word features 0.00419723
words model 0.00336119
morphological features 0.003343335
morphological feature 0.003032575
alignment features 0.002985062
dependency features 0.002929925
other features 0.002925319
context features 0.002894799
possible features 0.002830502
morphology features 0.002784662
additional features 0.002777673
multiple features 0.002745273
mixture model 0.002707006
sequence model 0.002699561
tional features 0.002681959
level features 0.002681298
extra features 0.002641654
extended features 0.002629925
morphology model 0.002620552
phology features 0.00261847
ated features 0.002616173
same feature 0.0026129480000000004
similar model 0.00257272
clustering model 0.002555759
basic model 0.002520592
feature space 0.0025185380000000003
feature type 0.0025131140000000003
bayesian model 0.0025055570000000003
ment model 0.002484876
second feature 0.002475003
joint model 0.002467626
extended model 0.002465815
probabilistic model 0.002462
sic model 0.002452117
first feature 0.0024504360000000003
single feature 0.002442271
features 0.00240947
feature types 0.002375985
feature vectors 0.002358605
feature counts 0.0023476020000000003
extra feature 0.002330894
feature tokens 0.0023302030000000003
conditioning feature 0.0023129970000000002
phology feature 0.00230771
feature fjk 0.00230576
ogy feature 0.00230576
other word 0.002303609
context word 0.002273089
model 0.00224536
word type 0.002202164
word alignments 0.002144703
single word 0.002131321
feature 0.00209871
frequent word 0.002072187
word types 0.002065035
word align 0.002016499
word kind 0.002004797
context words 0.001601159
other language 0.001480536
frequent words 0.001400257
possible language 0.001385719
common words 0.0013650569999999998
language pairs 0.001347497
infrequent words 0.001324285
quent words 0.001323473
language types 0.001241962
wsj corpus 0.001231334
morphological segmentation 0.0012251879999999999
paired language 0.00122393
sible language 0.001222616
training sections 0.0012176770000000001
corpus statistics 0.001216238
sequence models 0.001213864
bulgarian corpus 0.001178017
actual corpus 0.001168939
conll corpus 0.0011679659999999999
alignment results 0.001158142
linguistic data 0.001143589
words 0.00111583
various models 0.001108951
other results 0.001098399
english data 0.001054746
training 0.00100799
deficient models 9.66646E-4
results table 9.66487E-4
language 9.64687E-4
test time 9.562920000000001E-4
syntactic class 9.52664E-4
corpus 9.50541E-4
alignment fea 9.49041E-4
standard mixture 9.30235E-4
good results 9.27636E-4
additional test 9.15284E-4
same class 9.15264E-4
previous results 9.008590000000001E-4
other systems 9.00463E-4
method system 8.98705E-4
test languages 8.983610000000001E-4
alignment procedure 8.92627E-4
same value 8.90105E-4
