different features 0.003369843
other features 0.003056371
different feature 0.002988173
document features 0.00294049
features output 0.002829511
lexical features 0.0028225109999999998
several features 0.002787766
new features 0.0027730660000000002
linguistic features 0.002731707
bow features 0.002703649
features figure 0.002701266
other feature 0.002674701
grained features 0.0026622160000000002
individual features 0.002660247
gazetteer features 0.002647855
features combinations 0.002646991
ferent features 0.002646263
available features 0.002639372
biographical features 0.002635507
ument features 0.002630548
dividual features 0.002624741
feature set 0.002571384
similarity feature 0.0025172449999999996
feature similarity 0.0025172449999999996
tokens feature 0.002481242
single feature 0.002425591
good feature 0.002418671
features 0.0024023
only feature 0.0023829
key feature 0.0023560649999999996
based feature 0.0023416549999999998
feature sets 0.002334484
bow feature 0.002321979
feature types 0.002302405
feature combination 0.002267357
feature combinations 0.002265321
sparse feature 0.002261768
feature sep 0.0022433789999999998
used feature 0.0022433789999999998
feature combi 0.0022433789999999998
feature 0.00202063
different results 0.0017454459999999999
different ner 0.001580258
different document 0.001505733
different web 0.001477285
search results 0.0014735260000000002
clustering system 0.001438487
ner system 0.001417781
clustering results 0.001411324
document text 0.001371933
clustering algorithm 0.0013576999999999999
different names 0.00134944
different fea 0.001325903
other words 0.001299598
text tokens 0.001294355
web results 0.001287645
search task 0.001287479
data avail 0.001281245
same document 0.00126235
similar results 0.001252723
learning algorithm 0.001250158
different types 0.001249318
different factors 0.001237339
tree results 0.001233591
clustering task 0.0012252769999999999
different people 0.001218095
same name 0.001211464
web search 0.001205365
same cluster 0.0012041719999999999
clustering problem 0.001202733
different sizes 0.001192409
clustering systems 0.0011870399999999999
tree algorithm 0.001179967
ner systems 0.001166334
coreference problem 0.001154713
clustering web 0.001143163
same domain 0.001142685
same person 0.0011333839999999999
additional information 0.0011327709999999999
full text 0.001124969
document coreference 0.0011235910000000002
recognition system 0.001068175
oak results 0.001060429
text surrounding 0.001057016
pwa performance 0.001030113
classification task 0.001015941
other fea 0.001012431
clustering algorithms 0.001005999
organisation results 0.00100563
same classifiers 0.001004015
nlp task 0.001003982
web name 9.97046E-4
classification problem 9.93397E-4
similarity function 9.78283E-4
clustering process 9.770199999999999E-4
poor performance 9.75755E-4
word sense 9.7118E-4
ing problem 9.6567E-4
ner tool 9.649960000000001E-4
potential information 9.59183E-4
