target word 0.00422795
word alignment 0.003660628
function word 0.003399362
word position 0.003350768
word align 0.003218752
word cloud 0.00319637
translation system 0.0031959130000000003
word sets 0.0031931249999999998
hmm word 0.003176926
europarl word 0.00316082
leverage word 0.003156779
word frequencies 0.003155856
word breaking 0.003154911
translation process 0.003047582
machine translation 0.003018531
translation output 0.003005574
level translation 0.002963691
translation quality 0.0029332280000000004
translation direction 0.0029223490000000003
translation phenomena 0.0028541390000000003
chine translation 0.002828521
minimal translation 0.002823912
translation directions 0.0028208350000000003
translation units 0.0028203280000000004
translation direc 0.0028161500000000003
tone translation 0.0028161500000000003
posite translation 0.0028161500000000003
language model 0.0027497299999999997
translation 0.00256738
bilingual features 0.0024949250000000003
different features 0.0024525890000000002
lexical features 0.002310506
monolingual features 0.002305506
alignment model 0.002292538
new features 0.002271412
order features 0.002244816
feature set 0.002224773
source language 0.00213858
gram features 0.0021170250000000002
mtu features 0.0021152510000000003
fication features 0.002103111
lexicalized features 0.002103111
unigram features 0.002103111
individual feature 0.002077013
feature extraction 0.00202976
top feature 0.002020985
eral feature 0.002019879
target pos 0.001969806
features 0.00185405
trigram model 0.001794439
feature 0.00176191
training data 0.001728616
many language 0.001689033
target side 0.0016637980000000002
order language 0.001602626
function words 0.001598192
language pairs 0.0015859399999999999
source pos 0.001574536
model 0.00153787
specific language 0.001484469
annotated language 0.001476306
native language 0.001460387
alignment models 0.001417143
test data 0.001401016
rare words 0.001394186
sentence pair 0.0013871159999999999
content words 0.001358132
source text 0.001336705
target 0.00132199
source order 0.001317486
sentence level 0.00129265
parallel data 0.001277851
sentence pairs 0.001270419
english pos 0.001243909
language 0.00121186
entire sentence 0.001196234
similar task 0.0011940829999999999
sentence cloud 0.001186749
training classifiers 0.001174624
aligned sentence 0.001166992
other research 0.001157059
parallel corpus 0.001154231
tains sentence 0.001144931
detection task 0.001142408
several results 0.0011362999999999998
first noun 0.00113153
cloud data 0.00112197
hansard data 0.001104907
words 0.00110479
linguistic analysis 0.0011025100000000001
wmt data 0.001089296
other corpora 0.001084227
data visualiza 0.0010805889999999999
linguistic structures 0.001065629
alignment tool 0.001044725
corresponding pos 0.001027908
hmm alignment 0.001025634
different corpora 0.001023463
bilingual fea 0.0010154909999999999
other direction 0.001014272
