word sense 0.0050379
text word 0.003869435
word senses 0.003514927
target word 0.003480394
first word 0.003388713
word correlation 0.003387811
word pairs 0.003386812
paradigm word 0.003354817
metaphorical word 0.0033519459999999997
order word 0.003347569
word usage 0.00333866
concrete word 0.003330161
second word 0.003272309
word red 0.00323467
classical word 0.003221587
sify word 0.003213831
sense disambiguation 0.002612746
metaphorical sense 0.0024717460000000004
literal sense 0.0024661630000000004
concrete sense 0.002449961
target words 0.002349744
new words 0.002344558
political sense 0.002337495
single words 0.00232047
ing words 0.002262301
paradigm words 0.002224167
words order 0.002216919
concrete words 0.002199511
words rating 0.002171392
rating words 0.002171392
abstract words 0.002150862
words abstract 0.002150862
mrc words 0.002148854
tive words 0.002137011
positive words 0.002120407
rates words 0.00208916
nent words 0.002083452
words accord 0.002083452
paragidm words 0.002083452
sense 0.00207885
semantic similarity 0.001958656
words 0.0018284
training data 0.001643576
single model 0.00151909
such data 0.0014864400000000001
context frequency 0.001461828
semantic analysis 0.00146103
regression model 0.001442636
separate model 0.001416034
semantic orientation 0.001371128
different scores 0.001362585
stract context 0.001349144
space model 0.001333289
semantic content 0.00132862
testing data 0.001316174
rate model 0.001308715
metaphorical text 0.0013032809999999999
gression model 0.00128294
other verbs 0.001271029
similarity measure 0.001266519
training set 0.001266176
performance algorithm 0.001265164
similarity rating 0.001246258
new algorithm 0.001228933
feature vector 0.001224749
numerical similarity 0.001213003
same number 0.001192819
training verbs 0.001187325
set performance 0.001184069
plain text 0.001169185
technical text 0.001169185
text genres 0.001169185
learning algorithm 0.0011597880000000001
new set 0.001147838
test set 0.001145135
algorithm accuracy 0.00113743
new matrix 0.001094872
large corpus 0.001092951
context 0.00108879
daily language 0.001069005
new verbs 0.001068987
ing set 0.001065581
wsd approach 0.001065071
regression models 0.001061654
set correlation 0.001060441
noun abstractness 0.0010588540000000001
rating algorithm 0.001055767
training sentences 0.001044294
abstractness value 0.001039537
ing system 0.001032847
eign language 0.001028719
paradigm set 0.001027447
model 0.00102702
other hand 0.001023901
average abstractness 0.001020683
disambiguation task 0.001014207
same subset 0.001014134
own algorithm 0.0010018380000000001
new approach 0.0010011479999999999
feature vectors 9.98867E-4
