word context 0.005436959
word alignment 0.005371733
training word 0.0053637649999999995
semantic word 0.005111963
learning word 0.005107884
source word 0.004947661
word similarity 0.00494306
target word 0.004908086999999999
word input 0.004896047
input word 0.004896047
null word 0.00481047
word types 0.004809822
word frequency 0.0048019889999999996
word type 0.004801657
word tokens 0.004795278
word classes 0.004780416
good word 0.004778526999999999
word alignments 0.004746591
word align 0.00474581
arbitrary word 0.004719004
word simi 0.004717745
word sim 0.004716245
word eai 0.004716209999999999
word fertility 0.004715278
context words 0.0028808790000000003
context model 0.002709609
language model 0.002687987
alignment model 0.002644383
probability model 0.0025300599999999998
target words 0.002352007
lexical words 0.002313452
similar words 0.002288258
frequency words 0.002245909
frequent words 0.0022441510000000002
similarity model 0.00221571
model parameters 0.00220269
rare words 0.002176859
content words 0.0021599550000000003
lar words 0.0021599550000000003
ilar words 0.0021599550000000003
interchangeable words 0.0021599550000000003
quency words 0.0021599550000000003
model figure 0.0020908660000000003
our model 0.002079589
ibm model 0.002052781
model contexts 0.002050755
model precision 0.002023472
mixture model 0.002016733
ity model 0.002003362
model variants 0.001990598
larity model 0.001989741
ilarity model 0.001987897
words 0.0019331
alignment models 0.0019157330000000002
translation models 0.001886291
model 0.00176183
training data 0.001541326
different data 0.001528292
training algorithm 0.0015001580000000001
similarity models 0.0014870600000000001
english translation 0.001436092
test data 0.0014093489999999998
context probabilities 0.001363825
simple training 0.001354347
vocabulary models 0.001353397
ibm models 0.001324131
related models 0.001314749
base models 0.0012993590000000001
language pairs 0.001272012
ing translation 0.0012557520000000002
alignment tasks 0.0012451089999999999
lexical translation 0.001233463
semantic approach 0.001222961
machine translation 0.001215749
translation tasks 0.0012156670000000001
context prob 0.001212144
alignment experiments 0.001196672
natural language 0.001195445
alignment links 0.001184067
alignment quality 0.0011838109999999999
language processing 0.001170719
translation experiments 0.00116723
syntactic features 0.001163962
translation quality 0.0011543690000000001
ural language 0.001152372
unrelated language 0.001152372
translation rules 0.00113988
alignment problems 0.001138813
bleu test 0.001134428
source sentence 0.001134001
translation systems 0.0011165110000000002
cient training 0.001101107
training samples 0.001101107
native training 0.001101107
target sentence 0.001094427
different subsets 0.0010887100000000001
translation proba 0.001088026
translation sys 0.001085989
chine translation 0.001081197
gigaword corpus 0.001074545
