probability model 0.00297257
clustering model 0.002718633
bigram model 0.002320617
above model 0.002306441
model description 0.002291795
optimal model 0.002268569
current model 0.00226772
general model 0.0022602769999999998
cut model 0.0022337859999999998
word clustering 0.002204473
ofa model 0.0021926109999999997
discrete model 0.002190916
bility model 0.002190007
restricted model 0.002188645
training data 0.001994927
model 0.0019703
word pairs 0.001929492
test data 0.0019216329999999998
word distribution 0.001920061
word classes 0.001880757
ing data 0.001808221
clustering words 0.0016799739999999999
data description 0.001675425
data size 0.0016701539999999999
probability models 0.00165349
clustering method 0.001650529
data sparseness 0.001601789
total data 0.001592932
entire data 0.001575285
data base 0.001572485
data compression 0.001570463
data descrip 0.001564397
probability distribution 0.001466191
ion method 0.001460814
noun class 0.001449348
probability values 0.0013999849999999999
clustering models 0.001399553
clustering algorithm 0.001397902
probability parameters 0.0013430270000000001
joint probability 0.001327242
probability dis 0.001322761
probability distributions 0.00128963
class pairs 0.0012501230000000001
disambiguation method 0.0012464759999999998
head words 0.001234307
equal probability 0.001230934
tion method 0.001185764
clustering problem 0.001172638
ferent words 0.001138869
clustering methods 0.001132443
estimation algorithm 0.001125142
previous clustering 0.001124093
analogous method 0.001113523
method acc 0.0011110949999999999
biguation method 0.0011110949999999999
same class 0.001109056
byour method 0.001109054
method coy 0.001109054
single noun 0.001097237
noun classes 0.0010971940000000001
possible models 0.00108377
class pair 0.001063416
first noun 0.0010531310000000001
clustering process 0.001034981
different classes 0.001019227
noun disambiguation 0.001016857
probability 0.00100227
hard clustering 9.88934E-4
soft clustering 9.85652E-4
noun set 9.59781E-4
heuristic algorithm 9.53128E-4
noun triples 9.3658E-4
words 9.31641E-4
likelihood function 9.19098E-4
likelihood estimation 9.1874E-4
cut models 9.147059999999999E-4
statistical estimation 9.11969E-4
penn tree 9.042259999999999E-4
tree cut 9.040789999999999E-4
method 9.02196E-4
compound noun 8.98769E-4
pound noun 8.796450000000001E-4
neighboring noun 8.796450000000001E-4
noun thesauruses 8.796450000000001E-4
other hand 8.75961E-4
efficient algorithm 8.68791E-4
cient algorithm 8.57926E-4
tree bank 8.519539999999999E-4
likelihood estimate 8.35836E-4
different raining 8.032369999999999E-4
different ypes 8.032369999999999E-4
information reduction 7.994899999999999E-4
joint distribution 7.888929999999999E-4
desirable feature 7.85381E-4
isambiguat ion 7.82001E-4
class 7.76771E-4
imat ion 7.72623E-4
previous methods 7.5987E-4
parameter description 7.57757E-4
clustering 7.48333E-4
