word model 0.00458123
translation model 0.00394164
probability model 0.003602372
syntactic model 0.003436102
model probabilities 0.003246765
model parameters 0.003182492
word alignment 0.00318154
baseline model 0.003167906
model accuracy 0.003131146
single model 0.003084749
probabilistic model 0.003071812
semantics model 0.003030969
regression model 0.00300668
surface model 0.002998904
tic model 0.002997915
component model 0.002996316
actual model 0.002996211
linear model 0.002992385
erative model 0.002971984
combined model 0.002971747
tive model 0.002971508
latter model 0.002970259
poe model 0.002967086
model correspon 0.002961076
overlap model 0.002960846
model outper 0.002959372
model metaparameters 0.002958581
detailed model 0.002958581
model incorpo 0.002958581
lap model 0.002958581
model 0.00272595
source word 0.002507511
target word 0.002447637
word distribution 0.002375452
word corpus 0.002329458
unigram word 0.002152156
word unigram 0.002152156
head word 0.002136968
word root 0.002095278
root word 0.002095278
ith word 0.002089429
other sentence 0.0018063340000000002
tree alignment 0.0017847039999999998
source sentence 0.0016953010000000002
simple features 0.0016408339999999999
target sentence 0.001635427
similar features 0.001626335
structural alignment 0.0016202209999999998
machine translation 0.0015983899999999999
target words 0.001544024
sentence pair 0.0015440230000000003
various features 0.001540105
training data 0.001539536
other models 0.001537864
semantics features 0.0015034089999999998
first sentence 0.001498717
similarity features 0.001481275
different feature 0.001479059
surface features 0.0014713439999999999
sider features 0.00143188
tactic features 0.00143188
target language 0.001408916
training set 0.00139766
same source 0.001347633
alignment 0.00132626
sentence similarity 0.0013259550000000002
training pairs 0.0013199499999999999
grammar models 0.001299721
sure sentence 0.001290031
hidden alignments 0.001281652
generative probability 0.001249608
probability estimate 0.001245282
conditional probability 0.001240958
identical words 0.001223171
translation 0.00121569
loose alignments 0.001208196
features 0.00119839
tween words 0.001188261
standard data 0.001185131
low probability 0.001182508
unigram probability 0.001173298
syntactic tree 0.001168596
target sentences 0.001168157
feature ablation 0.001160043
few feature 0.001155962
same way 0.001149056
posterior probability 0.001145182
feature sets 0.001139871
natural language 0.001135016
treebank data 0.001125364
rior probability 0.001112058
source tree 0.001110675
terior probability 0.0011093309999999999
possible target 0.001099117
discriminative training 0.0010958259999999998
dependency grammar 0.001095108
syntactic structure 0.00108107
development data 0.001072396
test set 0.001066585
other configurations 0.0010646030000000001
