translation model 0.00296889
model models 0.002662112
language model 0.0025526529999999998
translation models 0.002250722
problem word 0.002186483
solution word 0.002167813
model learning 0.002130608
word source 0.002120153
word pairs 0.002101021
tion model 0.002051045
generative model 0.002033166
ibm model 0.002001678
first word 0.001994905
model correlation 0.001981166
cluster model 0.001961453
model respective 0.001938071
other features 0.001933793
guage model 0.001928162
erative model 0.001923534
language models 0.0018344849999999998
such features 0.0018250609999999998
problem words 0.001818453
solution words 0.0017997830000000001
second word 0.001774127
reply word 0.001751694
word regularization 0.001746105
fractional word 0.001737825
lem word 0.001699745
word level 0.001695985
word frequen 0.001693206
model 0.00169014
word suggestions 0.001685959
proactive word 0.001685959
solution models 0.001683735
only translation 0.00157768
complex translation 0.001575945
position translation 0.0015341909999999999
translation mod 0.001522928
ularized translation 0.001508576
training data 0.001468461
tion words 0.0014489250000000002
problem solution 0.001442196
based features 0.001432416
post data 0.0014322850000000002
textual features 0.0014206219999999999
structural features 0.001414283
learning models 0.00141244
various features 0.0013993209999999998
reply words 0.0013836640000000002
certain features 0.001381827
top words 0.001369736
generic words 0.0013684390000000002
unique words 0.0013669420000000001
approach data 0.001361003
solution pairs 0.001356734
tion models 0.001332877
perative words 0.001319337
statistical models 0.001317797
based feature 0.001280836
translation 0.00127875
problem post 0.0012730369999999999
textual feature 0.001269042
alignment vector 0.001266315
structural feature 0.001262703
feature space 0.00125619
solution post 0.0012543670000000002
appropriate feature 0.001226927
lation models 0.001226261
other posts 0.001221807
guage models 0.001209994
data size 0.001204002
analogous models 0.001201554
centroids models 0.001201554
clustering data 0.001189168
post pairs 0.0011875750000000002
tive language 0.001175838
learning problem 0.001170901
data points 0.001164574
only language 0.0011614429999999999
forum data 0.001160174
example alignment 0.001153919
problem posts 0.001151077
alignment vectors 0.001147696
ditional data 0.001138102
identification problem 0.001133537
varying data 0.001132959
features 0.00113263
solution posts 0.001132407
method unsupervised 0.001130651
unsupervised method 0.001130651
problem author 0.0011275599999999999
data drops 0.001123212
such assumptions 0.0011172
solution identification 0.001114867
such posts 0.001113075
solution author 0.00110889
language mod 0.001106691
unsupervised solution 0.001106645
solution parts 0.001105633
unigram language 0.001097176
