corpus error 0.003231906
same error 0.002954542
error type 0.002935902
error analysis 0.002712768
order error 0.002679874
single error 0.0026653700000000002
error types 0.002654091
choice error 0.002610224
misspelling error 0.0025635280000000002
idiom error 0.002562192
different data 0.0023751700000000002
error 0.00232152
training correction 0.002299392
correction detection 0.002218764
word set 0.002217351
same word 0.002216872
same correction 0.002203782
correction systems 0.002183476
common correction 0.001977048
original word 0.0019560099999999998
word order 0.001942204
single word 0.0019276999999999999
current correction 0.00189812
incorrect word 0.0018950969999999999
word choice 0.0018725539999999998
feature set 0.001848401
combined correction 0.0018465
word substitution 0.001846237
correction patterns 0.001841093
correction mis 0.001832415
word insertions 0.001831844
ror correction 0.001828991
word deletions 0.0018254929999999999
word substi 0.0018254929999999999
correction fixes 0.001811551
merging errors 0.001795207
different problem 0.0017235190000000002
model training 0.001664071
training corpus 0.001639018
different writing 0.001598124
correction 0.00157076
single data 0.0015632999999999999
different cor 0.0015534260000000001
system accuracy 0.001547776
same corpus 0.001543408
current feature 0.0015422600000000002
corpus sentences 0.001533565
annotated data 0.001527483
different corpora 0.001516389
system performance 0.0015065240000000002
ideal data 0.001486441
different esl 0.001477679
data resource 0.0014733799999999998
data collection 0.00146413
original words 0.00146286
data collections 0.00146079
different annotation 0.001446224
different guidelines 0.001444108
overall system 0.0014169970000000001
different sources 0.001413255
different problems 0.0014111500000000001
errors 0.00141007
language learning 0.0013898629999999999
tection system 0.001354774
educational system 0.0013514960000000002
revised words 0.001339418
tween words 0.00133563
merging model 0.001320576
phrase pairs 0.001298329
language tutors 0.001249317
sentences sentences 0.001246358
other edits 0.001246085
phrase pair 0.001221862
phrase extraction 0.001218268
feature 0.0012149
corpus size 0.001214037
same problem 0.001200821
other component 0.00118865
fce corpus 0.001169825
cle corpus 0.001151966
tracted phrase 0.001147732
other hand 0.001141152
same pos 0.001125459
detection models 0.001114858
system 0.00111018
original sentence 0.00109642
english experts 0.001092607
words 0.0010907
same writing 0.001075426
previous systems 0.001048831
example sentence 0.001032477
wrong set 0.0010309919999999999
same cor 0.001030728
features 0.00102384
training instances 0.001012418
tion detection 0.0010103389999999999
writing problem 0.0010102029999999999
language 0.00100786
training dataset 0.0010001300000000001
original sentences 9.95339E-4
