.. |
bilingual-lm
|
nplm_train: more options
|
2015-03-20 14:12:41 +00:00 |
rdlm
|
RDLM training without editing bash scripts
|
2015-03-20 14:12:41 +00:00 |
wrappers
|
EMS: support for syntactic metrics for MERT/MIRA
|
2015-03-20 17:15:33 +00:00 |
absolutize_moses_model.pl
|
Send stderr to /dev/null when looking for pawd.
|
2012-09-28 14:37:53 -04:00 |
analyse_moses_model.pl
|
Update the training scripts to support the new format parameter for
|
2010-04-09 11:37:43 +00:00 |
binarize-model.perl
|
Enable skipping of filtering in EMS
|
2013-05-02 15:15:52 +01:00 |
build-generation-table.perl
|
add svn id comments to start of file
|
2007-03-14 22:22:36 +00:00 |
build-mmsapt.perl
|
bug fix mmsapt training
|
2014-09-21 06:02:35 +01:00 |
clean-corpus-n-ratio.perl
|
EMS convenience:
|
2015-03-04 14:43:05 +00:00 |
clean-corpus-n.perl
|
EMS convenience:
|
2015-03-04 14:43:05 +00:00 |
clone_moses_model.pl
|
handle binarized phrase table in clone_moses_model.pl
|
2012-10-09 16:05:12 +02:00 |
combine_factors.pl
|
cherry-picked commit 2d47a5637b from master
|
2012-04-12 12:29:12 +01:00 |
convert-moses-ini-to-v2.perl
|
update convert-moses-ini-to-v2.perl with memory pt for SCFFG decoding. Start on constrained ff
|
2013-09-16 07:46:45 +02:00 |
convert-moses-ini-v2-to-v1.perl
|
script to convert moses.ini v2 to v1 /Tom Hoar
|
2015-02-03 10:59:38 +00:00 |
corpus-sizes.perl
|
Implementation of corpus identifier feature
|
2011-10-14 12:44:37 +01:00 |
create_count_tables.py
|
documentation/permissions
|
2013-09-18 15:13:56 +02:00 |
exodus.perl
|
keep perl scripts with Unix line endings
|
2010-10-11 11:32:27 +00:00 |
filter-model-given-input.pl
|
filter-model-given-input.pl: drop "-encoding None" from phrase table binaization with processPhraseTableMin. Recommended by Marcin.
|
2015-03-23 14:38:24 +00:00 |
filter-rule-table.py
|
filter-rule-table.py: change default pruning count from 1 to 0
|
2013-03-04 21:02:50 +00:00 |
flexibility_score.py
|
swap position of alignment and scores in phrase table halves (before consolidate step).
|
2014-03-02 16:55:42 +00:00 |
get-lexical.perl
|
new training option -write-lexical-counts
|
2012-09-06 11:48:54 +02:00 |
giza2bal.pl
|
move giza2bal.pl back into script/training
|
2012-05-31 18:04:29 +01:00 |
Jamfile
|
fix start weights in experiment.perl, add hypothesis queue for picking hope and fear translations, add variations to 1slack formulation
|
2012-06-01 01:49:42 +01:00 |
LexicalTranslationModel.pm
|
instance weighting of lex weights
|
2013-01-08 15:34:29 +00:00 |
mert-moses.pl
|
fix option --return-best-dev with hypergraph MIRA (which I broke in commit d39cbca0b9 )
|
2015-02-27 14:47:37 +00:00 |
postprocess-lopar.perl
|
add svn id comments to start of file
|
2007-03-14 22:22:36 +00:00 |
reduce_combine.pl
|
mert-moses.pl now supports multiple input weights for lattices and confusion networks, using the --inputweights argument.
|
2009-02-05 17:39:36 +00:00 |
reduce-factors.perl
|
reduce-factors: port xml support from train-model.perl
|
2015-03-20 14:44:48 +00:00 |
reduce-topt-count.pl
|
fixed off-by-one bug
|
2012-07-06 14:18:39 -04:00 |
remove-orphan-phrase-pairs-from-reordering-table.perl
|
added scripts for threshold filtering phrase table
|
2013-12-10 19:19:12 +00:00 |
threshold-filter.perl
|
same spec for dedicated script as for train-model.perl and filter-model-given-input.pl
|
2014-12-21 01:37:05 +00:00 |
train-global-lexicon-model.perl
|
Separated train-global-lexicon-model into three steps.
|
2012-02-01 14:16:09 +01:00 |
train-model.perl
|
Always use "SyntaxInputWeight0" as name of SyntaxInputWeight feature
|
2015-03-18 09:56:46 +00:00 |