diff options
Diffstat (limited to 'training/dtrain/examples/standard')
-rw-r--r-- | training/dtrain/examples/standard/README | 2 | ||||
-rw-r--r-- | training/dtrain/examples/standard/cdec.ini | 27 | ||||
-rw-r--r-- | training/dtrain/examples/standard/dtrain.ini | 27 | ||||
-rw-r--r-- | training/dtrain/examples/standard/expected-output | 123 | ||||
-rw-r--r-- | training/dtrain/examples/standard/nc-wmt11.de.gz | bin | 58324 -> 0 bytes | |||
-rw-r--r-- | training/dtrain/examples/standard/nc-wmt11.en.gz | bin | 49600 -> 0 bytes | |||
-rw-r--r-- | training/dtrain/examples/standard/nc-wmt11.en.srilm.gz | bin | 16017291 -> 0 bytes | |||
-rw-r--r-- | training/dtrain/examples/standard/nc-wmt11.grammar.gz | bin | 1399924 -> 0 bytes | |||
-rw-r--r-- | training/dtrain/examples/standard/nc-wmt11.gz | bin | 113504 -> 0 bytes |
9 files changed, 0 insertions, 179 deletions
diff --git a/training/dtrain/examples/standard/README b/training/dtrain/examples/standard/README deleted file mode 100644 index ce37d31a..00000000 --- a/training/dtrain/examples/standard/README +++ /dev/null @@ -1,2 +0,0 @@ -Call `dtrain` from this folder with ../../dtrain -c dtrain.ini . - diff --git a/training/dtrain/examples/standard/cdec.ini b/training/dtrain/examples/standard/cdec.ini deleted file mode 100644 index 3330dd71..00000000 --- a/training/dtrain/examples/standard/cdec.ini +++ /dev/null @@ -1,27 +0,0 @@ -formalism=scfg -add_pass_through_rules=true -scfg_max_span_limit=15 -intersection_strategy=cube_pruning -cubepruning_pop_limit=200 -grammar=nc-wmt11.grammar.gz -feature_function=WordPenalty -feature_function=KLanguageModel ./nc-wmt11.en.srilm.gz -# all currently working feature functions for translation: -# (with those features active that were used in the ACL paper) -#feature_function=ArityPenalty -#feature_function=CMR2008ReorderingFeatures -#feature_function=Dwarf -#feature_function=InputIndicator -#feature_function=LexNullJump -#feature_function=NewJump -#feature_function=NgramFeatures -#feature_function=NonLatinCount -#feature_function=OutputIndicator -feature_function=RuleIdentityFeatures -feature_function=RuleSourceBigramFeatures -feature_function=RuleTargetBigramFeatures -feature_function=RuleShape -feature_function=LexicalFeatures 1 1 1 -#feature_function=SourceSpanSizeFeatures -#feature_function=SourceWordPenalty -#feature_function=SpanFeatures diff --git a/training/dtrain/examples/standard/dtrain.ini b/training/dtrain/examples/standard/dtrain.ini deleted file mode 100644 index a515db02..00000000 --- a/training/dtrain/examples/standard/dtrain.ini +++ /dev/null @@ -1,27 +0,0 @@ -#input=./nc-wmt11.de.gz -#refs=./nc-wmt11.en.gz -bitext=./nc-wmt11.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=Glue WordPenalty LanguageModel LanguageModel_OOV PhraseModel_0 PhraseModel_1 PhraseModel_2 PhraseModel_3 PhraseModel_4 PhraseModel_5 PhraseModel_6 PassThrough -# newer version of the grammar extractor use different feature names: -#print_weights= EgivenFCoherent SampleCountF CountEF MaxLexFgivenE MaxLexEgivenF IsSingletonF IsSingletonFE Glue WordPenalty PassThrough LanguageModel LanguageModel_OOV -stop_after=10 # stop epoch after 10 inputs - -# interesting stuff -epochs=3 # run over input 3 times -k=100 # use 100best lists -N=4 # optimize (approx) BLEU4 -scorer=fixed_stupid_bleu # use 'stupid' BLEU+1 -learning_rate=0.1 # learning rate, don't care if gamma=0 (perceptron) and loss_margin=0 (not margin 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 # update if correctly ranked, but within this margin -repeat=1 # repeat training on a kbest list 1 times -#batch=true # batch tuning, update after accumulating over all sentences and all kbest lists diff --git a/training/dtrain/examples/standard/expected-output b/training/dtrain/examples/standard/expected-output deleted file mode 100644 index 2460cfbb..00000000 --- a/training/dtrain/examples/standard/expected-output +++ /dev/null @@ -1,123 +0,0 @@ - cdec cfg './cdec.ini' -Loading the LM will be faster if you build a binary file. -Reading ./nc-wmt11.en.srilm.gz -----5---10---15---20---25---30---35---40---45---50---55---60---65---70---75---80---85---90---95--100 -**************************************************************************************************** - Example feature: Shape_S00000_T00000 -T=1 I=1 D=1 -Seeding random number sequence to 2327685089 - -dtrain -Parameters: - k 100 - N 4 - T 3 - batch 0 - scorer 'fixed_stupid_bleu' - sample from 'kbest' - filter 'uniq' - learning rate 0.1 - gamma 0 - loss margin 0 - faster perceptron 1 - pairs 'XYX' - hi lo 0.1 - pair threshold 0 - select weights 'avg' - l1 reg 0 'none' - pclr no - max pairs 4294967295 - repeat 1 - cdec cfg './cdec.ini' - input './nc-wmt11.gz' - output '-' - stop_after 10 -(a dot represents 10 inputs) -Iteration #1 of 3. - . 10 -Stopping after 10 input sentences. -WEIGHTS - Glue = +6.9 - WordPenalty = -46.426 - LanguageModel = +535.12 - LanguageModel_OOV = -123.5 - PhraseModel_0 = -160.73 - PhraseModel_1 = -350.13 - PhraseModel_2 = -187.81 - PhraseModel_3 = +172.04 - PhraseModel_4 = +0.90108 - PhraseModel_5 = +21.6 - PhraseModel_6 = +67.2 - PassThrough = -149.7 - --- - 1best avg score: 0.23327 (+0.23327) - 1best avg model score: -9084.9 (-9084.9) - avg # pairs: 780.7 - avg # rank err: 0 (meaningless) - avg # margin viol: 0 - k-best loss imp: 100% - non0 feature count: 1389 - avg list sz: 91.3 - avg f count: 146.2 -(time 0.37 min, 2.2 s/S) - -Iteration #2 of 3. - . 10 -WEIGHTS - Glue = -43 - WordPenalty = -22.019 - LanguageModel = +591.53 - LanguageModel_OOV = -252.1 - PhraseModel_0 = -120.21 - PhraseModel_1 = -43.589 - PhraseModel_2 = +73.53 - PhraseModel_3 = +113.7 - PhraseModel_4 = -223.81 - PhraseModel_5 = +64 - PhraseModel_6 = +54.8 - PassThrough = -331.1 - --- - 1best avg score: 0.29568 (+0.062413) - 1best avg model score: -15879 (-6794.1) - avg # pairs: 566.1 - avg # rank err: 0 (meaningless) - avg # margin viol: 0 - k-best loss imp: 100% - non0 feature count: 1931 - avg list sz: 91.3 - avg f count: 139.89 -(time 0.33 min, 2 s/S) - -Iteration #3 of 3. - . 10 -WEIGHTS - Glue = -44.3 - WordPenalty = -131.85 - LanguageModel = +230.91 - LanguageModel_OOV = -285.4 - PhraseModel_0 = -194.27 - PhraseModel_1 = -294.83 - PhraseModel_2 = -92.043 - PhraseModel_3 = -140.24 - PhraseModel_4 = +85.613 - PhraseModel_5 = +238.1 - PhraseModel_6 = +158.7 - PassThrough = -359.6 - --- - 1best avg score: 0.37375 (+0.078067) - 1best avg model score: -14519 (+1359.7) - avg # pairs: 545.4 - avg # rank err: 0 (meaningless) - avg # margin viol: 0 - k-best loss imp: 100% - non0 feature count: 2218 - avg list sz: 91.3 - avg f count: 137.77 -(time 0.35 min, 2.1 s/S) - -Writing weights file to '-' ... -done - ---- -Best iteration: 3 [SCORE 'fixed_stupid_bleu'=0.37375]. -This took 1.05 min. diff --git a/training/dtrain/examples/standard/nc-wmt11.de.gz b/training/dtrain/examples/standard/nc-wmt11.de.gz Binary files differdeleted file mode 100644 index 0741fd92..00000000 --- a/training/dtrain/examples/standard/nc-wmt11.de.gz +++ /dev/null diff --git a/training/dtrain/examples/standard/nc-wmt11.en.gz b/training/dtrain/examples/standard/nc-wmt11.en.gz Binary files differdeleted file mode 100644 index 1c0bd401..00000000 --- a/training/dtrain/examples/standard/nc-wmt11.en.gz +++ /dev/null diff --git a/training/dtrain/examples/standard/nc-wmt11.en.srilm.gz b/training/dtrain/examples/standard/nc-wmt11.en.srilm.gz Binary files differdeleted file mode 100644 index 7ce81057..00000000 --- a/training/dtrain/examples/standard/nc-wmt11.en.srilm.gz +++ /dev/null diff --git a/training/dtrain/examples/standard/nc-wmt11.grammar.gz b/training/dtrain/examples/standard/nc-wmt11.grammar.gz Binary files differdeleted file mode 100644 index ce4024a1..00000000 --- a/training/dtrain/examples/standard/nc-wmt11.grammar.gz +++ /dev/null diff --git a/training/dtrain/examples/standard/nc-wmt11.gz b/training/dtrain/examples/standard/nc-wmt11.gz Binary files differdeleted file mode 100644 index c39c5aef..00000000 --- a/training/dtrain/examples/standard/nc-wmt11.gz +++ /dev/null |