word word 0.01023738
word alignment 0.00821145
word segmentation 0.00622633
chinese word 0.005966549000000001
same word 0.005893014
different word 0.005770071000000001
word pair 0.005700719
word align 0.005619672
word segmenter 0.005539329000000001
char word 0.005502561
corresponding word 0.0054662600000000006
wsr word 0.005465960000000001
stanford word 0.005456987
modeling word 0.005455078
motivated word 0.0054485290000000006
word seg 0.0054342340000000005
original word 0.005431129000000001
word lattice 0.005417243
wordsys word 0.0054167930000000005
nese word 0.005415419
tional word 0.005411777
word segmenters 0.005411671000000001
word packing 0.005411603
word segmen 0.005410422000000001
word aligners 0.005409413
conventional word 0.005408256
packed word 0.005404291
word 切尼愿 0.005404291
word 阿拉法特 0.005404291
ictclas word 0.005404291
ployed word 0.005404291
alignment model 0.00406891
alignment bilingual 0.003881586
character alignment 0.0038292079999999997
alignment character 0.0038292079999999997
alignment evaluation 0.0036539149999999998
alignment combination 0.003644818
alignment models 0.003637685
many alignment 0.003601861
alignment quality 0.003479706
alignment errors 0.0034249709999999997
alignment alterna 0.00337823
alignment 0.00309276
english words 0.00220004
bilingual corpus 0.002165016
training corpus 0.002074754
translation features 0.001982028
language model 0.00197786
english sentence 0.001975696
translation evaluation 0.0019638349999999997
translation results 0.0018898019999999999
parallel corpus 0.001883852
translation performance 0.0018657539999999999
translation rules 0.001823271
translation rule 0.00182048
machine translation 0.0017824129999999998
wrong translation 0.001743676
same sentence 0.00174103
corpus wsr 0.00172346
new words 0.001719005
wsa translation 0.0017134519999999999
fbis corpus 0.00169365
corpus wsa 0.001686962
same method 0.001678602
aligned corpus 0.00167504
corpus aligned 0.00167504
gigaword corpus 0.001667322
chinese character 0.001584307
smt system 0.001554064
sentence pair 0.0015487349999999999
sentence pairs 0.001545473
phrase length 0.001534854
ctb segmentation 0.001492253
segmented words 0.0014922029999999999
segmentation specifications 0.001426437
large phrase 0.001423644
translation 0.00140268
segmentation specifi 0.001394471
segmentation specification 0.001394471
corpus 0.00137619
chinese sentences 0.0013525529999999998
simple method 0.00131429
system wsa 0.001231525
chinese side 0.00120381
version method 0.001199421
conversion method 0.001195817
words 0.00119105
character segmenter 0.001157087
test set 0.001139648
chinese portions 0.001136771
evaluation set 0.0011331420000000002
different segmentations 0.001108473
segmentation 0.00110764
linguistic knowledge 0.0011073720000000001
modeling character 0.001072836
smt systems 0.00105275
different segmenta 0.001036981
other works 0.001025332
english 0.00100899
language 0.00100171
