target data 0.00251624
language domain 0.00245226
domain adaptation 0.0023584599999999997
source data 0.0023121870000000003
target domain 0.00227662
test data 0.002262697
labeled data 0.002194495
source domain 0.002072567
feature vector 0.002067006
unlabeled data 0.002020597
sentiment classification 0.001991334
word distributions 0.001952952
many word 0.001937621
data points 0.001888589
word pairs 0.001867839
source language 0.001811127
sentiment classifier 0.001798581
feature vectors 0.001776564
average feature 0.001770071
input feature 0.001742669
different distribution 0.001702768
target distribution 0.0016949159999999999
other adaptation 0.00167756
domain mismatch 0.0016749389999999999
feature vec 0.0016601139999999999
feature normalization 0.001649022
different source 0.0016433390000000002
domain mis 0.001628863
inappropriate domain 0.001628863
adaptation problem 0.001625703
positive features 0.001605067
target classifier 0.001601721
adaptation algorithm 0.0015803969999999999
good results 0.001571971
sentiment polarity 0.001570908
same language 0.0015588099999999999
negative features 0.001516304
unigram features 0.001487474
standard adaptation 0.00148222
adaptation methods 0.0014653399999999999
language pair 0.001430749
language differences 0.001420813
language mismatch 0.001413499
new adaptation 0.0014134780000000001
clear sentiment 0.001408309
difficult language 0.001394962
sentiment ori 0.001389654
different polarity 0.0013819000000000001
language adapt 0.0013753300000000001
feature 0.00137517
strong adaptation 0.001371884
positive results 0.001365331
adaptation algorithms 0.0013637039999999999
svm results 0.001361817
adaptation problems 0.001361012
different domains 0.001358909
domain 0.00135685
unlabeled target 0.001343897
different labels 0.0013389370000000001
main adaptation 0.001338571
supervised results 0.001326486
adaptation algo 0.001318311
labeled source 0.0013137420000000001
adaptation scenario 0.001294787
lingual adaptation 0.0012908120000000001
adaptation scenarios 0.001287415
adaptation meth 0.001284185
different story 0.001277115
adaptation chal 0.001273987
label table 0.001218989
different settings 0.001214538
mixed results 0.001207052
prior work 0.001204608
different effects 0.001201574
good performance 0.0011943190000000001
features 0.00117066
source dataset 0.0011633910000000002
classification boundary 0.001157628
conditional distribution 0.001155915
sentiment 0.00111663
svm classifier 0.001112844
language 0.00109541
unigram distribution 0.00109196
average vector 0.001086737
source samples 0.001076759
average test 0.0010611280000000002
source distribu 0.001036628
foreign words 0.0010262399999999999
parameter tuning 0.001026199
classifier oracle 0.00101232
corresponding source 0.00100994
sample vector 0.001008131
adaptation 0.00100161
machine translation 9.97926E-4
learning 9.95334E-4
positive weight 9.90489E-4
book reviews 9.84523E-4
label mismatch 9.77433E-4
first row 9.741140000000001E-4
dvd reviews 9.71265E-4
