source word 0.0038524600000000003
target word 0.00384053
other word 0.00317598
translation lexicon 0.0030693379999999996
word pairs 0.003064471
word types 0.003012585
word tokens 0.002965249
noun word 0.002964111
few word 0.002958586
word vectors 0.002952087
word type 0.0029032380000000003
matched word 0.002894743
hmm word 0.0028780050000000003
unmatched word 0.0028447
other translation 0.00263228
bilingual translation 0.0025805859999999997
translation pair 0.0025384189999999997
translation pairs 0.0025207709999999998
source feature 0.00251804
feature source 0.00251804
target feature 0.00250611
source target 0.00246371
example translation 0.002433681
machine translation 0.002432839
translation lexicons 0.002409353
source features 0.00236625
target features 0.00235432
translation systems 0.002339729
sible translation 0.002322031
source language 0.00231006
tical translation 0.002305863
target language 0.00229813
alignment model 0.002298125
translation correspon 0.00229745
initial translation 0.00229745
fident translation 0.00229745
valid translation 0.00229745
source lexicon 0.002236218
target lexicon 0.002224288
model parameters 0.002217743
context feature 0.0021544990000000003
current model 0.0021475319999999997
source words 0.002080081
translation 0.00207094
target words 0.002068151
generative model 0.0020612399999999998
probabilistic model 0.002031467
source corpus 0.00202265
context features 0.002002709
mcca model 0.002001307
cca model 0.001999893
monolingual feature 0.001854717
feature set 0.0018213450000000003
model 0.00176436
feature vector 0.0017622340000000001
monolingual features 0.001702927
rank source 0.0016791179999999998
source space 0.0016532
target space 0.0016412700000000002
other language 0.00163358
feature vectors 0.0016176670000000001
orthographic feature 0.0015982880000000002
optimal feature 0.001597623
target noun 0.0015753610000000002
monolingual lexicon 0.001572895
target fea 0.0015470850000000001
feature correspondences 0.0015324170000000001
feature relationships 0.001530212
feature representations 0.0015227600000000002
language pairs 0.0015220709999999998
feature correlations 0.001510768
bilingual lexicon 0.001508044
frequent source 0.001506453
map source 0.0015060849999999999
monolingual data 0.0015054320000000001
target correct 0.001491315
evaluation lexicon 0.001478152
unmatched source 0.00146788
target spaces 0.001467339
source feat 0.001465062
identical source 0.0014641399999999998
target mono 0.0014605030000000001
unmatched target 0.0014559500000000001
target feats 0.0014521120000000002
various features 0.00145084
orthographic features 0.001446498
type features 0.0014170279999999999
related language 0.0013805509999999998
features sets 0.001375447
seed lexicon 0.001370857
parallel corpus 0.001369645
graphic features 0.0013619939999999998
monolingual corpus 0.001359327
lexicon entries 0.001311735
language variation 0.001306341
morphological errors 0.001286024
feature 0.00128022
lexicon induction 0.001238191
source 0.00123782
lexicon variation 0.001232499
