text fragments 0.002024714
corpus tokenization 0.001825175
project corpus 0.001573638
ent corpus 0.001544826
text classification 0.0015225820000000002
test fragments 0.001520203
plain corpus 0.0015057620000000001
extant corpus 0.001489219
hittite text 0.001479966
cuneiform fragment 0.001453201
cuneiform fragments 0.001411351
fragment figure 0.001408043
large text 0.001397538
this fragment 0.001376639
individual fragments 0.001360732
new texts 0.0013539099999999998
related text 0.001337031
tablet fragment 0.0013204660000000002
total fragments 0.001318534
hittite texts 0.001316724
fragment transcriptions 0.001316618
small fragments 0.0013161899999999999
unknown fragments 0.00131335
individual text 0.001307346
tablet fragments 0.001278616
corpus 0.00126833
text file 0.0012491590000000001
other cuneiform 0.001227799
text classi 0.001225263
plain text 0.0012230960000000001
text present 0.001215629
text classifica 0.001210807
text assembly 0.001207408
cuneiform texts 0.001194723
different characteris 0.0011211300000000001
training set 0.001119739
other approaches 0.001116299
new set 0.001116281
hittite words 0.001106155
other ways 0.001098236
texts com 0.00108896
classification method 0.0010859200000000002
fragment 0.0010809
new word 0.001078702
other ancient 0.001077228
test set 0.001065946
same subject 0.001062169
cth texts 0.001052238
plete texts 0.001048247
fragments 0.00103905
language toolkit 0.00102443
test accuracy 0.001019011
excellent results 0.001015957
results section 0.001007262
hittite hittite 9.88604E-4
common words 9.80551E-4
classification task 9.7559E-4
current word 9.110419999999999E-4
entropy classification 8.68623E-4
hittite cuneiform 8.66603E-4
accuracy values 8.579060000000001E-4
large number 8.43644E-4
hittite noun 8.38856E-4
sentence similarity 8.34165E-4
texts 8.22422E-4
such writings 8.119049999999999E-4
classification metrics 8.09335E-4
bayes classification 8.08566E-4
language 8.0339E-4
various hittite 7.9951E-4
raw accuracy 7.92664E-4
single document 7.86272E-4
tokenization scheme 7.78406E-4
further work 7.73671E-4
cuneiform languages 7.69802E-4
hittite capital 7.696109999999999E-4
discussion accuracy 7.60115E-4
computational work 7.54831E-4
general problems 7.54706E-4
new publishing 7.54494E-4
phonemic value 7.525E-4
typical hittite 7.398279999999999E-4
standard akkadian 7.353310000000001E-4
hittite tablet 7.338679999999999E-4
standard algorithms 7.3379E-4
original work 7.33618E-4
hittite treaty 7.2448E-4
correct categorization 7.233540000000001E-4
hittite schol 7.15519E-4
hittite empire 7.15519E-4
hittite scholars 7.15519E-4
hittite city 7.15519E-4
results 7.0833E-4
legitimate test 7.04691E-4
bracket characters 7.020959999999999E-4
case characters 7.01868E-4
entropy classifier 6.923809999999999E-4
actual characters 6.91416E-4
variable frequency 6.850879999999999E-4
many pieces 6.84413E-4
