topic model 0.00402732
topic distribution 0.003826195
text topic 0.00360136
topic models 0.003439538
topic number 0.003347077
topic inference 0.003311621
topic space 0.003276395
topic analysis 0.0032437110000000003
topic distribu 0.0031602080000000003
various topic 0.0031392580000000002
topic distri 0.0031315790000000002
classic topic 0.003108674
topic consistence 0.003108674
topic zek 0.003108674
topic 0.00291478
word distribution 0.002622755
word distributions 0.002123357
same topics 0.001994317
word distri 0.001928139
other words 0.0019209519999999999
word wei 0.00190693
word respec 0.001905567
new words 0.0018097439999999998
external words 0.001792175
additional words 0.001771875
many words 0.0017317329999999998
known topics 0.001706749
lda model 0.001657251
relevant words 0.001645978
stop words 0.0015913869999999999
rare words 0.001589547
added words 0.001584461
noisy words 0.0015830549999999999
abstract words 0.0015826929999999998
vant words 0.001579744
topics 0.00147205
analysis model 0.001441471
words 0.0013857
based model 0.001338426
novel model 0.0013182979999999999
mization model 0.001308826
our model 0.001307489
different number 0.001246603
new data 0.001230689
model 0.00111254
additional information 0.001077119
other corpus 0.0010710339999999998
text classification 0.001034975
data sparseness 0.0010212020000000001
such ability 0.0010135460000000002
common text 0.00101332
different rep 0.001010811
structure information 0.001003838
other methods 9.8157E-4
short text 9.62993E-4
text representation 9.627699999999999E-4
external corpus 9.42257E-4
tional information 9.34006E-4
distribution 9.11415E-4
traditional text 9.0991E-4
news corpus 8.99296E-4
text clustering 8.94875E-4
limited information 8.85998E-4
mentary information 8.85998E-4
information abundance 8.85998E-4
news documents 8.85225E-4
text represen 8.84595E-4
original lda 8.53888E-4
average accuracy 8.146399999999999E-4
document gener 8.10089E-4
document dej 8.091169999999999E-4
semantic analysis 7.99386E-4
term frequency 7.9694E-4
classification methods 7.947130000000001E-4
many methods 7.92351E-4
microblog number 7.7921E-4
other case 7.77935E-4
high level 7.770710000000001E-4
lda estimation 7.764E-4
classification accuracy 7.69675E-4
lda optimization 7.64804E-4
classification results 7.465740000000001E-4
lda esti 7.40696E-4
ning lda 7.39136E-4
other cases 7.36476E-4
other hand 7.332879999999999E-4
proper time 7.30227E-4
same role 7.20237E-4
same condition 7.17072E-4
inference problem 7.14988E-4
representation vector 7.13622E-4
external knowledge 7.11719E-4
relevant methods 7.065960000000001E-4
latent space 7.059220000000001E-4
microblog classification 6.95308E-4
information 6.90944E-4
line methods 6.75603E-4
results representation 6.74369E-4
traditional methods 6.69648E-4
gibbs sampling 6.66692E-4
