context words 0.00313775
target words 0.002366441
text words 0.002278379
source word 0.002249027
words table 0.002247962
word sense 0.002167508
translation candidate 0.002156069
other words 0.002140091
context vector 0.002126475
word alignment 0.002107715
word distribution 0.002104799
significant words 0.002045144
specific words 0.002035733
source context 0.001987547
relevant words 0.001973451
compound words 0.001964014
words ambiguities 0.001945005
words otero 0.001937902
words fung 0.001937902
words ismail 0.001937902
words morin 0.001937902
words chiao 0.001937902
context vectors 0.001904478
lexical context 0.001876704
english language 0.001813967
parallel corpus 0.0018057529999999998
language dictionary 0.0017440710000000002
target language 0.0017338610000000002
translation 0.00171998
computing context 0.001718986
words 0.00169701
context vec 0.001696908
context distributions 0.001692452
historical context 0.001685977
comparable corpus 0.00168358
transfer context 0.001681019
language pairs 0.00164335
bilingual corpora 0.0016155459999999998
different translations 0.001585817
bilingual lexicon 0.001565091
large corpus 0.001532893
small corpus 0.001508194
parallel corpora 0.001494113
bilingual dictionary 0.001484017
corpus sizes 0.0014560369999999999
context 0.00144074
general language 0.0014327230000000001
training corpus 0.0013767889999999998
comparable corpora 0.0013719399999999999
different languages 0.001349915
projection method 0.001304006
jection method 0.001293261
linear model 0.001284995
lexicon extraction 0.001281346
text vector 0.001267104
different regression 0.001266507
regression model 0.001244218
different heuristics 0.001238061
size corpora 0.001236888
source vector 0.001232542
different experiments 0.001192654
first target 0.001173784
target terms 0.001168493
standard approach 0.001157656
several translations 0.001143324
bilingual lexicons 0.001140339
candidate translations 0.00113974
target languages 0.00113718
target vectors 0.0011331689999999998
corpus 0.00112281
candidate vector 0.001121824
gual corpora 0.001117959
prediction model 0.00111717
sion model 0.001105787
target candidate 0.00110552
gression model 0.001104493
domain terms 0.001102854
bilingual lex 0.00108622
target texts 0.001076599
domain languages 0.001071541
tual information 0.001068803
bilingual dictio 0.001065978
training corpora 0.001065149
language 0.00106443
balanced corpora 0.001056661
corpora com 0.001055954
parable corpora 0.001055039
vector distance 0.00105483
bilingual terminology 0.001048013
bilingual lexi 0.001047908
method 0.00103689
similarity score 0.001009281
lexicon extrac 0.00100629
association measure 9.93823E-4
text analysis 9.91905E-4
vector element 9.82705E-4
main work 9.78662E-4
input vector 9.758950000000001E-4
general domain 9.72085E-4
similarity measures 9.66017E-4
