language model 0.003452511
segmentation model 0.003289249
syntactic model 0.0030793070000000003
joint model 0.0030604380000000004
computational model 0.002990705
word segmentation 0.002973699
bigram model 0.0029665110000000002
unigram model 0.0029604960000000004
variation model 0.0029333500000000004
gram model 0.0028829850000000002
generative model 0.002881825
possible word 0.0028761079999999996
same word 0.00285424
tation model 0.002836438
graphical model 0.0028349100000000004
gle model 0.002832162
model han 0.002832162
joint word 0.002744888
bayesian word 0.0026986239999999997
word tokens 0.0026959469999999998
word form 0.0026828159999999998
example word 0.002679651
word type 0.002653346
word bigram 0.002650961
bigram word 0.002650961
word boundary 0.002625582
model 0.0026025
word boundaries 0.00260124
gold word 0.00259438
word right 0.002576575
word types 0.002572305
word constraint 0.002554517
true word 0.0025544929999999997
jth word 0.00254361
known word 0.002538884
word segmenta 0.002527807
pervised word 0.0025269
word segmen 0.002519479
word predictability 0.0025164529999999997
word segmention 0.0025164529999999997
possible words 0.001854888
individual words 0.0015659150000000002
sible words 0.0015368690000000002
dividual words 0.001496278
segmentation models 0.001389724
large corpus 0.001378142
such models 0.0013605470000000001
english data 0.001313144
actual corpus 0.0012824
bigram probability 0.00126648
words 0.00126573
data experiments 0.001264237
buckeye corpus 0.0012230029999999999
deletion probability 0.001221291
segmentation performance 0.001221194
actual data 0.0012195119999999999
corpus lists 0.00121053
probability vector 0.0012080840000000001
enough corpus 0.001207477
ads corpus 0.001205883
different rules 0.001204261
artificial data 0.00119138
gram probability 0.001182954
problems language 0.001173115
buckeye data 0.001160115
real data 0.001153264
joint segmentation 0.001144687
naturalistic data 0.001144492
original data 0.001144276
possible context 0.0011404660000000001
gram language 0.001130496
statistical distribution 0.001117055
bayesian models 0.0011146490000000001
base distribution 0.0011102479999999999
prior distribution 0.00109267
computational models 0.00109118
segmentation scores 0.001073811
different contexts 0.0010491370000000001
segmentation experiments 0.001044024
natural distribution 0.001038488
context work 0.001034902
global distribution 0.001013756
empirical distribution 0.00100469
different assumptions 9.923850000000001E-4
generative models 9.823E-4
ing context 9.7803E-4
corpus 9.6985E-4
phonological context 9.63739E-4
different occurrences 9.62838E-4
small set 9.544460000000001E-4
joint inference 9.4765E-4
tation models 9.369129999999999E-4
different factors 9.3006E-4
phonological rules 9.22294E-4
simple example 9.200880000000001E-4
unigram case 9.166840000000001E-4
surface forms 9.10156E-4
ing forms 9.03226E-4
probability 9.02469E-4
many tokens 8.85233E-4
