word sense 0.00480506
word feature 0.00386566
english word 0.003284831
wordnet sense 0.0030715929999999996
first sense 0.0030316839999999998
chinese word 0.0030127640000000002
correct sense 0.002861537
word alignment 0.002848233
default sense 0.0028185729999999996
frequent sense 0.0028170689999999997
target word 0.002804329
word type 0.002795478
sense disambiguation 0.00279002
sense inventory 0.002758433
word interest 0.002745935
fault sense 0.0027347469999999996
corresponding word 0.002725224
instance word 0.002719427
content word 0.0027115570000000003
word types 0.002710484
ambiguous word 0.0026929090000000003
word segmentation 0.002680089
ous word 0.002665217
tent word 0.002661179
word segmen 0.0026574660000000003
sense 0.00243644
training data 0.00236482
feature vector 0.0022525649999999998
wsd system 0.002150247
wsd accuracy 0.002143126
words features 0.002120154
tag feature 0.002103638
wsd approach 0.002029641
feature value 0.002010267
wsd systems 0.0019495290000000002
feature type 0.001923898
learning approach 0.0018416209999999999
training examples 0.0018400060000000002
feature types 0.0018389040000000001
feature extraction 0.001838802
own feature 0.00182978
training process 0.001826991
data set 0.00179498
feature extractors 0.001787431
liblinear feature 0.0017846070000000001
high wsd 0.0017703990000000002
good wsd 0.0017523460000000001
test data 0.0017497279999999999
ing words 0.001735751
supervised wsd 0.001713302
source wsd 0.001702659
machine learning 0.001701414
wsd component 0.0016734850000000002
available wsd 0.0016559020000000001
surrounding words 0.00164928
words surrounding 0.00164928
annotated training 0.0016480040000000002
wsd accuracies 0.0016474600000000001
training instances 0.0016457560000000002
stop words 0.001630749
cessful wsd 0.001616379
content words 0.001613727
individual words 0.001607267
learning method 0.001605926
learning methods 0.001571596
supervised learning 0.001525282
different machine 0.00152115
feature 0.00149704
tag features 0.0014559619999999999
learning toolkit 0.00143108
chine learning 0.001430769
pervised learning 0.001428986
english translation 0.001424608
english tasks 0.00141049
data sets 0.0014044
same sentence 0.001388341
linguistic data 0.001380232
english texts 0.0013474
tion model 0.001343533
annotated data 0.0013424840000000001
training 0.00133517
semeval english 0.00133183
benchmark data 0.001318621
data consortium 0.00131704
various features 0.001304863
english side 0.001294747
pos tagging 0.001294641
different preprocessing 0.001290697
pos tag 0.0012795609999999998
senseval english 0.001274683
words 0.00127079
different classifiers 0.001258267
new features 0.001235336
pos noun 0.001234278
english fine 0.001215996
system framework 0.001198696
pos tags 0.001181754
evaluation results 0.001171675
ims system 0.001162552
parallel corpora 0.001155
