word segmentation 0.0040322399999999994
different word 0.00394428
standard word 0.0035393229999999996
language model 0.00343759
context word 0.003385782
word boundary 0.003336573
first model 0.003333921
word learning 0.0033132839999999997
form word 0.0032954599999999996
unigram model 0.003291816
bayesian word 0.0032913499999999997
previous word 0.0032767129999999997
learning model 0.003275054
new word 0.0032678819999999997
model scores 0.003255562
bigram model 0.003253808
bayesian model 0.00325312
word forms 0.003250674
transducer model 0.003248136
unknown word 0.003243686
word strings 0.0032320499999999998
source model 0.003216343
ing word 0.0032116799999999997
initial model 0.003200123
joint model 0.003183692
word tokens 0.003176081
intended word 0.00317186
real word 0.0031661249999999997
word type 0.003160109
full model 0.003158072
word segmentations 0.0031401209999999996
word boundaries 0.003137333
word sequences 0.003125411
own model 0.003118867
word seg 0.00311681
word segmen 0.003106148
next word 0.0031054809999999998
ggj model 0.003100006
word recognition 0.0030937259999999998
explicit model 0.003092536
markov model 0.0030923
known word 0.0030897769999999997
word segmenta 0.0030886589999999997
current word 0.003087511
pipelined model 0.003086649
sample word 0.003086587
gram model 0.003083222
word maps 0.0030807589999999998
graphical model 0.003080709
channel model 0.003079034
adjacent word 0.003074846
content word 0.0030733479999999996
word meanings 0.0030725839999999997
coverage model 0.003056328
tation model 0.003044405
pipeline model 0.003044124
noise model 0.003042714
tegrated model 0.003034631
cognitive model 0.003034631
ducer model 0.003034631
model 0.00279079
function words 0.002004645
words probabilities 0.001970214
single words 0.0019440500000000001
unknown words 0.001931196
possible words 0.001892009
frequent words 0.0018611090000000001
segmented words 0.0018374230000000001
ambiguous words 0.0018279770000000002
plausible words 0.0017808190000000001
known words 0.0017772870000000002
same segmentation 0.0017726310000000002
segmentation error 0.0017469410000000001
segmentation performance 0.00173071
segmentation scores 0.001667992
segmentation errors 0.001651133
segmentation problem 0.001615264
high segmentation 0.00157777
segmentation accuracy 0.001553288
similar segmentation 0.001530929
segmentation tasks 0.0015267240000000001
words 0.00151653
mean segmentation 0.001506483
overall segmentation 0.0014956090000000002
segmentation literature 0.001472365
tween segmentation 0.001453267
segmentation mistakes 0.001446912
tory segmentation 0.001446912
different segments 0.001446688
character sequence 0.001427243
test data 0.001421592
speech corpus 0.001411239
different ways 0.001371985
different sur 0.001365444
different talker 0.001360321
different tone 0.001360321
unigram distribution 0.00134359
lexical context 0.001294793
surface character 0.001291207
null character 0.0012878730000000001
