word alignment 0.00691838
bilingual word 0.00556473
word collocation 0.005509512
word pairs 0.005459314
language word 0.005397572
monolingual word 0.005272543
chinese word 0.00520499
word alignments 0.005184691
statistical word 0.005136847
source word 0.005118813
word pair 0.005094545
target word 0.005018593
lingual word 0.004936934
word align 0.004897044
word sequence 0.004893885
gual word 0.004873643
consecutive word 0.004863364
guage word 0.004844183
interrupted word 0.004842375
word iaw 0.004842375
alignment method 0.00371217
alignment model 0.0035716100000000002
alignment probability 0.003144713
alignment set 0.003120537
precision alignment 0.003094446
alignment results 0.0030171110000000003
alignment algorithm 0.002869897
alignment probabilities 0.002828881
alignment frequency 0.0028118830000000003
alignment sequence 0.002770605
alignment ing 0.002732843
refined alignment 0.002731566
alignment algo 0.00271987
alignment probabili 0.0027188810000000002
alignment 0.00239755
english translation 0.0023522300000000003
words pairs 0.002318974
corpus corpus 0.00223466
bilingual sentence 0.00220435
english sentence 0.0021644200000000002
bilingual corpus 0.00216123
english corpus 0.0021213
chinese words 0.00206465
english collocation 0.001992652
other words 0.001962662
monolingual sentence 0.001912163
monolingual corpus 0.001869043
chinese sentence 0.00184461
words col 0.001828208
training corpus 0.001824161
baseline method 0.0018181820000000002
method baseline 0.0018181820000000002
chinese corpus 0.0018014899999999998
collocation probability 0.0017358450000000002
sentence pair 0.001734165
our method 0.001731327
ment method 0.001720924
mwa method 0.001716099
machine translation 0.0017151760000000001
adjacent words 0.00170288
collocated words 0.00170288
chinese collocations 0.00169923
sentence figure 0.001676351
line method 0.0016452060000000002
improved method 0.001640603
ranking method 0.001638717
proved method 0.0016374660000000002
corpus size 0.0016218819999999998
ibm model 0.001598353
same language 0.001588522
parallel corpus 0.0015872009999999999
mwa model 0.001575539
english corpora 0.001548784
corpus our 0.0015340369999999998
lingual corpus 0.001533434
collocations baseline 0.0015186320000000002
training data 0.001512687
news corpus 0.001497235
probability probability 0.001494326
gual corpus 0.001470143
error collocations 0.001466392
other language 0.001458914
position collocation 0.001458239
collocation dictionaries 0.001455476
top collocations 0.001452132
collocation extraction 0.001441236
whole corpus 0.001439873
collocation candidates 0.001436138
english sentences 0.001435164
different methods 0.001404073
reliable collocations 0.001387755
span collocations 0.0013873050000000001
true collocations 0.001384838
scores collocation 0.001382765
words 0.00138049
target language 0.001374505
collocation construction 0.001368188
false collocations 0.00136206
bigram collocations 0.0013499100000000002
different association 0.001348524
