language review 0.00249509
review translation 0.0024787200000000002
review text 0.00240834
language features 0.00226465
review rating 0.002130247
product reviews 0.002005921
text classification 0.001973321
test review 0.001959008
different language 0.001914187
training reviews 0.001888908
test reviews 0.001781608
review texts 0.001771963
same language 0.001744349
machine translation 0.001726309
regression learning 0.001715212
full review 0.001694091
regression model 0.001686455
labeled reviews 0.0016757999999999999
movie review 0.001669182
review transla 0.0016679730000000001
target language 0.001662311
classification task 0.001654586
model training 0.0016411540000000001
unlabeled reviews 0.001603804
source language 0.0016008049999999998
various features 0.001582356
sentiment classification 0.001580564
translation quality 0.001571369
prediction model 0.001535051
full reviews 0.001516691
regression task 0.001474314
product information 0.0014727310000000001
original reviews 0.0014715879999999998
unrated reviews 0.0014459009999999999
translation services 0.001424243
feature weight 0.0014167140000000001
regression algorithm 0.001407464
other words 0.0013957639999999999
automatic text 0.0013926289999999998
language gap 0.001388566
chine translation 0.001380507
labeled data 0.001368607
rating prediction 0.001363552
review 0.00136345
text field 0.0013370539999999998
learning process 0.001329298
prediction task 0.00132291
different target 0.0013132180000000001
prediction results 0.001312037
binary classification 0.00130904
text summaries 0.0013042499999999999
new regression 0.001303167
different languages 0.00130062
new task 0.001281163
evaluation results 0.0012777280000000001
training set 0.001264538
regression methods 0.001263613
learning framework 0.001261642
regression problem 0.0012527229999999999
different source 0.0012517119999999999
many regression 0.001228152
lazy learning 0.0012259430000000002
other classifier 0.001202298
amazon product 0.001198625
rating scores 0.001198276
regression performance 0.00119618
training documents 0.001193911
labeled training 0.001192608
classification scenario 0.001190698
rating score 0.001190067
regression svm 0.001186695
reviews 0.00118605
product category 0.001176877
test set 0.001157238
view rating 0.001150535
training dataset 0.001138513
different iteration 0.0011355649999999998
semantic topic 0.001133519
features 0.00113301
language 0.00113164
overall rating 0.001122034
translation 0.00111527
tion task 0.001114386
above regression 0.001106432
following baseline 0.001097614
product categories 0.001091314
final rating 0.001090045
test documents 0.001086611
feature 0.00108616
regression problems 0.001082907
comparison results 0.001080749
unrated product 0.001079722
regression algorithms 0.001070886
training process 0.001065103
monolingual training 0.001054877
labeled set 0.00105143
regression algo 0.001042879
previous work 0.001042157
binary sentiment 0.0010327420000000001
test dataset 0.001031213
