training data 0.004202330000000001
parallel data 0.00414346
english data 0.003941237
data english 0.003941237
test data 0.00392657
data unlabeled 0.0038722770000000004
unlabeled data 0.0038722770000000004
news data 0.00383845
domain data 0.0037662340000000002
labeled data 0.003683027
first data 0.00365903
data chinese 0.0036565900000000004
chinese data 0.0036565900000000004
data figure 0.0035844360000000003
data sets 0.003536247
second data 0.00351966
input data 0.003449129
data setting 0.003429386
data output 0.0034290510000000002
multiple data 0.0034124890000000003
ntcir data 0.0033799990000000003
data settings 0.0033654320000000002
mpqa data 0.003361354
english model 0.002711597
joint model 0.002498187
generative model 0.00224725
statistical model 0.002234648
model complexity 0.0021897460000000002
novel model 0.002150539
language information 0.002132763
new language 0.002069642
target language 0.001980592
source language 0.001971816
word alignment 0.001881322
unlabeled parallel 0.001869717
parallel text 0.001867615
language pair 0.0018564550000000001
parallel corpus 0.0018540319999999998
original language 0.001845242
model 0.00184337
translation system 0.001834541
translation probability 0.0018161560000000002
chinese word 0.00181561
other learning 0.001796764
joint training 0.001784137
parallel sentences 0.0017677679999999999
new translation 0.0017675720000000002
language gap 0.0017628420000000001
chinese translation 0.00175481
training set 0.001750303
labeled training 0.001739337
parallel information 0.001729913
weight word 0.001721547
word weight 0.001721547
machine translation 0.001702341
translation pairs 0.001693945
word sense 0.0016833310000000002
english corpus 0.001651809
translation probabilities 0.0016504590000000002
english sentence 0.001616757
negative word 0.0015682860000000001
english sentiment 0.001559988
unlabeled sentence 0.001547797
word aligner 0.001524683
berkeley word 0.001521582
word segmenter 0.001521582
direct translation 0.001508741
other languages 0.001504474
unlabeled sentences 0.001496585
labeled english 0.001478244
test set 0.001474543
language 0.0014733
translation engines 0.001470237
joint learning 0.001460937
chinese english 0.0014518069999999998
english chinese 0.0014518069999999998
other nlp 0.001446027
same sentiment 0.001440808
other tasks 0.001409037
large feature 0.001371064
parallel instances 0.0013605689999999998
chinese sentence 0.00133211
chinese feature 0.0013260680000000001
unlabeled figure 0.001310693
alignment information 0.001308755
chinese sentences 0.001280898
chinese sentiment 0.0012753410000000001
sentence pairs 0.0012712449999999998
english gigaword 0.001259573
english resources 0.0012410869999999999
original english 0.001240169
different languages 0.0012383189999999999
results figure 0.0012345210000000001
linear models 0.0012333749999999999
sentence level 0.001232311
monolingual models 0.001220002
text classification 0.001218168
domain adaptation 0.001216742
same label 0.001216276
optimization problem 0.001207028
