language models 0.001649273
source model 0.0016331890000000002
data set 0.0015525019999999999
source data 0.001545429
character data 0.001527947
space model 0.0014966200000000002
probabilistic model 0.001468315
frequency model 0.0014517970000000001
test data 0.001448385
bigram model 0.001445337
models results 0.001429865
source models 0.001428335
linguistic data 0.001427194
character models 0.0014108529999999999
channel model 0.001395986
news data 0.001379415
model bootstrapping 0.001371293
gram model 0.0013656830000000001
trigram model 0.001360915
fertility model 0.001355361
harsh model 0.0013477300000000001
source word 0.0013474770000000001
such methods 0.001320384
english word 0.001304856
phonetic decipherment 0.0012765300000000001
hindi word 0.001254224
unsupervised word 0.001253159
source language 0.001209536
complex models 0.001205455
initial models 0.001167858
word frequency 0.001166085
same method 0.0011632399999999998
model 0.00113889
different source 0.001137348
word align 0.001104365
such knowl 0.001085848
hindi decipherment 0.001075144
same distribution 0.001071786
such situations 0.001068921
correct decipherment 0.001067475
methods phonetic 0.001064047
decipherment error 0.001056307
substitution decipherment 0.0010462470000000001
language pairs 0.001037517
several decipherment 0.001030944
analysis problem 0.001005747
other languages 9.98138E-4
good language 9.88405E-4
same sentence 9.88385E-4
code decipherment 9.79394E-4
second decipherment 9.76292E-4
source character 9.71116E-4
decipherment problems 9.710560000000001E-4
natural language 9.70282E-4
same inventory 9.6839E-4
first results 9.644E-4
machine decipherment 9.6363E-4
other constraints 9.5305E-4
english words 9.43585E-4
same don 9.42812E-4
different problems 9.400070000000001E-4
language deci 9.388409999999999E-4
models 9.34036E-4
spanish words 9.318919999999999E-4
language mod 9.31295E-4
force decipherment 9.277910000000001E-4
language processing 9.257499999999999E-4
animal language 9.24626E-4
supervised methods 9.22291E-4
automatic decipherment 9.2102E-4
empirical results 9.175260000000001E-4
same thing 9.16225E-4
phonetic bigram 9.08879E-4
initial decipherment 9.0792E-4
source corpus 9.07729E-4
source languages 9.06034E-4
universal phonetic 9.01029E-4
test set 8.98627E-4
hindi words 8.929529999999999E-4
decipherment domains 8.895940000000001E-4
perfect decipherment 8.89239E-4
improved decipherment 8.89033E-4
other values 8.865570000000001E-4
proved decipherment 8.83428E-4
other problems 8.83361E-4
english letter 8.80294E-4
hindi character 8.77863E-4
supervised training 8.757999999999999E-4
phonetic sequences 8.743189999999999E-4
english training 8.668020000000001E-4
unsupervised methods 8.615960000000001E-4
many languages 8.578889999999999E-4
different standards 8.54052E-4
plaintext source 8.49692E-4
other lan 8.44593E-4
large source 8.41998E-4
small source 8.37788E-4
space character 8.345469999999999E-4
plaintext character 8.3221E-4
similar results 8.29142E-4
