training document 0.00192288
document similarity 0.001871911
test document 0.0017948500000000002
query document 0.001753447
training data 0.0017327089999999998
test data 0.001604679
similarity features 0.0015941549999999999
document space 0.001576197
document vector 0.001565749
training documents 0.001560705
document length 0.001523137
document representation 0.001517218
word length 0.001509607
training set 0.001495081
negative documents 0.001468432
learning method 0.00146744
method learning 0.00146744
average document 0.00146385
document frequency 0.001458968
sample document 0.001458502
average word 0.00145032
test documents 0.001432675
original document 0.001424936
many features 0.00141302
pairwise document 0.001410565
word count 0.001410291
classic document 0.001394022
query documents 0.0013912719999999998
other test 0.001383119
feature space 0.001382304
document drijk 0.001377531
similarity function 0.001375608
word uni 0.001372557
feature vector 0.001371856
test set 0.0013670510000000002
document repre 0.001366315
raw document 0.001366175
word unigrams 0.0013644199999999999
inverse document 0.0013643190000000001
document dti 0.001360349
document similarities 0.001360349
learning algorithm 0.001345455
new method 0.0013363490000000001
query set 0.001325648
retrieval method 0.0013162949999999999
feature vectors 0.001298701
experiment data 0.001275177
ing documents 0.001269104
basic data 0.001267528
author set 0.001259676
other methods 0.001256224
test query 0.0012561970000000001
decision method 0.001248197
positive documents 0.001240335
classification learning 0.001238267
good features 0.001233859
original feature 0.001231043
data sets 0.001208388
negative score 0.001206539
new learning 0.0011910290000000001
test author 0.001190225
style features 0.001184098
voting method 0.0011715480000000001
following features 0.001162202
similarity space 0.001156008
similarity values 0.001155407
same author 0.0011501839999999998
different number 0.001149653
query author 0.0011488219999999999
document 0.00114605
sentence similarity 0.00114417
different decision 0.001122095
many classification 0.001121933
same problem 0.0011205199999999998
similarity measure 0.001109267
other userids 0.001101569
only documents 0.001099366
classification score 0.001099189
sample documents 0.001096327
unigram features 0.0010936700000000001
space learning 0.0010912069999999999
classification problem 0.001088968
first similarity 0.001087812
promising features 0.0010853710000000001
test case 0.001076197
training authors 0.001075913
many methods 0.0010666310000000002
similarity measures 0.001063742
other experiments 0.001060021
function words 0.001058692
aggregation method 0.001049735
training example 0.001049594
based method 0.00104833
different userids 0.001047528
ing classifier 0.0010419449999999999
model auxilia 0.001041494
known documents 0.001040086
similarity scores 0.001039221
default method 0.0010385659999999999
lss method 0.00103368
