language word 0.00414005
cognate word 0.003445597
word list 0.0032257680000000004
word alignment 0.0029924220000000002
target word 0.002970141
word pairs 0.0029518
source word 0.00291163
word lists 0.002881935
input word 0.00286381
correct word 0.00284159
word level 0.002837926
word boundary 0.002825929
plain word 0.002812629
cognate words 0.002540227
other words 0.002413481
target language 0.001936851
whole words 0.001934569
unknown words 0.00193435
known words 0.0019287599999999998
source language 0.00187834
language file 0.0018336000000000001
language unigrams 0.001814709
language portability 0.00178111
training data 0.001768583
words 0.0016813
different languages 0.001672897
language 0.00155338
cognate list 0.001498025
possible translation 0.001493011
model 0.00148124
algorithm figure 0.001429063
cognate distance 0.001378261
different edit 0.001357577
learning approach 0.0013317770000000001
translation rules 0.001326975
different features 0.00131931
machine translation 0.001316006
much data 0.00128388
data file 0.001264885
translation lexicons 0.001264741
data the 0.001260146
whole data 0.001237934
different machine 0.001232221
cognate pairs 0.001224057
initial list 0.001223233
translation studies 0.001193432
cognate pair 0.001192848
other features 0.001167329
possible list 0.001164162
same feature 0.001161612
cognate lists 0.001154192
cognate recognition 0.001153913
cognate detection 0.001151023
different environment 0.00114078
cognate file 0.001139147
different perspective 0.001133255
different scenarios 0.001117563
cognate generation 0.001117266
cognate creation 0.001114458
different entry 0.001111344
algorithm design 0.001109261
probable cognate 0.001104754
generation algorithm 0.0011037500000000001
creation algorithm 0.001100942
training purposes 0.001100202
cognate prediction 0.00110004
cognate production 0.001090631
training entries 0.001080654
algorithm merges 0.001071296
input languages 0.001065875
training file 0.001064138
same way 0.001053557
learning step 0.001040901
third languages 0.001039407
same problem 0.001026817
same alphabet 0.001012929
formatted training 0.001007881
original list 0.001007769
edit distance 9.92749E-4
flexible approach 9.87396E-4
proposed approach 9.80872E-4
renowned approach 9.78173E-4
learning parameters 9.71144E-4
small context 9.70313E-4
translation 9.67947E-4
pairs figure 9.48782E-4
necessary information 9.40569E-4
phonetic similarity 9.33351E-4
learning machine 9.28286E-4
machine learning 9.28286E-4
levenshtein distance 9.220529999999999E-4
such cases 9.07193E-4
first time 9.03179E-4
probability scores 8.9719E-4
possible cognates 8.91732E-4
learning module 8.59899E-4
learning classifiers 8.595300000000001E-4
cognate 8.58927E-4
algorithm 8.45411E-4
large corpora 8.43253E-4
