From 10a232656a0c882b3b955d2bcfac138ce11e8a2e Mon Sep 17 00:00:00 2001
From: Patrick Simianer <p@simianer.de>
Date: Tue, 13 Mar 2012 09:15:46 +0100
Subject: polish

---
 dtrain/test/example/cdec.ini   |  8 +++++---
 dtrain/test/example/dtrain.ini | 28 ++++++++++++++--------------
 2 files changed, 19 insertions(+), 17 deletions(-)

(limited to 'dtrain/test/example')

diff --git a/dtrain/test/example/cdec.ini b/dtrain/test/example/cdec.ini
index ad958ca6..fe5ca759 100644
--- a/dtrain/test/example/cdec.ini
+++ b/dtrain/test/example/cdec.ini
@@ -5,6 +5,7 @@ intersection_strategy=cube_pruning
 cubepruning_pop_limit=30
 feature_function=WordPenalty
 feature_function=KLanguageModel test/example/nc-wmt11.en.srilm.gz
+# all currently working feature function for translation:
 #feature_function=ArityPenalty
 #feature_function=CMR2008ReorderingFeatures
 #feature_function=Dwarf
@@ -14,9 +15,10 @@ feature_function=KLanguageModel test/example/nc-wmt11.en.srilm.gz
 #feature_function=NgramFeatures
 #feature_function=NonLatinCount
 #feature_function=OutputIndicator
-#feature_function=RuleIdentityFeatures
-#feature_function=RuleNgramFeatures
-#feature_function=RuleShape
+feature_function=RuleIdentityFeatures
+feature_function=RuleNgramFeatures
+feature_function=RuleShape
 #feature_function=SourceSpanSizeFeatures
 #feature_function=SourceWordPenalty
 #feature_function=SpanFeatures
+# ^^^ features active that were used in the ACL paper
diff --git a/dtrain/test/example/dtrain.ini b/dtrain/test/example/dtrain.ini
index ed1b7e5f..68173e11 100644
--- a/dtrain/test/example/dtrain.ini
+++ b/dtrain/test/example/dtrain.ini
@@ -1,20 +1,20 @@
 input=test/example/nc-wmt11.1k.gz    # use '-' for stdin
-output=w.gz                             # a weights file
-decoder_config=test/example/cdec.ini # a ini for cdec
+output=-                             # a weights file or stdout
+decoder_config=test/example/cdec.ini # ini for cdec
 # these will be printed on each iteration
 print_weights=Glue WordPenalty LanguageModel LanguageModel_OOV PhraseModel_0 PhraseModel_1 PhraseModel_2 PhraseModel_3 PhraseModel_4 PhraseModel_5 PhraseModel_6 PassThrough
 tmp=/tmp
-stop_after=20
+stop_after=10 # stop iteration after 10 inputs 
 
 # interesting stuff
-epochs=1
-k=100
-N=4
-learning_rate=0.0001
-gamma=0.00001
-scorer=stupid_bleu
-sample_from=kbest
-filter=uniq
-pair_sampling=108010
-pair_threshold=0.01
-select_weights=last
+epochs=3                # run over input 3 times
+k=200                   # use 100best lists
+N=4                     # optimize (approx) BLEU4
+learning_rate=0.0001    # learning rate
+gamma=0.00001           # use SVM reg
+scorer=stupid_bleu      # use stupid BLEU+1 approx.
+sample_from=kbest       # use kbest lists (as opposed to forest)
+filter=uniq             # only uniq entries in kbest
+pair_sampling=108010    # 10 vs 80 vs 10 and 80 vs 10
+pair_threshold=0        # minimum distance in BLEU
+select_weights=last     # just output last weights
-- 
cgit v1.2.3