word clustering 0.0018425009999999999
training data 0.001732559
language model 0.001525627
clustering algorithm 0.001510163
word pair 0.001473186
english data 0.001462828
clustering method 0.001417278
word alignments 0.001365675
model structure 0.001324127
stanford word 0.00130481
word seg 0.00130481
chinese data 0.0012882500000000001
gram model 0.0012725940000000002
samt model 0.001254302
japanese data 0.001213713
data sets 0.001212727
guage model 0.001203049
synchronous rules 0.001200849
times data 0.0012001940000000001
overall model 0.001199745
joint model 0.001199125
data lang 0.0011783990000000001
appropriate rules 0.001156508
new method 0.001119437
chronous rules 0.001104683
language models 0.00108728
initial clustering 0.001076329
exchange clustering 0.001071903
clustering speed 0.00107007
machine translation 0.0010544999999999999
clustering experiment 0.001015871
training development 9.976849999999999E-4
tive clustering 9.90572E-4
model 9.79042E-4
lang training 9.75628E-4
cluster number 9.72795E-4
rule number 9.69911E-4
translation samt 9.677659999999999E-4
clustering increase 9.631869999999999E-4
agglomerative clustering 9.58055E-4
vious clustering 9.571759999999999E-4
glomerative clustering 9.571759999999999E-4
translation tasks 9.308389999999999E-4
posterior probability 9.291309999999999E-4
test set 9.25978E-4
translation quality 9.11911E-4
side rule 9.1066E-4
chine translation 9.042799999999999E-4
translation perfor 9.01823E-4
baseline method 8.98292E-4
syntactic information 8.95915E-4
rules 8.90988E-4
large grammar 8.86627E-4
initialization method 8.79805E-4
tering method 8.79805E-4
large number 8.74249E-4
label set 8.68879E-4
phrase structure 8.673330000000001E-4
generative probability 8.6509E-4
linguistic information 8.60715E-4
label rule 8.56853E-4
ing criterion 8.532609999999999E-4
initial cluster 8.490469999999999E-4
exchanges words 8.35176E-4
rule probabilities 8.27994E-4
synchronous rule 8.274459999999999E-4
ccg samt 8.1883E-4
samt models 8.159549999999999E-4
first summation 7.949859999999999E-4
previous work 7.825379999999999E-4
equivalence cluster 7.730669999999999E-4
training 7.64894E-4
cluster mapping 7.64024E-4
algorithm 7.62412E-4
tuning set 7.557940000000001E-4
clustering 7.47751E-4
grammar size 7.43792E-4
samt grammar 7.39964E-4
probabilistic distributions 7.354460000000001E-4
computation time 7.34759E-4
statistical machine 7.34228E-4
english tasks 7.334959999999999E-4
side label 7.32343E-4
rule inr 7.27294E-4
ing speeds 7.264589999999999E-4
new objective 7.20862E-4
syntactical information 7.206879999999999E-4
tactic information 7.18266E-4
target side 7.15544E-4
second summation 7.154349999999999E-4
syntactic labels 7.13637E-4
categorial grammar 7.128E-4
english references 7.1046E-4
objective function 7.05286E-4
time complexity 7.03011E-4
syntactic cor 6.93204E-4
translation 6.92506E-4
free grammar 6.89912E-4
label distributions 6.871E-4
fixed number 6.84675E-4
