Edinburgh Research Archive logo

Edinburgh Research Archive

University of Edinburgh homecrest
View Item 
  •   ERA Home
  • Informatics, School of
  • Informatics thesis and dissertation collection
  • View Item
  •   ERA Home
  • Informatics, School of
  • Informatics thesis and dissertation collection
  • View Item
  • Login
JavaScript is disabled for your browser. Some features of this site may not work without it.

Fast machine translation on parallel and massively parallel hardware

View/Open
Bogoychev2019.pdf (3.170Mb)
Date
01/07/2019
Author
Bogoychev, Nikolay Veselinov
Metadata
Show full item record
Abstract
Parallel systems have been widely adopted in the field of machine translation, because the raw computational power they offer is well suited to this computationally intensive task. However programming for parallel hardware is not trivial as it requires redesign of the existing algorithms. In my thesis I design efficient algorithms for machine translation on parallel hardware. I identify memory accesses as the biggest bottleneck to processing speed and propose novel algorithms that minimize them. I present three distinct case studies in which minimizing memory access substantially improves speed: Starting with statistical machine translation, I design a phrase table that makes decoding ten times faster on a multi-threaded CPU. Next, I design a GPU-based n-gram language model that is twice as fast per £ as a highly optimized CPU implementation. Turning to neural machine translation, I design new stochastic gradient descent techniques that make end-to-end training twice as fast. The work in this thesis has been incorporated in two popular machine translation toolkits: Moses and Marian.
URI
http://hdl.handle.net/1842/35886
Collections
  • Informatics thesis and dissertation collection

Library & University Collections HomeUniversity of Edinburgh Information Services Home
Privacy & Cookies | Takedown Policy | Accessibility | Contact
Privacy & Cookies
Takedown Policy
Accessibility
Contact
feed RSS Feeds

RSS Feed not available for this page

 

 

All of ERACommunities & CollectionsBy Issue DateAuthorsTitlesSubjectsPublication TypeSponsorSupervisorsThis CollectionBy Issue DateAuthorsTitlesSubjectsPublication TypeSponsorSupervisors
LoginRegister

Library & University Collections HomeUniversity of Edinburgh Information Services Home
Privacy & Cookies | Takedown Policy | Accessibility | Contact
Privacy & Cookies
Takedown Policy
Accessibility
Contact
feed RSS Feeds

RSS Feed not available for this page