blob: 68173e11e60bda164f8019051583fbace2e21d18 (
plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
|
input=test/example/nc-wmt11.1k.gz # use '-' for stdin
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=10 # stop iteration after 10 inputs
# interesting stuff
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
|
