topic similarity 0.00373258
word similarity 0.0032717400000000004
latent topic 0.002920818
topic information 0.002919652
text similarity 0.0027621
topic segment 0.0027529769999999998
semantic similarity 0.00266294
coherent topic 0.0025677089999999996
specific topic 0.0025420729999999997
topic mixtures 0.0024855339999999997
text segmentation 0.0023594
different data 0.00224827
other similarity 0.002248129
topic 0.00221919
information similarity 0.002213852
word probabilities 0.002099277
word sequence 0.002080134
traditional word 0.002073404
similarity figure 0.0020498
word density 0.002033462
word repetitions 0.002031522
similarity representation 0.0019469980000000001
similarity score 0.001939561
similarity measure 0.0019310030000000001
similarity measures 0.001901792
semantic distribution 0.001898909
semantic information 0.001850012
cosine similarity 0.001832113
similarity curve 0.00180539
ent similarity 0.0018051550000000001
statistical similarity 0.001803785
similarity mea 0.001797205
density similarity 0.001788502
similarity eval 0.001785382
similarity part 0.001784791
similarity metrics 0.0017816140000000002
semantic topics 0.001779869
segmentation method 0.001761948
text structure 0.001699184
probability model 0.0016568389999999998
text seg 0.0016215830000000002
segmentation performance 0.0016057469999999998
semantic kernel 0.001588804
semantic cohesion 0.001578706
data sets 0.0015558290000000001
chinese data 0.001549573
independent text 0.001548927
similarity 0.00151339
data items 0.0015107240000000002
semantic similarities 0.00149972
segmentation task 0.0014927649999999998
lda model 0.0014282219999999998
segmentation points 0.001427476
optimal segmentation 0.001412621
different terms 0.00141105
segmentation tasks 0.0013923999999999998
such segments 0.001384831
reality words 0.001382791
probability distribution 0.001379308
complicated segmentation 0.0013758779999999999
different algorithms 0.001367105
latent topics 0.001331947
different sets 0.001326759
different samples 0.001283223
lexical cohesion 0.0012580669999999999
test corpus 0.001209644
length probability 0.001189037
dirichlet distribution 0.001149738
new method 0.001116519
words 0.00111647
segmentation 0.00111069
experimental results 0.001109689
latent dirichlet 0.0011020070000000001
coherent segments 0.001095804
segment length 0.001092875
segments selection 0.001072197
multinomial distribution 0.001061652
chinese corpus 0.001051453
information retrieval 0.001039756
model 0.00102689
individual results 0.001024791
empirical distribution 0.001020624
marginal distribution 0.00101681
related topics 0.001010729
other authors 0.001002092
imental results 9.8224E-4
news docu 9.79095E-4
exact information 9.692839999999999E-4
language modeling 9.68356E-4
generative probability 9.671689999999999E-4
texttiling method 9.580000000000001E-4
test set 9.50392E-4
similar way 9.475849999999999E-4
probability part 9.0135E-4
kernel function 9.0066E-4
lda framework 8.885060000000001E-4
previous block 8.88263E-4
score function 8.87577E-4
common term 8.81603E-4
similar vocabularies 8.80242E-4
