chinese word 0.001893744
chinese language 0.001763146
language data 0.001754084
word segmentation 0.001629991
word boundary 0.001626639
chinese words 0.001620116
word precision 0.001533762
correct word 0.001494315
other languages 0.001452262
important language 0.001437218
word boundaries 0.00142911
word seg 0.001412944
word border 0.001404302
word borders 0.001395762
word extraction 0.00137315
word preci 0.00137315
tect word 0.00137315
target language 0.001373105
language con 0.0013651359999999999
chinese number 0.001363511
chinese text 0.0013364359999999999
chinese segmentation 0.0013189550000000001
other experiments 0.001309166
chinese characters 0.00125456
other factors 0.001251723
language engineering 0.001242812
man language 0.001242812
test data 0.001242022
other hand 0.0012228579999999998
correct words 0.001220687
general data 0.001218074
training data 0.001214782
same context 0.001207088
chinese cor 0.0012003959999999998
model 0.00119427
learning data 0.001189813
character words 0.0011877670000000002
other chances 0.001179687
same example 0.001172026
same task 0.001149539
ideogram words 0.001144549
whole data 0.001120096
test corpus 0.001118847
chinese linguistics 0.001113865
inside words 0.001111178
segmented data 0.001108642
segments words 0.001100735
second boundary 0.001099983
guage data 0.001096515
performance results 0.0010946950000000001
training corpus 0.001091607
data size 0.001086019
context boundary 0.001076258
newspaper data 0.001074802
text segmentation 0.001072683
such cases 0.0010696619999999999
chinese literature 0.001068203
input text 0.001067847
maximum value 0.001067082
learning corpus 0.001066638
contemporary chinese 0.001065904
chinese maga 0.001062781
chinese linguis 0.001062781
data amounts 0.0010557779999999998
input phrase 0.001053529
corpus con 0.001052461
length sequence 0.001041607
possible transition 0.001041024
number characters 0.001035363
similar method 0.001034558
segmentation method 0.001031692
input length 0.001029315
entropy value 0.001028295
set length 0.001015618
such observation 0.001012338
semantic units 0.001007267
high value 0.001003159
small example 9.92932E-4
ing point 9.895939999999999E-4
semantic unit 9.84993E-4
daily corpus 9.75078E-4
language 9.71792E-4
possible substrings 9.68873E-4
correct number 9.64082E-4
corpus size 9.62844E-4
evaluation function 9.60902E-4
ing locations 9.60899E-4
boundary precision 9.55621E-4
segmentation methods 9.50682E-4
maximum length 9.43824E-4
second graph 9.389609999999999E-4
total number 9.354389999999999E-4
precision figure 9.257289999999999E-4
second line 9.24212E-4
many works 9.21999E-4
correct segmentation 9.19526E-4
segmentation problem 9.07843E-4
proximity value 9.051860000000001E-4
logical contraposition 8.952760000000001E-4
ing inequality 8.9191E-4
