other word 0.004622112
word corpus 0.0046050530000000004
word similarity 0.004493907
new word 0.004467736
word pairs 0.004396205
word association 0.004381623
frequency word 0.004360827
word pair 0.00433324
multiple word 0.004259034
common word 0.004255396
frequent word 0.004213644
approximate word 0.0042037490000000005
word sense 0.004183179
exact word 0.004175153
unique word 0.004151859
target word 0.0041350200000000005
rare word 0.00413198
topk word 0.004108792
tween word 0.004106368
infrequent word 0.004104934
frequent words 0.001712824
training data 0.001710493
content words 0.001704011
negative words 0.001695811
unique words 0.001651039
stop words 0.00162977
prototype words 0.0016169140000000001
positive words 0.001604379
vidual words 0.001600687
large data 0.001551172
context vector 0.001528249
such data 0.001525932
test data 0.0015176010000000001
text data 0.001500983
model size 0.0014901329999999998
single model 0.001470323
different sketch 0.001468092
web data 0.0014447120000000001
context vectors 0.001423168
data structure 0.001406808
words 0.00138188
data stream 0.0013489230000000001
semantic similarity 0.001327387
different size 0.001327185
streaming data 0.001324198
language models 0.00132288
other sketch 0.001316142
context pairs 0.001309447
sketch vector 0.0013090369999999999
different number 0.001305595
summary data 0.0012947730000000001
counter model 0.001289592
parameterized model 0.0012780959999999998
storage data 0.001278054
labeled data 0.0012742550000000002
data gigaword 0.001270869
combined data 0.0012679380000000001
different values 0.001263226
translation models 0.001241888
size models 0.001172218
different input 0.001166711
corpus size 0.001158176
different sizes 0.001141613
different settings 0.00113328
different runs 0.001132084
context window 0.001091197
rank context 0.00108952
model 0.00105431
ing corpus 0.00105032
corpus statistics 0.0010287949999999999
topk context 0.001022034
plausible context 0.0010146
sketch size 0.001012553
pairs association 0.0010124280000000001
other details 0.0010105169999999998
semantic orientation 9.814749999999999E-4
other settings 9.813299999999999E-4
sketch counts 9.78186E-4
corpus sizes 9.72604E-4
counter models 9.71677E-4
other advantages 9.675599999999999E-4
similarity pmi 9.654679999999999E-4
other datasets 9.651709999999999E-4
corpus subset 9.48153E-4
similarity measure 9.46336E-4
small sketch 9.45081E-4
gigaword corpus 9.44742E-4
whole corpus 9.439240000000001E-4
same counts 9.40843E-4
semantic ori 9.35877E-4
similarity llr 9.19004E-4
distributional similarity 9.098649999999999E-4
similarity distributional 9.098649999999999E-4
approximate sketch 8.97779E-4
mutual information 8.91088E-4
relation learning 8.88125E-4
phrase pairs 8.82258E-4
first group 8.801939999999999E-4
frequency counts 8.79583E-4
natural language 8.76751E-4
