word segmentation 0.00431343
segmentation model 0.0040579399999999995
bilingual word 0.003637538
word alignments 0.003615803
translation model 0.0035722439999999996
word boundary 0.0035585
language word 0.0035365329999999997
chinese word 0.003528508
english word 0.003519516
target word 0.0034781869999999998
model learning 0.0033951439999999997
statistical word 0.003306485
input word 0.003287034
language model 0.003281043
other model 0.0032771939999999998
similar word 0.003263437
word dictionary 0.003261121
supervised word 0.003233251
model training 0.003214349
binary word 0.003202273
candidate word 0.0031930789999999997
word xfi 0.0031883519999999998
explicit word 0.003182627
level word 0.003176935
foreign word 0.00317534
word boundaries 0.003167901
olympus word 0.0031660069999999998
nese word 0.003162353
extracts word 0.003157247
word occurrence 0.003147889
proximated word 0.003145252
word granularity 0.003145252
word aligner 0.003145252
model parameters 0.003113986
tion model 0.0030742079999999997
cws model 0.0030342399999999997
crfs model 0.003003511
structural model 0.002984339
supervised model 0.0029777609999999998
smt model 0.0029632879999999997
labeling model 0.0029486029999999997
model induction 0.0029208339999999998
our model 0.002912485
guage model 0.0028995509999999998
model expectations 0.0028958599999999997
scalable model 0.00289181
model sim 0.002889886
model 0.00266683
segmentation models 0.002203525
bilingual segmentation 0.002106328
segmentation features 0.002098365
segmentation standard 0.0018904910000000002
alignment target 0.001829217
bilingual data 0.0017860279999999998
entropy segmentation 0.001736743
segmentation knowledge 0.001719447
linguistic segmentation 0.001716588
segmentation mod 0.001708688
supervised segmentation 0.001702041
treebank segmentation 0.001674378
various segmentation 0.001671231
english data 0.001668006
segmentation effects 0.001665583
segmentation fea 0.001663214
positive segmentation 0.001657042
segmentation ambiguities 0.0016537190000000001
ter segmentation 0.0016508340000000001
matching segmentation 0.001647486
segmentation patterns 0.001634063
segmentation properties 0.001631129
crucial segmentation 0.001630595
guistic segmentation 0.001629379
other words 0.001628304
segmentation supervisions 0.0016249460000000002
chinese words 0.0016241279999999999
training data 0.001618329
segmentation consistency 0.0016177960000000001
predefined segmentation 0.001616919
segmentation consis 0.001615876
english words 0.001615136
segmentation supervi 0.001614247
partial segmentation 0.001614247
preferable segmentation 0.001614247
segmentation consen 0.001614247
segmentation consistence 0.001614247
target words 0.001573807
test data 0.001543277
alignment pairs 0.00152652
alignment pattern 0.001517914
alignment targets 0.0014966089999999999
alignment pat 0.0014966089999999999
input data 0.0014355239999999999
segmented data 0.001418425
parallel data 0.0014025539999999999
segmentation 0.00139111
supervised data 0.001381741
unlabeled data 0.001368321
labeled data 0.0013683179999999999
testing data 0.0013651499999999999
treebank data 0.0013540779999999999
