training data 0.0029521
data set 0.002365017
active learning 0.0022728130000000003
learning method 0.002262076
unlabeled data 0.002211572
data distribution 0.002075562
training set 0.002072897
learning algorithm 0.002070348
ing data 0.002034608
learning experiments 0.001995027
machine learning 0.0019283
original data 0.001915922
supervised learning 0.001892244
data sets 0.001889081
learning iteration 0.001879601
imbalanced data 0.001859566
data the 0.001855783
the data 0.001855783
anced data 0.0018529129999999999
learning algorithms 0.001847631
learning comparison 0.001842349
training examples 0.0018389970000000002
word sense 0.0018312189999999998
tive learning 0.001784806
learning procedure 0.0017819749999999999
learning rules 0.001762628
new training 0.0017558460000000001
training samples 0.0017011970000000002
small training 0.001673056
current training 0.001643647
useful training 0.001635146
training cost 0.0016271760000000001
initial training 0.001599712
human annotation 0.00159754
training sam 0.001593864
borderline training 0.0015712
desirable training 0.001562657
training material 0.0015602110000000001
learning 0.00151534
classifier performance 0.001457019
wsd classifier 0.0014336
sampling method 0.0013985170000000002
target word 0.001390403
unlabeled corpus 0.001377552
words sense 0.001353824
noun word 0.001344781
training 0.00132999
classification performance 0.0012959669999999999
skewed word 0.001287784
disambiguated word 0.0012870689999999998
automated word 0.0012846659999999998
other instances 0.00124375
classifier confidence 0.001241022
unlabeled instances 0.001240063
supervised classifier 0.00123306
sense distribution 0.0012311610000000001
classification accuracy 0.00122426
class sample 0.001220195
basic classifier 0.001208016
final classifier 0.001174054
current classifier 0.001169813
other words 0.001169264
sample set 0.001162041
small class 0.001144127
text classification 0.001139052
class imbalance 0.001138748
accuracy performance 0.001130019
initial classifier 0.0011258779999999999
effective classifier 0.001120106
classification results 0.001114117
classifier effectiveness 0.001110859
sense disambiguation 0.001109339
sense ambiguity 0.001100646
same classification 0.001100053
unlabeled examples 0.001098469
trained classifier 0.001093511
estimating classifier 0.001088814
random sampling 0.001086923
minority class 0.001084913
sense distributions 0.001083235
annotation 0.00108216
classification confidence 0.00107997
new instances 0.001076457
majority class 0.001062697
class balance 0.001062266
uncertainty sampling 0.00105027
error method 0.001041787
rate information 0.00103834
predominant class 0.001035244
infrequent sense 0.00103469
complete class 0.00103147
distribution words 0.001029567
human labeling 0.001028157
bootstrap method 0.001023498
former method 0.001020933
bootstrap set 0.001019669
information extraction 0.001016621
latter method 0.001015633
active learner 0.001015275
wsd random 0.001012586
