Parallelizing a machine translation decoder for multicore computer

Machine translation (MT), with its broad potential use, has gained increased attention from both researchers and software vendors. To generate high quality translations, however, MT decoders can be highly computation intensive. With significant raw computing power, multi-core microprocessors have th...

Full description

Saved in:
Bibliographic Details
Published in2011 Seventh International Conference on Natural Computation Vol. 4; pp. 2220 - 2225
Main Authors Long Chen, Wei Huo, Haitao Mi, Zhaoqing Zhang, Xiaobing Feng, Zhiyuan Li
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.07.2011
Subjects
Computational modeling
Decoding
Instruction sets
Load modeling
Memory management
Sorting
Online AccessGet full text

Cover

More Information
Summary:Machine translation (MT), with its broad potential use, has gained increased attention from both researchers and software vendors. To generate high quality translations, however, MT decoders can be highly computation intensive. With significant raw computing power, multi-core microprocessors have the potential to speed up MT software on desktop machines. However, retrofitting existing MT decoders is a nontrivial issue. Race conditions and atomicity issues are among those complications making parallelization difficult. In this article, we show that, to parallelize a state-of-the-art MT decoder, it is much easier to overcome such difficulties by using a process-based parallelization method, called functional task parallelism, than using conventional thread-based methods. We achieve a 7.60 times speed up on an 8-core desktop machine while making significantly less changes to the original sequential code than required by using multiple threads.
ISBN:9781424499502
142449950X
ISSN:2157-9555
DOI:10.1109/ICNC.2011.6022551