diff options
Diffstat (limited to 'scripts/ems/example/config.factored')
| -rw-r--r-- | scripts/ems/example/config.factored | 15 |
1 files changed, 11 insertions, 4 deletions
diff --git a/scripts/ems/example/config.factored b/scripts/ems/example/config.factored index 2faa5de4c..9aff587ff 100644 --- a/scripts/ems/example/config.factored +++ b/scripts/ems/example/config.factored @@ -137,7 +137,7 @@ raw-stem = $wmt12-data/training/undoc.2000.$pair-extension ### tool to be used for language model training # kenlm training lm-training = "$moses-script-dir/ems/support/lmplz-wrapper.perl -bin $moses-bin-dir/lmplz" -settings = "--prune '0 0 1' -T $working-dir/lm/tmp -S 50%" +settings = "--prune '0 0 1' -T $working-dir/lm -S 20%" # srilm #lm-training = $srilm-dir/ngram-count @@ -319,6 +319,7 @@ script = $moses-script-dir/training/train-model.perl # * "-mgiza -mgiza-cpus 8" to use mgiza instead of giza # * "-sort-buffer-size 8G -sort-compress gzip" to reduce on-disk sorting # * "-sort-parallel 8 -cores 8" to speed up phrase table building +# * "-parallel" for parallel execution of mkcls and giza # #training-options = "" @@ -408,11 +409,17 @@ alignment-symmetrization-method = grow-diag-final-and #operation-sequence-model = "yes" #operation-sequence-model-order = 5 #operation-sequence-model-settings = "-lmplz '$moses-src-dir/bin/lmplz -S 40% -T $working-dir/model/tmp'" +# +# if OSM training should be skipped, point to OSM Model +#osm-model = -### if OSM training should be skipped, -# point to OSM Model +### unsupervised transliteration module +# Durrani, Sajjad, Hoang and Koehn (EACL, 2014). +# "Integrating an Unsupervised Transliteration Model +# into Statistical Machine Translation." # -# osm-model = +#transliteration-module = "yes" +#post-decoding-transliteration = "yes" ### lexicalized reordering: specify orientation type # (default: only distance-based reordering model) |