Tera-Scale Translation Models via Pattern Matching

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Translation model size is growing at a pace that outstrips improvements in computing power, and this hinders research on many interesting models. We show how an algorithmic scaling technique can be used to easily handle very large models. Using this technique, we explore several large model variants and show an improvement 1.4 BLEU on the NIST 2006 Chinese-English task. This opens the door for work on a variety of models that are much less constrained by computational limitations.
Original languageEnglish
Title of host publicationProceedings of the 22nd International Conference on Computational Linguistics (Coling 2008)
Place of PublicationManchester, UK
PublisherColing 2008 Organizing Committee
Pages505-512
Number of pages8
Publication statusPublished - 1 Aug 2008

Fingerprint

Dive into the research topics of 'Tera-Scale Translation Models via Pattern Matching'. Together they form a unique fingerprint.

Cite this