word segmentation 0.005922709999999999
chinese word 0.00573039
unknown word 0.005585468
head word 0.005547747
word structure 0.005521965
word structures 0.005494745
word tree 0.0054518299999999995
example word 0.005437574
word suffix 0.005427187
flat word 0.0053789269999999995
joint word 0.005362585
only word 0.005360551
word boundaries 0.0053420559999999995
prefix word 0.0053352
unified word 0.005333164
nese word 0.005329426
word seg 0.005329139
word segmen 0.005325593
rates word 0.005319104
complex word 0.005312473999999999
root word 0.005312077
word generation 0.005311815
structured word 0.005310098
word struc 0.005309034
ordinary word 0.005308165
word 憞䠮䞎 0.005307286
cover word 0.005306557
word segmenta 0.005305931
traditional word 0.005305392999999999
rable word 0.005304524
other words 0.002569822
such words 0.002568506
chinese words 0.00256553
many words 0.002471894
unknown words 0.002420608
structures words 0.002329885
vocabulary words 0.002303414
compound words 0.00221427
flat words 0.002214067
few words 0.002170606
structured words 0.002145238
separable words 0.002140156
unseen words 0.002140156
semantic model 0.0019470210000000002
words 0.00192356
parsing model 0.0017613
statistical model 0.0016985350000000001
ing model 0.001556385
single model 0.0015409220000000001
generative model 0.001529586
training data 0.001524232
markov model 0.001519691
ity model 0.0014956120000000001
such data 0.001466873
ability model 0.0014609640000000001
same corpus 0.001374653
parsing models 0.001265537
model 0.00124477
morphological segmentation 0.001220799
segmentation accuracy 0.001207956
segmentation system 0.001206408
same character 0.001191069
chinese sentence 0.0011788089999999998
chinese parsing 0.0011584999999999998
different applications 0.001153369
university corpus 0.001142824
ferent segmentation 0.001102238
segmentation standards 0.001098133
segmentation paradigm 0.001093058
different levels 0.001086418
annotated corpus 0.00107974
ear segmentation 0.001062403
former segmentation 0.001059337
different requirements 0.001058945
character sequence 0.001057582
natural language 0.001055571
language processing 0.001053019
machine translation 0.001041716
data sparsity 0.001039116
generative models 0.0010338230000000001
different story 0.001031299
language usages 0.001022664
other tree 0.001009672
speech information 0.0010072430000000001
chinese tree 0.00100538
other probabilities 9.97214E-4
chinese parser 9.93966E-4
driven models 9.8141E-4
syntactic parsing 9.75236E-4
chinese treebank 9.735969999999999E-4
jjf nnf 9.72999E-4
statistical parsing 9.702949999999999E-4
label nnf 9.689289999999999E-4
pipelined models 9.65675E-4
chinese characters 9.59178E-4
structure parsing 9.50075E-4
parsing algorithm 9.46155E-4
important information 9.373910000000001E-4
other systems 9.33268E-4
戽䊂䠽 nnf 8.987099999999999E-4
