Cubit - A Cube Pruning Decoder for Phrase-based Translation
[ About | Download | Related Papers ]
Welcome! This page contains information about Cubit, an efficient Python implementation
of phrase-based decoding, à la Pharaoh, but
using Cube Pruning
inspired by k-best parsing to
accelerate the language model integration (hence the name "cubit").
Under typical parameter settings,
it can achieve 10-30 fold relative speed up (at the same level of search errors)
against conventional beam search, or an even bigger speed up
at the same level of BLEU.
It is described in Section 5.1 of the following paper:
Source code will be available for download soon.
- Version 0.8 (only for referencial uses for implementation of cube pruning). Released Feb. 27, 2008.
The manual will contain a more detailed description of the adaptation of cube
pruning to phrase-based decoding.
The name "cubit" is suggested by Jonathan May.
Last modified: Wed Feb 27 14:44:57 EST 2008