word alignment 0.00483935
phrase alignment 0.003471687
alignment algorithm 0.003394833
alignment size 0.003343312
segmentation alignment 0.003333694
level alignment 0.003255251
single alignment 0.003239708
alignment context 0.003171481
quent alignment 0.003069365
alignment components 0.003061996
alignment 0.00277721
english word 0.00262803
word level 0.002540181
typographic word 0.002397128
bilingual corpus 0.002233014
phrase translation 0.002219667
small corpus 0.002192963
parallel corpus 0.002177674
translation probabilities 0.002082913
btec corpus 0.002060913
monolingual corpus 0.002058506
europarl corpus 0.002051149
different language 0.002049886
corpus index 0.002047726
parliament corpus 0.002044839
japanese corpus 0.002013956
lel corpus 0.001980094
allel corpus 0.001979009
whole corpus 0.001978298
corpus cache 0.001975902
translation research 0.001949658
machine translation 0.001949238
language model 0.0018501099999999999
language pairs 0.0017471649999999997
corpus 0.00170353
translation 0.00152519
data structure 0.0014120040000000001
probability model 0.001397396
simple data 0.001387699
meaningful data 0.0013374720000000001
typographic words 0.0013317770000000001
english sentence 0.001281837
graphic words 0.0012795050000000002
individual words 0.0012793330000000001
same correlation 0.001270583
such languages 0.001217256
sentence level 0.001193988
language 0.00118722
different settings 0.001180855
phrase level 0.001172518
large corpora 0.001168443
statistical approach 0.001161169
different granularities 0.001146857
practical evaluation 0.00113464
multiple alignments 0.0011340690000000001
chinese sentence 0.001127906
such suffix 0.001125085
lexical dictionaries 0.001112439
many substrings 0.001109381
test set 0.001101239
linguistic knowledge 0.001094956
first suffix 0.00108666
unique english 0.001065582
same solution 0.001060274
index sentence 0.001060143
store phrase 0.0010533159999999999
french sentence 0.001051136
same qualities 0.001049363
same assump 0.001049363
parallel corpora 0.00104392
segmentation rules 0.001031392
opposite sentence 0.001021986
single segmentation 0.0010189819999999999
ment algorithm 0.001017174
joint probability 0.001015669
many algorithms 0.001013649
substrings pairs 0.001007769
words 9.96789E-4
thorough evaluation 9.96545E-4
sentence indexes 9.9107E-4
statistical machine 9.86823E-4
previous algorithm 9.84553E-4
other things 9.80696E-4
previous method 9.72137E-4
suffix array 9.66417E-4
own algorithm 9.64109E-4
many asians 9.63875E-4
correct alignments 9.53038E-4
future work 9.46411E-4
own approach 9.4488E-4
time complexity 9.419E-4
many possibilities 9.41365E-4
statistical processing 9.41019E-4
links precision 9.338780000000001E-4
good implementation 9.24882E-4
linking algorithm 9.24516E-4
english btec 9.232730000000001E-4
western languages 9.1876E-4
sentential alignments 9.13666E-4
efficient method 9.11146E-4
