lexical features 0.002676317
such features 0.002377677
first word 0.002355819
syntactic features 0.002280766
last word 0.002266912
next word 0.002253044
word subject 0.002248794
certain word 0.002227981
single word 0.002196483
word boundary 0.002174336
structure features 0.002154441
word position 0.002139702
tain word 0.002106341
word posi 0.002104277
available features 0.002024556
unlexicalized features 0.002016104
collocational features 0.002016104
baseline feature 0.001884148
feature selection 0.0018676510000000001
features 0.00180894
content words 0.001778277
last words 0.001771672
next words 0.001757804
feature combinations 0.001745326
present words 0.001654926
relevant words 0.0016196239999999998
feature 0.00148657
ing text 0.001463376
english text 0.0014593879999999998
data set 0.001399494
words 0.00139837
size text 0.001397127
text typeset 0.001362943
typeset text 0.001362943
training data 0.001332716
text frag 0.001313384
anticipated text 0.001313384
test set 0.001278901
second language 0.001211074
secondary language 0.001146903
language learners 0.001134457
foreign language 0.001131741
motivated information 0.00109361
our data 9.98307E-4
error analysis 9.767830000000002E-4
velopment data 9.69724E-4
new texts 9.66873E-4
other hand 9.47101E-4
other ways 9.437289999999999E-4
next sentence 9.42916E-4
basic algorithm 9.31435E-4
different documents 9.23296E-4
language 9.17827E-4
actual error 9.16058E-4
baseline system 8.89951E-4
other sources 8.8652E-4
single sentence 8.863549999999999E-4
atomic test 8.70869E-4
other things 8.694519999999999E-4
extensive set 8.67864E-4
modest set 8.65493E-4
breaking algorithm 8.645980000000001E-4
programming algorithm 8.6156E-4
information 8.54446E-4
rule set 8.5251E-4
genetic algorithm 8.413650000000001E-4
classification problem 8.3784E-4
pos tag 8.301790000000001E-4
baseline break 8.159700000000001E-4
netic algorithm 8.08794E-4
system maximum 8.06628E-4
such cases 8.05736E-4
semantic integrity 8.01922E-4
vious sentence 7.950429999999999E-4
such unbreak 7.770230000000001E-4
future work 7.74111E-4
linguistic techniques 7.58321E-4
break classifiers 7.54224E-4
anticipation errors 7.5383E-4
break classifier 7.368850000000001E-4
next line 7.34245E-4
breaking problem 7.27575E-4
incorrect break 7.263720000000001E-4
prior work 7.238259999999999E-4
single break 7.21265E-4
simple application 7.18881E-4
overall paragraph 7.17657E-4
baseline classifier 7.16071E-4
complicated texts 7.13394E-4
ample work 7.10156E-4
certain number 7.036309999999999E-4
content breaks 6.98217E-4
current evaluation 6.97162E-4
entropy classifier 6.970710000000001E-4
subject phrase 6.95385E-4
correct breaks 6.936659999999999E-4
actual break 6.9308E-4
maximum entropy 6.92833E-4
syntactic integrity 6.86332E-4
break point 6.74507E-4
