overhauled ruby scripts and examples

1 files changed, 24 insertions, 0 deletions

diff --git a/training/dtrain/examples/standard/dtrain.ini b/training/dtrain/examples/standard/dtrain.ini
new file mode 100644
index 00000000..a05e9c29
--- /dev/null
+++ b/training/dtrain/examples/standard/dtrain.ini
@@ -0,0 +1,24 @@
+input=./nc-wmt11.de.gz
+refs=./nc-wmt11.en.gz
+output=-                  # a weights file (add .gz for gzip compression) or STDOUT '-'
+select_weights=avg        # output average (over epochs) weight vector
+decoder_config=./cdec.ini # config for cdec
+# weights for these features will be printed on each iteration
+print_weights= EgivenFCoherent SampleCountF CountEF MaxLexFgivenE MaxLexEgivenF IsSingletonF IsSingletonFE Glue WordPenalty PassThrough LanguageModel LanguageModel_OOV
+# newer version of the grammar extractor use different feature names: 
+#print_weights=Glue WordPenalty LanguageModel LanguageModel_OOV PhraseModel_0 PhraseModel_1 PhraseModel_2 PhraseModel_3 PhraseModel_4 PhraseModel_5 PhraseModel_6 PassThrough
+stop_after=10 # stop epoch after 10 inputs
+
+# interesting stuff
+epochs=2                # run over input 2 times
+k=100                   # use 100best lists
+N=4                     # optimize (approx) BLEU4
+scorer=stupid_bleu      # use 'stupid' BLEU+1
+learning_rate=1.0       # learning rate, don't care if gamma=0 (perceptron)
+gamma=0                 # use SVM reg
+sample_from=kbest       # use kbest lists (as opposed to forest)
+filter=uniq             # only unique entries in kbest (surface form)
+pair_sampling=XYX       #
+hi_lo=0.1               # 10 vs 80 vs 10 and 80 vs 10 here
+pair_threshold=0        # minimum distance in BLEU (here: > 0)
+loss_margin=0