morphological data 0.002515504
morphological information 0.002376629
morphological analysis 0.0023536530000000003
word tag 0.00219229
word order 0.0020336910000000002
different features 0.00202807
word tags 0.001976665
word segmentation 0.001927523
single word 0.001918699
morphological generation 0.0019149520000000001
morphological analyses 0.001897447
original word 0.0018856930000000001
different feature 0.0018824800000000002
analyses word 0.001872697
morphological informa 0.0018706120000000002
morphological analyser 0.001860958
morphological disambiguator 0.0018572780000000002
morphological analy 0.001852866
word categories 0.0018481
word category 0.001846598
exploring word 0.001844347
actual word 0.0018366230000000001
word cate 0.0018341800000000001
word frequencies 0.001833133
words approach 0.0018212430000000002
training data 0.001774463
complex words 0.001664862
feature set 0.001625938
morphological 0.00162497
example features 0.001623622
words tirthankar 0.001578577
informative words 0.00156732
stop words 0.00155043
primary features 0.001529857
main features 0.001518698
informative features 0.0015045
second language 0.00147114
feature space 0.001458067
small feature 0.001432499
first tag 0.001431868
model approach 0.001421286
test data 0.0014108670000000001
language processing 0.001410473
language tasks 0.0014016439999999999
natural language 0.001385695
resource language 0.0013839909999999998
feature sets 0.001380503
tive language 0.0013804619999999998
language learners 0.0013639249999999998
language identification 0.0013621179999999998
language resources 0.0013593309999999999
text classification 0.00133805
words 0.00132112
different test 0.001290103
data selection 0.0012830390000000001
space model 0.0012665200000000001
several learning 0.001262165
syntactic information 0.001260277
features 0.0012583
different classifiers 0.001253183
model representation 0.001241248
syntactic analysis 0.0012373010000000001
data representation 0.001210619
data size 0.001199208
training size 0.001192603
different languages 0.001190924
text documents 0.0011845199999999999
sentiment analysis 0.00117835
graphical model 0.001171943
few training 0.001170953
different number 0.00117095
data sets 0.001158327
learning methods 0.0011557709999999999
annotated data 0.001147862
data sizes 0.001143778
training instances 0.001138719
enough data 0.001124647
text categorization 0.001124478
training sam 0.001124308
training files 0.0011181189999999999
first setting 0.0011179900000000001
feature 0.00111271
undergraduate training 0.0011120589999999999
language 0.00111142
text classi 0.0011048619999999999
different prefix 0.001100564
different fea 0.001099683
machine learning 0.001092959
first characters 0.00108925
pos tag 0.0010807669999999998
analysis process 0.001077613
first derivation 0.001077567
student research 0.001077005
best first 0.0010727409999999999
similar results 0.001070389
first syllable 0.001070107
learning maria 0.001065067
other level 0.001060282
different dimension 0.001059343
ish text 0.0010578369999999998
