conditional model 0.003069888
binomial model 0.003024201
joint model 0.002965144
last model 0.002888421
mixture model 0.002851608
second model 0.0028513
final model 0.002851147
bernoulli model 0.002829613
full model 0.002817615
mle model 0.002804806
third model 0.00280206
multinomial model 0.002786558
poisson model 0.00275662
ture model 0.002752321
event model 0.00275178
zinb model 0.00274817
son model 0.00274817
ing word 0.0025904910000000003
model 0.00252491
word vocabulary 0.002466316
length word 0.002459707
word occurrence 0.002446045
word types 0.0024015430000000003
word frequency 0.0023918340000000002
probability models 0.00235331
word occurrences 0.002343238
target word 0.00234064
innocent word 0.002329087
binomial models 0.0021658709999999998
linear models 0.0020212529999999998
simple models 0.002017903
classification models 0.00201244
training data 0.002000543
mixture models 0.001993278
standard models 0.001990172
bernoulli models 0.001971283
independent models 0.001968407
robust models 0.001938566
overdispersed models 0.00191909
ple models 0.001911584
inflated models 0.001895735
event models 0.00189345
mial models 0.001893244
multivariate models 0.001893125
dard models 0.001891088
pendent models 0.001889864
models 0.00166658
other words 0.0016212470000000001
test data 0.001612081
ing data 0.001559491
binomial distribution 0.001530601
many words 0.001523529
data set 0.001488262
empirical distribution 0.001435605
different probability 0.0014133169999999999
overall distribution 0.0013785829999999998
count data 0.001372964
standard distribution 0.0013549019999999998
language modeling 0.001348012
group data 0.001347835
actual data 0.0013451589999999999
newsgroup data 0.0013367
bernoulli distribution 0.001336013
webkb data 0.0012990039999999999
multinomial distribution 0.0012929579999999999
distribution binom 0.0012795579999999999
training classification 0.001271543
certain words 0.001271399
distribution moments 0.001263021
poisson distribution 0.00126302
mial distribution 0.0012579739999999998
nomial distribution 0.0012563569999999998
individual words 0.00125568
eggenberger distribution 0.001254667
distribution negbin 0.001254667
test results 0.00117982
taboo words 0.001175497
accuracy results 0.001130688
different vocabulary 0.001087043
parameter estimation 0.001075179
distribution 0.00103131
standard probability 0.001010322
probability mass 0.00100706
negative binomial 0.001004428
evaluation results 9.99491E-4
single parameter 9.88505E-4
classification results 9.884590000000001E-4
binomial likelihood 9.710700000000001E-4
language 9.65405E-4
likelihood estimation 9.63046E-4
words 9.51483E-4
different classifiers 9.512990000000001E-4
different parameterization 9.512990000000001E-4
test set 9.50623E-4
other hand 9.412590000000001E-4
training 9.25683E-4
entire probability 9.18288E-4
large counts 9.12327E-4
other outcomes 8.937E-4
other compo 8.937E-4
