lexical information 0.001678974
frequency words 0.001457712
similar word 0.00143011
word level 0.001314211
reliable information 0.001306725
automatic language 0.0012517000000000001
real word 0.001222987
word real 0.001222987
foreign words 0.001202765
language pairs 0.001180477
frequent words 0.001149431
word distributions 0.0011410370000000001
word positions 0.0011401480000000001
expected word 0.0011313200000000001
position word 0.0011220000000000002
word position 0.0011220000000000002
same time 0.001114917
language similarity 0.001113074
portuguese word 0.001112223
homograph word 0.001108491
homograph words 0.001105249
word posi 0.001098394
latin words 0.001096617
pected word 0.001094668
word patten 0.001094668
cognate words 0.00109179
same number 0.001084437
kernel language 0.00107069
other constraints 0.001068142
other lan 0.001067951
language corre 0.001056209
design language 0.001049808
other tries 0.0010412239999999999
similar distance 0.001035486
information 0.00102681
different translations 0.0010238530000000001
different alphabets 0.0010155820000000001
english text 0.001015005
small text 9.97547E-4
parallel corpus 9.93813E-4
chinese texts 9.8674E-4
human time 9.738349999999999E-4
term order 9.70125E-4
new candidate 9.54349E-4
parallel text 9.53862E-4
term translation 9.517799999999999E-4
automatic methods 9.32158E-4
average number 9.21619E-4
text alignment 9.20882E-4
full text 9.09311E-4
equal frequency 9.036840000000001E-4
same languages 8.9293E-4
confidence level 8.9219E-4
total number 8.91523E-4
same punctuation 8.89759E-4
frequency homographs 8.80869E-4
computational system 8.79875E-4
same form 8.7819E-4
independent method 8.77628E-4
average value 8.74561E-4
statistical approach 8.74299E-4
text segments 8.74269E-4
line confidence 8.691829999999999E-4
high precision 8.68134E-4
words 8.63366E-4
large text 8.616100000000001E-4
small texts 8.5884E-4
corpus con 8.58183E-4
text tagging 8.57292E-4
candidate correspondence 8.540069999999999E-4
same frequencies 8.52854E-4
sentence boundaries 8.52649E-4
text window 8.52358E-4
baf corpus 8.518239999999999E-4
specific term 8.507429999999999E-4
previous work 8.494539999999999E-4
english parallel 8.38599E-4
similar distributions 8.379310000000001E-4
similar positions 8.370420000000001E-4
analysis table 8.36687E-4
extraction task 8.3541E-4
first class 8.33215E-4
similar charac 8.30274E-4
way candidate 8.29599E-4
average ratio 8.295220000000001E-4
filter candidate 8.22595E-4
good candidate 8.22433E-4
language 8.21063E-4
parallel texts 8.15155E-4
sentence delimiters 8.14483E-4
correspondence points 8.1443E-4
term translations 8.13863E-4
portuguese text 8.10749E-4
alignment points 8.10194E-4
ambiguity level 8.04713E-4
similar forms 7.95421E-4
similar distri 7.94253E-4
text scope 7.94002E-4
regression line 7.85758E-4
texts alignment 7.82175E-4
