segmentation model 0.0049708
language model 0.0046737720000000005
bigram model 0.004462173
joint model 0.004392162
bayesian model 0.0043808020000000005
unigram model 0.004367523
statistical model 0.0043325790000000005
model simple 0.004326962
markov model 0.004311358
model inference 0.004307123
unsupervised model 0.0042835
process model 0.004273405
hmm model 0.00425691
model segments 0.004255161
gram model 0.0042481590000000005
initialization model 0.004219142
ter model 0.004214906
model take 0.00421189
nvbe model 0.00420872
based model 0.004208081
hdp model 0.004204931
model goldwater 0.004202938
former model 0.004195827
model signif 0.0041905020000000005
iterative model 0.0041905020000000005
model 0.00396055
word segmentation 0.0030567700000000003
different word 0.0028906970000000002
chinese word 0.002689944
first word 0.002560483
word bigram 0.002548143
same word 0.002547001
word boundary 0.002533033
several word 0.002471228
word length 0.002467535
single word 0.002389282
unsupervised word 0.0023694700000000003
word level 0.002366426
potential word 0.002347083
word list 0.002326546
explicit word 0.002317476
word sequences 0.002315835
word boundaries 0.00231328
supervised word 0.002305737
word seg 0.002301403
ith word 0.002298768
word segmen 0.002295574
word segmenta 0.002292236
word precision 0.002291579
pervised word 0.002283986
word candidates 0.002279364
different segmentation 0.001854427
segmentation results 0.001577401
words sequence 0.00154487
different distribution 0.0014750940000000001
segmentation result 0.0014385230000000001
segmentation problem 0.0014346510000000001
test data 0.001379736
segmentation systems 0.001377769
random segmentation 0.0013584550000000002
chinese language 0.001356646
segmentation methods 0.001347279
english words 0.001321643
training data 0.001317293
bayesian method 0.0013152939999999998
current segmentation 0.001314483
segmentation errors 0.0013098040000000001
probability distribution 0.001297303
segmentation ambiguity 0.001295685
final segmentation 0.0012886660000000002
segmentation ambiguities 0.0012819790000000001
training corpus 0.001273765
character sequence 0.001270943
segmentation literature 0.001262831
segmentation standards 0.0012400990000000001
character information 0.001225265
segmented words 0.001220954
bigram language 0.001214845
words sequences 0.00121374
different systems 0.001211696
other models 0.0011942699999999999
testing data 0.001163348
empirical method 0.001161048
different types 0.001160119
different distributions 0.001136907
bayesian language 0.001133474
pervised method 0.001132508
dominant method 0.001126728
bootstrapping method 0.001126728
annotated data 0.001126365
different type 0.001123058
different disambiguation 0.001118773
different settings 0.001113395
test results 0.0011123090000000001
gold corpus 0.001109558
msra corpus 0.001089199
labeled data 0.001079824
different levels 0.0010790420000000001
character unigram 0.001077471
different perspectives 0.001076091
