training data 0.002326801
training set 0.002181776
different word 0.001954699
different feature 0.001846001
unsupervised classifier 0.001832511
other words 0.001815911
new training 0.0017884469999999999
words feature 0.0017711720000000001
data set 0.001768237
second classifier 0.001765519
supervised classifier 0.001752443
small training 0.001729342
feature set 0.001720688
combined classifier 0.001693847
initial training 0.001658446
semantic analysis 0.0016454529999999998
pervised classifier 0.001627679
test data 0.001624146
separate classifier 0.00162269
classifier bias 0.0016192099999999998
trained classifier 0.001614919
enlarged training 0.001611096
imbalanced training 0.001605239
different classifiers 0.001603772
class figure 0.001600654
other features 0.0015835649999999999
different features 0.001566663
word sense 0.0015613860000000001
class baseline 0.0015370790000000002
literal class 0.001528449
feature analysis 0.001466095
classification decision 0.00145713
such examples 0.001450433
semantic distance 0.001413375
semantic roles 0.0014063959999999999
literal classification 0.001404424
different experiments 0.001398362
classifier 0.00138124
training 0.00137017
other approaches 0.001356452
minority class 0.0013480470000000002
class overall 0.0013476970000000001
classification approach 0.0013464549999999999
majority class 0.0013447910000000001
semantic relatedness 0.001344125
other expressions 0.001335984
idiom classification 0.001330216
class iteration 0.001322433
small data 0.001315803
classification task 0.001315588
class distri 0.0013019330000000001
word fire 0.001286654
feature vector 0.0012724519999999999
different iterations 0.001267951
word senses 0.001254293
feature sets 0.001243278
feature space 0.00124227
other concepts 0.001241661
overall data 0.0012343480000000001
classification errors 0.0012259229999999999
other variations 0.001222902
set size 0.001211268
automatic classification 0.001210277
other hand 0.001205203
separate data 0.001198081
ing set 0.001196476
other clues 0.001192928
imbalanced data 0.0011917
data sparseness 0.0011916119999999999
feature dimensions 0.001191394
different variants 0.001189813
complete data 0.0011897470000000001
classification focus 0.001188104
good performance 0.001185661
unsupervised method 0.001185139
feature prec 0.001180323
different aspects 0.001179872
neighbour classification 0.001177743
related words 0.001176336
different measures 0.001174003
small set 0.001170778
connectivity feature 0.001168443
saliency feature 0.001153973
component words 0.0011496660000000001
ful feature 0.001144649
fourth feature 0.001141373
feature engineering 0.001141373
test instances 0.001120086
unsupervised model 0.001117957
set enlargement 0.001115076
cue words 0.001112177
content words 0.001107694
indicative words 0.001101329
salient words 0.001096541
tify words 0.001095239
literal examples 0.001092684
class 0.00106998
development set 0.0010640559999999999
overall performance 0.001059502
set increases 0.001059407
