word segmentation 0.005946667
input word 0.005601391
output word 0.00555868
word types 0.005510581
word boundary 0.005482604
word order 0.005472542
phonotactic word 0.005467139
word learner 0.005461646
real word 0.005433746
novel word 0.005426788
word segmenta 0.005415497
word segmen 0.005392036
word boundaries 0.005390684
word edges 0.005385259
true word 0.0053832080000000004
freestanding word 0.005377293
posited word 0.005377293
infant word 0.005377293
word beginnings 0.005377293
segmentation model 0.002259797
input words 0.002213071
segmented words 0.002082067
learning model 0.002041556
potential words 0.0020311360000000002
quent words 0.001996493
lexical model 0.00186894
baseline model 0.001784763
model baseline 0.001784763
phonotactic model 0.001780269
words 0.00175512
cognitive model 0.001730403
dibs model 0.001706679
phrasal model 0.0017028879999999998
egmentation model 0.001690563
test corpus 0.0016388409999999998
lexical models 0.0014647
model 0.00145657
text corpus 0.001382162
phonotactic models 0.001376029
diphone models 0.0013615329999999998
computational models 0.001317988
raw corpus 0.0013089249999999998
dibs models 0.0013024389999999999
segmentation error 0.001298735
phrasal models 0.001298648
phonetic corpus 0.001268687
high segmentation 0.001206349
segmentation algorithm 0.0011944479999999999
phonotactic segmentation 0.0011269259999999999
type segmentation 0.001122273
token segmentation 0.001086813
segmentation algorithms 0.001085616
tic segmentation 0.001074853
such example 0.001063117
optimal segmentation 0.001057691
models 0.00105233
successful segmentation 0.001044241
test case 0.0010061179999999999
corpus 0.0010041
challenging language 9.93656E-4
other classes 9.50492E-4
interesting test 9.453269999999999E-4
other examples 9.289330000000001E-4
high error 8.9863E-4
test sample 8.91262E-4
test corpora 8.878919999999999E-4
unsupervised learning 8.68898E-4
english diphones 8.64487E-4
frequent phrase 8.63373E-4
error analysis 8.573529999999999E-4
computational learning 8.50644E-4
high frequency 8.49096E-4
frequent input 8.42956E-4
many fre 8.37162E-4
error rate 8.35098E-4
learning algo 8.19528E-4
mentation error 8.07349E-4
segmentation 8.03227E-4
frequent output 8.00245E-4
previous languages 7.86206E-4
tion error 7.748709999999999E-4
lexical approaches 7.70704E-4
limited set 7.69844E-4
error rates 7.68665E-4
language 7.51317E-4
input projection 7.49669E-4
morphological analysis 7.41458E-4
minimal sequence 7.3866E-4
sequence indi 7.3866E-4
phonological rules 7.31745E-4
undersegmentation error 7.3158E-4
previous studies 7.30109E-4
phrase edges 7.20187E-4
rean speech 7.18178E-4
phrase breaks 7.15067E-4
notactic approach 7.12269E-4
various properties 7.12049E-4
lexical processing 7.0953E-4
output projection 7.069579999999999E-4
child input 7.04221E-4
