topic distribution 0.00490231
topic model 0.004717546
topic models 0.004366014
lda topic 0.004246415
topic terms 0.004176403
standard topic 0.004170806
topic label 0.004115704
previous topic 0.004113725
topic labels 0.0040860720000000005
latent topic 0.004080781
topic labelling 0.00405448
overall topic 0.004038648
ranking topic 0.004036341
twitter topic 0.004025855
automatic topic 0.004015204
topic pair 0.0040133700000000005
topic pairs 0.004002666
candidate topic 0.004001903
select topic 0.003999464
prominent topic 0.003989978
topic modelling 0.003988232
topic 0.00376004
word distribution 0.00301996
word distributions 0.002307725
word probabilities 0.002196157
word dis 0.00218972
weighted word 0.002140268
initial word 0.002134494
word distri 0.002116199
word frequencies 0.002111434
stop word 0.002098608
word removal 0.002089624
such topics 0.001964744
lda topics 0.001770965
latent topics 0.001605331
labelling topics 0.00157903
meaningful topics 0.001567108
twitter topics 0.001550405
external data 0.001486824
data sources 0.001466004
top words 0.001460172
media data 0.001433991
data source 0.0014278000000000001
data sparseness 0.0013522550000000001
structured data 0.0013522550000000001
unique words 0.001325954
frequent words 0.0013035520000000001
ofnd words 0.0012985170000000001
stop words 0.0012979880000000001
topics 0.00128459
different terms 0.0012628000000000001
model variables 0.001252615
different summarisation 0.001197315
distribution 0.00114227
different ranking 0.001122738
different categories 0.0011113030000000001
words 0.00107707
different challenges 0.001073213
different well 0.001059384
mutual information 0.001057281
document collection 0.001002602
global information 9.95473E-4
document frequency 9.727029999999999E-4
model 9.57506E-4
relevant information 9.44243E-4
document categorisation 9.34266E-4
weighted document 9.318239999999999E-4
such docu 9.15514E-4
good label 9.10336E-4
same period 9.003500000000001E-4
semantic content 8.90848E-4
same preprocessing 8.86932E-4
good labels 8.80704E-4
lda top 8.69477E-4
same procedure 8.65162E-4
similarity approach 8.62264E-4
same range 8.51426E-4
average probability 8.49912E-4
news corpus 8.36521E-4
human evaluation 8.27302E-4
semantic concept 8.25997E-4
latent dirichlet 8.186280000000001E-4
posterior inference 8.11035E-4
corpus size 8.103559999999999E-4
twitter corpus 8.004069999999999E-4
top terms 7.994650000000001E-4
reference corpus 7.915159999999999E-4
relevant documents 7.86152E-4
average results 7.860040000000001E-4
marginal probability 7.70164E-4
good indi 7.69512E-4
standard evaluation 7.68887E-4
standard label 7.6643E-4
previous work 7.6377E-4
mariser method 7.472760000000001E-4
dirichlet allocation 7.421070000000001E-4
summarisation task 7.37563E-4
terms baseline 7.362849999999999E-4
lexical features 7.34546E-4
semantic coher 7.33153E-4
