https://github.com/moses-smt/giza-pp

GIZA++ is a statistical machine translation toolkit that is used to train IBM Models 1-5 and an HMM word alignment model. This package also contains the source for the mkcls tool which generates the word classes necessary for training some of the alignment models.
https://github.com/moses-smt/giza-pp

Last synced: 1 day ago
JSON representation

GIZA++ is a statistical machine translation toolkit that is used to train IBM Models 1-5 and an HMM word alignment model. This package also contains the source for the mkcls tool which generates the word classes necessary for training some of the alignment models.

• Host: GitHub
• URL: https://github.com/moses-smt/giza-pp
• Owner: moses-smt
• Created: 2015-03-17T15:09:44.000Z (almost 10 years ago)
• Default Branch: master
• Last Pushed: 2023-03-31T17:14:49.000Z (almost 2 years ago)
• Last Synced: 2025-02-06T21:12:08.305Z (9 days ago)
• Language: C++
• Homepage:
• Size: 256 KB
• Stars: 264
• Watchers: 23
• Forks: 82
• Open Issues: 7
• Metadata Files:
  • Readme: README

Awesome Lists containing this project

• low-resource-languages - giza-pp - GIZA++ is a statistical machine translation toolkit that is used to train IBM Models 1-5 and an HMM word alignment model. This package also contains the source for the mkcls tool which generates the word classes necessary for training some of the alignment models. (Software / Utilities)

README

        
This package contains the GIZA++ toolkit and the mkcls tool, originally

written by F.J. Och and several other authors.

For more information, refer to the README files and the following pages:

  http://www.fjoch.com/mkcls.html

  http://www.fjoch.com/GIZA++.html

UPDATE 4th April 2015, by Hieu Hoang:

Works with most versions of gcc and clang, including really old versions.

Why not try using mgiza? It's multi-threaded and kept up to date to work with most compilers

   https://github.com/moses-smt/mgiza