word alignment 0.00599666
word alignments 0.005236348
word sequence 0.0051680070000000005
word segmentation 0.00503092
word pairs 0.004924022
chinese word 0.00489806
standard word 0.004879584
word units 0.004818269
word unpacking 0.0047760960000000005
word align 0.004770074
clear word 0.00475839
word aligner 0.00473447
unary word 0.004723562
word boundaries 0.004719017
word bounda 0.004715119
existent word 0.004715119
translation model 0.00355602
language model 0.0031059
reordering model 0.002772844
model order 0.00263886
segmentation model 0.00262236
phrase translation 0.00259197
language translation 0.00257558
english translation 0.002444062
ibm model 0.002415308
model weights 0.0023612249999999998
translation probability 0.002340815
guage model 0.002319303
source sentence 0.00226437
translation task 0.002146958
source language 0.00209851
model 0.00204317
translation chinese 0.00195918
alignment methods 0.00194976
target sentence 0.001923045
alignment entries 0.001918574
news translation 0.0019166880000000002
alignment cases 0.001896971
translation domain 0.0018788910000000002
machine translation 0.001878682
alignment techniques 0.001871734
multiple translation 0.001840578
null alignment 0.001840006
monolingual sentence 0.001802213
travel translation 0.0017906060000000001
target language 0.001757185
sentence pair 0.0017525230000000002
sentence pairs 0.0017008820000000001
large corpus 0.001686267
sentence length 0.0016801070000000001
chinese sentence 0.00167492
order language 0.0016584199999999999
small corpus 0.001626347
many language 0.0016178009999999999
parallel corpus 0.001571933
corpus table 0.0015665079999999999
phrase pairs 0.001551412
alignment 0.00154493
language side 0.001543049
language pairs 0.001535022
phrase length 0.001530637
reference sentence 0.001518608
source side 0.001516099
translation 0.00151285
whole sentence 0.001505845
average sentence 0.0014933630000000002
corpus frequencies 0.001481134
max phrase 0.001451959
corpus scale 0.001438948
bilingual sequence 0.001438441
original words 0.0014360829999999999
language modeling 0.001427268
english side 0.001411531
phrasal alignments 0.00140552
real words 0.0013997039999999999
phrase extraction 0.001392907
such alignments 0.001388626
consecutive words 0.00138148
unary words 0.001359732
language sides 0.0013281410000000001
sri language 0.001326691
bilingual segmentation 0.001301354
english machine 0.001297044
search target 0.001295205
monolingual sequence 0.0012899
sequence pair 0.0012402099999999998
search algorithm 0.0012339920000000002
sentence 0.00122859
corpus 0.00117497
target side 0.001174774
same length 0.0011670410000000002
monolingual way 0.001165543
large bleu 0.0011150679999999999
smt models 0.001110635
lexical reordering 0.001106709
sequence sig 0.00108945
test set 0.001089027
bilingual units 0.001088703
words 0.0010879
data set 0.001087569
