summaryrefslogtreecommitdiff
path: root/training/dtrain/test/example/dtrain.ini
diff options
context:
space:
mode:
authorMichael Denkowski <michael.j.denkowski@gmail.com>2012-12-22 16:01:23 -0500
committerMichael Denkowski <michael.j.denkowski@gmail.com>2012-12-22 16:01:23 -0500
commit597d89c11db53e91bc011eab70fd613bbe6453e8 (patch)
tree83c87c07d1ff6d3ee4e3b1626f7eddd49c61095b /training/dtrain/test/example/dtrain.ini
parent65e958ff2678a41c22be7171456a63f002ef370b (diff)
parent201af2acd394415a05072fbd53d42584875aa4b4 (diff)
Merge branch 'master' of git://github.com/redpony/cdec
Diffstat (limited to 'training/dtrain/test/example/dtrain.ini')
-rw-r--r--training/dtrain/test/example/dtrain.ini22
1 files changed, 22 insertions, 0 deletions
diff --git a/training/dtrain/test/example/dtrain.ini b/training/dtrain/test/example/dtrain.ini
new file mode 100644
index 00000000..72d50ca1
--- /dev/null
+++ b/training/dtrain/test/example/dtrain.ini
@@ -0,0 +1,22 @@
+input=test/example/nc-wmt11.1k.gz # use '-' for STDIN
+output=- # a weights file (add .gz for gzip compression) or STDOUT '-'
+select_weights=VOID # don't output weights
+decoder_config=test/example/cdec.ini # config for cdec
+# weights for these features 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=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 (this will still only use pairs with diff > 0)
+loss_margin=0