, outline the improvements that have turned out to
give the biggest gains\, and talk about two exten
sions in more detail.\n\nFirstly we'll discuss how
MapReduce can be used for SMT:\n\nT. Brants\, A.
Popat\, P. Xu\, F. Och\, and J. Dean\, “Large Lang
uage Models in Machine Translation\,” Proceedings
of the 2007 Joint Conference on Empirical Methods
in Natural Language Processing and Computational N
atural Language Learning (EMNLP-CoNLL)\, 2007\, pp
. 867\, 858.\n\nC. Dyer\, A. Cordova\, A. Mont\, a
nd J. Lin\, “Fast\, easy\, and cheap:\nConstructio
n of statistical machine translation models with M
apReduce\,” Proceedings of the Third Workshop on S
tatistical Machine Translation\, 2008\, pp. 199–20
7.\n\nThen we'll talk about hierarchical phrase-ba
sed translation\, which is theoretically pretty as
well as giving significant improvements in\ntrans
lation:\n\nChiang (2005) - "A hierarchical phrase-
based model for statistical machine translation" (
http://acl.ldc.upenn.edu/P/P05/p05-1033.pdf)\n\nG.
Iglesias\, A. de Gispert\, E. R. Banga and W. Byr
ne. (2009) "Hierarchical Phrase-Based Translation
with Weighted Finite State Transducers" (http://ww
w.aclweb.org/anthology-new/N/N09/N09-1049.pdf)\n\n
Background material we've found helpful includes t
he book "Statistical Machine Translation" by Koehn
(2009) (http://www.statmt.org/)\, and the review
paper by Lopez (2008) "Statistical Machine Transla
tion"\n(http://homepages.inf.ed.ac.uk/alopez/paper
s/survey.pdf).\n
LOCATION:Engineering Department\, CBL Room 438
CONTACT:Shakir Mohamed
END:VEVENT
END:VCALENDAR