diff options
Diffstat (limited to 'scripts/ems/example/config.basic')
| -rw-r--r-- | scripts/ems/example/config.basic | 35 |
1 files changed, 35 insertions, 0 deletions
diff --git a/scripts/ems/example/config.basic b/scripts/ems/example/config.basic index 1fce185df..4af8664aa 100644 --- a/scripts/ems/example/config.basic +++ b/scripts/ems/example/config.basic @@ -252,6 +252,35 @@ type = 8 #lm-randomizer = "$randlm-dir/buildlm -falsepos 8 -values 8" ################################################################# +# MODIFIED MOORE LEWIS FILTERING + +[MML] IGNORE + +### specifications for language models to be trained +# +#lm-training = $srilm-dir/ngram-count +#lm-settings = "-interpolate -kndiscount -unk" +#lm-binarizer = $moses-src-dir/bin/build_binary +#lm-query = $moses-src-dir/bin/query +#order = 5 + +### in-/out-of-domain source/target corpora to train the 4 language model +# +# in-domain: point either to a parallel corpus +#outdomain-stem = [CORPUS:toy:clean-split-stem] + +# ... or to two separate monolingual corpora +#indomain-target = [LM:toy:lowercased-corpus] +#raw-indomain-source = $toy-data/nc-5k.$input-extension + +# point to out-of-domain parallel corpus +#outdomain-stem = [CORPUS:giga:clean-split-stem] + +# settings: number of lines sampled from the corpora to train each language model on +# (typically a million or so) +#settings = "--line-count 1000000" + +################################################################# # TRANSLATION MODEL TRAINING [TRAINING] @@ -316,6 +345,12 @@ alignment-symmetrization-method = grow-diag-final-and # #word-alignment = $working-dir/model/aligned.1 +### filtering some corpora with modified Moore-Lewis +# specify corpora to be filtered and ratio to be kept, either before or after word alignment +#mml-filter-corpora = toy +#mml-before-wa = "-proportion 0.9" +#mml-after-wa = "-proportion 0.9" + ### create a bilingual concordancer for the model # #biconcor = $moses-script-dir/ems/biconcor/biconcor |