mirror of
https://github.com/moses-smt/mosesdecoder.git
synced 2024-12-27 22:14:57 +03:00
5240c430ce
This adds a new string-to-tree decoder, which can be enabled with the -s2t option. It's intended to be faster and simpler than the generic chart decoder, and is designed to support lattice input (still WIP). For a en-de system trained on WMT14 data, it's approximately 40% faster in practice. For background information, see the decoding section of the EMNLP tutorial on syntax-based MT: http://www.emnlp2014.org/tutorials/5_notes.pdf Some features are not implemented yet, including support for internal tree structure and soft source-syntactic constraints. |
||
|---|---|---|
| .. | ||
| analysis | ||
| ems | ||
| fuzzy-match | ||
| generic | ||
| OSM | ||
| other | ||
| recaser | ||
| regression-testing | ||
| server | ||
| share/nonbreaking_prefixes | ||
| tests | ||
| tokenizer | ||
| training | ||
| Transliteration | ||
| Jamfile | ||
| README | ||
2006-07-29 This directory should contain all multi-purpose scripts for: - training ... training moses (including BLEU evaluation needed for MERT) - analysis ... analyzing MT output (for human analysis) - generic ... script for handling generic issues (parallelization) - lib ... perl modules used by various scripts The Jamfile then takes care of proper 'release' from your git directory to the shared directories. The released scripts should remain in the *same directory structure*.