word word 0.00388456
word distribution 0.0038123799999999998
other model 0.002991131
single model 0.002765675
bayes model 0.002736052
perspective model 0.002708266
probabilistic model 0.0026494630000000003
unified model 0.002588609
probability distribution 0.002577727
base distribution 0.002405535
word distributions 0.002404285
similar word 0.002390548
single word 0.002377675
class distribution 0.002353142
word bigrams 0.002345383
model 0.00233028
generative distribution 0.00227832
word sequence 0.002236661
content distribution 0.002220162
word sequences 0.00221689
multinomial distribution 0.002210116
word position 0.002204639
distinct distribution 0.002180343
conservative distribution 0.002178958
progressive distribution 0.0021768259999999998
pcfg distribution 0.002165131
other words 0.002146751
original distribution 0.002142483
neutral distribution 0.002139389
terior distribution 0.002130133
distribution φzd 0.002128029
distribution 0.0018701
oov palestinian 0.001677936
palestinian oov 0.001677936
new language 0.00164918
training data 0.001612809
test data 0.00157112
oov work 0.001555222
bayesian models 0.001537521
words 0.0014859
oov time 0.001481664
time oov 0.001481664
classification models 0.00148014
grammar models 0.001429418
data sparsity 0.001421194
bayes models 0.001403453
recent oov 0.0013766219999999999
total oov 0.001371099
use oov 0.001357975
side oov 0.001341887
oov state 0.001339121
oov isra 0.001328782
isra oov 0.001328782
language substructures 0.001327076
inference algorithm 0.00132213
oov israel 0.001321924
israel oov 0.001321924
variable models 0.001318726
oov area 0.0013129419999999999
oov part 0.001312612
oov end 0.001310213
arafat oov 0.001309095
oov arafat 0.001309095
polit oov 0.001309095
sharon oov 0.001306491
attempt oov 0.001306491
oov agreement 0.001306491
howev oov 0.001306491
oov act 0.001306491
document classification 0.00129768
bayesian inference 0.001293418
nonparametric models 0.001288696
parametric models 0.00126461
classification results 0.001236935
small corpus 0.001201007
grammar inference 0.001185315
new table 0.001168874
other work 0.0011683029999999999
corpus size 0.001101448
tion results 0.001090203
such table 0.001089596
corpus filter 0.001089041
document collection 0.001088342
grammatical inference 0.001088313
lemons corpus 0.001086795
inference techniques 0.001084322
same time 0.001078451
document classifi 0.0010780569999999999
statistical inference 0.001077373
prior work 0.001076485
same grammar 0.001076294
same number 0.001072749
language 0.00106884
different labels 0.001062806
inference procedure 0.001060302
posterior inference 0.001052333
generator corpus 0.001050497
restaurant process 0.001041767
training set 0.001041061
corpus description 0.001028845
