BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Randomized Language Models via Perfect Hash Functions - Lin Sun
DTSTART:20100222T123000Z
DTEND:20100222T133000Z
UID:TALK23269@talks.cam.ac.uk
CONTACT:Diarmuid Ó Séaghdha
DESCRIPTION:At this session of the NLIP Reading Group we’ll be discussin
 g the following paper:\n\nDavid Talbot and Thorsten Brants. 2008. "Randomi
 zed Language Models via Perfect Hash Functions":http://aclweb.org/antholog
 y-new/P/P08/P08-1058.pdf. In Proceedings of ACL-08.\n\n*Abstract:*\nWe pro
 pose a succinct randomized language model which employs a perfect hash fun
 ction to encode fingerprints of n-grams and their associated probabilities
 \, backoff weights\, or other parameters. The scheme can represent any sta
 ndard n-gram model and is easily combined with existing model reduction te
 chniques such as entropy-pruning. We demonstrate the space-savings of the 
 scheme via machine translation experiments within a distributed language m
 odeling framework.
LOCATION:GS15\, Computer Laboratory
END:VEVENT
END:VCALENDAR