segmentation algorithm 0.00386068
text segmentation 0.003573926
other segmentation 0.003570714
human segmentation 0.003510231
unsupervised segmentation 0.003421319
segmentation analysis 0.003398448
lecture segmentation 0.0033479119999999998
new segmentation 0.003238189
segmentation performance 0.003201494
segmentation statistics 0.003162019
common segmentation 0.003153586
segmentation study 0.003125265
segmentation task 0.00312374
segmentation accuracy 0.0031218089999999997
segmentation datasets 0.00310778
accurate segmentation 0.003107521
segmentation algorithms 0.003093056
segmentation studies 0.003077828
segmentation collections 0.0030684469999999998
annotator segmentation 0.0030647409999999997
ture segmentation 0.00306014
segmentation granularity 0.003057457
timal segmentation 0.003053989
trivial segmentation 0.003053989
segmentation granularities 0.003053989
segmentation 0.0027914
lexical distribution 0.002227714
other words 0.001971244
topic changes 0.001917735
sentence similarity 0.001903257
other model 0.001878434
signal topic 0.001833363
topic transitions 0.001827138
high word 0.001785758
same words 0.001748669
word error 0.001738805
word block 0.001715864
word asr 0.001699622
other segments 0.001693933
different segments 0.001649429
total word 0.001635406
lexical distribu 0.001634661
optimal word 0.001630598
lexical transitions 0.001620748
lexical weighting 0.001612255
word distributions 0.0016004090000000001
word counts 0.00159931
word repeti 0.001591224
lexical weights 0.0015806779999999999
lexical distri 0.001563445
lexical dependen 0.001558578
topic 0.00149916
stop words 0.001462115
programming algorithm 0.0014551549999999999
similarity function 0.001453343
segment length 0.001452859
model parameters 0.001448848
average segment 0.0014277159999999999
lecture data 0.001405509
lecture corpus 0.001387393
similarity scores 0.001384217
different topics 0.001349762
ming algorithm 0.001340511
low similarity 0.001340153
first segment 0.001337008
cosine similarity 0.00132777
segment boundaries 0.001324924
text structure 0.0013082369999999999
pairwise similarity 0.001296954
first corpus 0.001288147
coherent segments 0.001282152
current sentence 0.001275867
similarity metric 0.001274593
sentence feature 0.001269963
similarity computation 0.001267491
similarity density 0.001267175
sentence boundary 0.001265273
similarity plot 0.001263827
account similarity 0.001262999
text blocks 0.001256979
various corpus 0.001250829
similarity relationships 0.001238145
sentence vectors 0.001225331
standard text 0.001218174
wise sentence 0.001207991
corpus statistics 0.0012014999999999999
random text 0.0011996659999999998
sentence similarities 0.001197773
real data 0.001193866
words 0.00119193
true segment 0.001164502
mean segment 0.0011570999999999999
typical segment 0.001156818
long text 0.0011415169999999999
reference text 0.001141482
human performance 0.001128925
synthetic corpus 0.0011198900000000001
language processing 0.001118118
corpus lectures 0.00110722
natural language 0.001104011
