first corpus 0.002082709
other words 0.001966757
newspaper corpus 0.0018607289999999998
english corpus 0.001845635
test corpus 0.001803047
multiple word 0.0017831790000000002
current word 0.00176467
training corpus 0.001671445
initial corpus 0.001607888
corpus type 0.0015965379999999998
little corpus 0.001581807
original corpus 0.001570459
corpora corpora 0.001559646
mogeneous corpus 0.001541499
words table 0.001440654
different experiments 0.001431669
words literature 0.00138889
syntactic information 0.001381588
newspaper corpora 0.001360262
english corpora 0.0013451679999999999
words philosophy 0.0013416090000000001
surrounding words 0.001339113
different writers 0.001318769
comma rules 0.001310944
comma proposals 0.001305193
different amounts 0.001288125
important data 0.001282876
corpus 0.00128029
first task 0.0012598219999999999
other experiments 0.0012522359999999999
basque language 0.0012213060000000001
other tasks 0.001219522
language processing 0.00121929
comma checker 0.0012180770000000001
other hand 0.001188914
same sense 0.001184205
training corpora 0.001170978
language academy 0.001165692
assisted language 0.001162387
other way 0.001156118
author corpora 0.001117658
other works 0.001112215
words 0.00110025
many commas 0.001088263
first choice 0.001083281
first attribute 0.0010775189999999999
original corpora 0.001069992
linguistic information 0.001068611
syntactic parser 0.001057977
first line 0.00105754
specific corpora 0.001056206
syntactic analysis 0.0010499020000000001
data mining 0.001045169
evaluation results 0.0010449230000000001
similar learning 0.001029863
setup corpora 0.00102958
raw text 0.001028997
homogeneous corpora 0.0010146460000000001
valid information 0.001011688
good results 0.001006004
learning techniques 9.96586E-4
normal text 9.66397E-4
vector machine 9.61525E-4
many purposes 9.5908E-4
much information 9.5687E-4
unique newspaper 9.55323E-4
several experiments 9.52292E-4
learning commas 9.48375E-4
similar problems 9.48319E-4
sentence number 9.4308E-4
standard measures 9.42203E-4
syntactic analysers 9.34565E-4
clause boundaries 9.30493E-4
information gain 9.16584E-4
comma 9.1321E-4
recall results 9.112090000000001E-4
basque texts 9.10218E-4
language 9.10208E-4
learning algorithms 9.10033E-4
similar machine 9.04424E-4
many studies 8.98095E-4
same way 8.95847E-4
same size 8.949100000000001E-4
same column 8.93217E-4
automatic clause 8.9077E-4
simple rules 8.905219999999999E-4
machine learning 8.901970000000001E-4
literature texts 8.8776E-4
many fields 8.87501E-4
same time 8.85793E-4
regular results 8.85205E-4
work machine 8.7605E-4
comparative results 8.737840000000001E-4
entific texts 8.722339999999999E-4
learning tasks 8.608330000000001E-4
correct commas 8.50551E-4
third test 8.45314E-4
clause identification 8.432660000000001E-4
philosophy texts 8.40479E-4
main points 8.348240000000001E-4
