Age | Commit message (Collapse) | Author |
|
|
|
|
|
|
|
|
|
need some further tweaking
|
|
|
|
|
|
|
|
evaluation step
|
|
|
|
can contains dense and sparse
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Conflicts:
scripts/training/filter-model-given-input.pl
|
|
Use 'binarize-all = path-to-binarize-model.perl
|
|
|
|
|
|
|
|
|
|
feature; threshold pruning in filter
|
|
|
|
|
|
|
|
|
|
- creates a virtual phrase table at decoding time based on a vector of component models and a combination algorithm
- linear interpolation or instance weighting
- two possible component model types supported so far: 0 (in-memory) or 12 (compact)
- weights can be set in config, and overriden on a sentence-level through mosesserver API
- online optimization (perplexity minimization) using dlib and xmlrpc-c call
|
|
|
|
|
|
get rid of ShortNames and move to refactored moses pdq
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
Change the default pruning threshold from 1 to 0 to allow for
Hiero-style fractional counts.
|
|
|
|
|
|
zcat is identical to "gunzip -c", but Mac OS X doesn't ship with zcat.
|
|
|
|
|
|
|