english word 0.004408197
japanese word 0.004304377
word alignment 0.004288052
word dictionary 0.004258056
word segmentation 0.004209379
katakana word 0.004181951
standard word 0.004159658
word alignments 0.004061246
general word 0.004047902
vocabulary word 0.004020728
word dictionaries 0.00401446
single word 0.004012547
word formation 0.00399807
supervised word 0.003992503
art word 0.003962756
word segmenta 0.003962626
word boundary 0.003955317
constituent word 0.003949253
word junk 0.003946374
word seg 0.003943495
word boundaries 0.003938445
word segmen 0.003936216
word corre 0.003930097
existent word 0.00392799
implicit word 0.003925075
english words 0.0028336670000000002
katakana words 0.0026074210000000004
many words 0.0025547210000000002
vocabulary words 0.002446198
foreign words 0.0023926240000000003
constituent words 0.002374723
parenthesis words 0.0023622530000000004
glish words 0.0023560760000000004
cle words 0.0023510320000000003
compounded words 0.0023510320000000003
stituent words 0.0023510320000000003
ated words 0.0023510320000000003
identiﬁed words 0.0023510320000000003
words 0.00212813
language model 0.001771092
different feature 0.001743811
similarity model 0.001643625
other feature 0.001580339
feature set 0.0015424969999999999
other features 0.001526706
test data 0.001507064
perceptron model 0.001469979
model parameters 0.0014667019999999998
new feature 0.001414247
probabilistic model 0.001409163
data set 0.001407478
discriminative model 0.0014026239999999999
japanese text 0.001395542
feature value 0.001382599
training algorithm 0.001378249
pipeline model 0.0013683019999999998
new features 0.001360614
transliteration feature 0.0013502050000000002
data system 0.0013237370000000002
feature vector 0.00132201
basic feature 0.001291347
feature sets 0.001279923
paraphrase feature 0.001238683
basic features 0.001237714
feature dict 0.001229277
binary feature 0.0012241180000000002
feature description 0.001206021
sic feature 0.001186021
splitting models 0.001157692
alignment information 0.001153259
model 0.00114567
oov data 0.001145306
translation table 0.001130177
factored features 0.001129215
such noun 0.001122725
same number 0.001102846
textual data 0.001087449
ical data 0.001085599
other languages 0.001077828
other research 0.001071292
web text 0.0010668399999999999
labeled text 0.001063038
bilingual dictionary 0.001051511
unlabeled text 0.0010484869999999999
other types 0.001046111
different values 0.00104385
character types 0.001040745
text processing 0.001029681
parenthesis text 0.0010279479999999999
anchor text 0.0010179219999999999
single english 0.001015424
english side 0.00101214
segmentation system 0.001006858
online training 9.961990000000001E-4
segmentation systems 9.84041E-4
test time 9.83587E-4
english counterparts 9.82407E-4
such compounds 9.778669999999999E-4
english substring 9.77541E-4
original english 9.76119E-4
