data set 0.002197874
data matrix 0.002163013
training data 0.002057393
language data 0.001993858
data distribution 0.001980726
data objects 0.001927906
data generation 0.0018341759999999999
data mean 0.001824663
data size 0.001789821
original data 0.001755174
transcribed data 0.001724222
newsgroups data 0.0017134329999999999
synthetic data 0.0017005409999999999
entire data 0.001700315
centered data 0.001685912
data centroid 0.001680249
guage data 0.001672016
feature vector 0.001412697
training set 0.001382307
feature space 0.00136005
similarity matrix 0.001330423
feature vectors 0.001319521
new feature 0.001316407
centered feature 0.001202207
implicit feature 0.001195273
different clusters 0.0011632629999999999
other words 0.001157672
other objects 0.0011494019999999999
knn matrix 0.001136899
other object 0.0011332690000000001
similarity measures 0.001122175
different clus 0.001115417
different classes 0.00111357
training objects 0.001112339
same cluster 0.001107719
other methods 0.001093252
object similarity 0.001079183
kernel function 0.001077468
product similarity 0.0010765640000000001
probabilistic model 0.001071567
many objects 0.00105873
similarity measure 0.00104133
known set 0.001029393
many test 0.001027314
similarity scores 0.001025041
ing method 9.98203E-4
similarity score 9.84268E-4
matrix xcent 9.73405E-4
gram matrix 9.7247E-4
several parameter 9.63976E-4
same class 9.63354E-4
matrix kcent 9.587490000000001E-4
identity matrix 9.55795E-4
ilarity matrix 9.54475E-4
classification performance 9.532080000000001E-4
matrix transpose 9.53195E-4
larity matrix 9.53195E-4
symmetric matrix 9.53195E-4
matrix inversion 9.53195E-4
feature 9.52775E-4
test objects 9.51436E-4
target word 9.44115E-4
knn algorithm 9.41259E-4
test object 9.35303E-4
vector object 9.35215E-4
similar objects 9.30789E-4
word sense 9.27249E-4
same analysis 9.21415E-4
weighted mean 9.146060000000001E-4
cosine similarity 9.137780000000001E-4
classification results 9.08254E-4
unsupervised method 8.97134E-4
document classification 8.93584E-4
labeled training 8.928879999999999E-4
natural language 8.92632E-4
distance measures 8.90257E-4
classification dataset 8.90169E-4
tive similarity 8.901670000000001E-4
standard sense 8.89578E-4
random variable 8.89078E-4
language tasks 8.86516E-4
standard way 8.81666E-4
random vari 8.8006E-4
elaborate features 8.71031E-4
transcribed method 8.66012E-4
many hub 8.628780000000001E-4
inner product 8.62268E-4
class information 8.61155E-4
knn classification 8.601780000000001E-4
weighted frequency 8.55763E-4
similarity mea 8.544070000000001E-4
centered similarity 8.533220000000001E-4
base similarity 8.524000000000001E-4
mean vector 8.48105E-4
centroid similarity 8.476590000000001E-4
information retrieval 8.46154E-4
weighted variant 8.45705E-4
target words 8.42643E-4
same way 8.410199999999999E-4
language process 8.385249999999999E-4
