word features 0.002353779
training data 0.00225835
lexicon features 0.002100577
dependency features 0.002036333
data wikipedia 0.001884525
crf features 0.0018455619999999998
basic features 0.0018151959999999998
ing data 0.0018037449999999998
additional features 0.001799116
contextualization features 0.001752107
test data 0.001744499
gaussian features 0.001728924
global features 0.001725665
boolean features 0.001722342
features fprevw 0.0017162809999999998
digit features 0.0017162809999999998
data extractor 0.0016714759999999999
data lexicons 0.001623044
extraction learning 0.001546604
training set 0.001522439
features 0.00150305
accuracy training 0.001493467
relational data 0.0014912839999999998
attribute extraction 0.001486912
sparse data 0.00146956
data limits 0.0014577799999999999
wikipedia text 0.001442915
extractor training 0.001440526
ing word 0.001409824
learning algorithm 0.001405844
lexicon learning 0.00138938
information extraction 0.00138788
few training 0.0013831339999999998
training examples 0.001382836
wikipedia attribute 0.001372036
training time 0.001360932
text attributes 0.001327571
training sentence 0.0013198279999999999
available training 0.001310089
little training 0.001281069
wikipedia wikipedia 0.00127975
extraction performance 0.001279578
feature weights 0.001279068
system performance 0.001277831
noisy training 0.0012735749999999999
learner training 0.001272373
feature functions 0.0012590499999999998
language text 0.00125345
training sets 0.001253078
supervised learning 0.00124126
feature fcap 0.001239413
feature fgaui 0.001239413
feature fdig 0.001239413
sparse training 0.00123861
web text 0.001237628
extraction accuracy 0.001234518
adequate training 0.001225212
offline training 0.001225212
extractor learning 0.001218679
infobox system 0.001216404
learning extractors 0.001213544
extraction problem 0.00118695
extraction patterns 0.001180997
attribute values 0.001171226
dependency information 0.001166412
wikipedia attributes 0.001164406
attribute extractor 0.001158987
infobox class 0.001158632
attribute extractors 0.0011538520000000001
wikipedia article 0.001145233
learning figure 0.001141002
crf learning 0.001134365
con learning 0.001127177
class classifier 0.001126158
labeled words 0.001118925
wikipedia infobox 0.001103275
attribute names 0.001100333
word contextualization 0.0010997860000000002
extraction techniques 0.0010936280000000001
learning technique 0.001092467
related words 0.001087355
extraction similarity 0.001072306
input word 0.001070954
random attribute 0.001057601
long text 0.001055845
pages extraction 0.001040555
full attribute 0.001039273
other phrases 0.0010278800000000001
feature 0.00102561
text paragraphs 0.001021692
overall extraction 0.001021486
guage text 0.001018151
open extraction 0.0010180459999999999
syntactic extraction 0.001015083
training 0.0010137
pervised learning 0.001012336
test set 0.001008588
article classification 0.001005448
test article 0.0010052070000000001
such classes 0.0010004139999999998
