word sense 0.00458754
different sense 0.00445653
predominant sense 0.003836632
sense priors 0.003824989
sense prediction 0.003777088
sense information 0.003772204
correct sense 0.003760943
sense disambiguation 0.003756512
frequent sense 0.003727859
true sense 0.003710083
respective sense 0.003705771
dominant sense 0.003690219
inant sense 0.003686461
sense pri 0.003686124
sense 0.00338677
domain data 0.0025668
different domain 0.00237908
different data 0.00232724
training data 0.00228976
wsd accuracy 0.00228618
domain adaptation 0.002195298
adaptation data 0.002143458
different senses 0.00208601
training examples 0.001992002
data set 0.001986818
test data 0.0019330240000000002
target domain 0.0019269110000000001
examples examples 0.001919444
training adaptation 0.001918258
form domain 0.0019021100000000003
new domain 0.001901804
other senses 0.001873333
new data 0.001849964
adaptation examples 0.0018457
supervised wsd 0.0018373410000000001
wsj data 0.001826557
specific domain 0.0018205780000000002
evaluation data 0.001812449
domain label 0.0017706900000000001
training set 0.001761618
language wsd 0.0017572479999999999
different corpora 0.001728873
wsd algorithms 0.00172418
related domain 0.001695625
wsd system 0.001689793
domain labels 0.001683631
tion data 0.001671915
learning approach 0.0016706
wsd systems 0.001666952
data sets 0.0016636950000000002
several wsd 0.00165405
same accuracy 0.0016445510000000002
test examples 0.001635266
conclusion domain 0.0016349140000000001
grammar domain 0.0016312260000000002
domain adap 0.0016301080000000001
labeled data 0.001625006
domain dependence 0.001623714
wsd setting 0.00161969
domain adapta 0.0016117240000000001
wsd accuracies 0.001607482
wsj corpus 0.001602147
word occurrence 0.001581429
different domains 0.0015527549999999998
ing examples 0.00155075
specific corpus 0.0015443280000000002
learning algorithm 0.0015356570000000002
wsj examples 0.001528799
ambiguous word 0.0015265460000000002
predominant senses 0.0014661119999999999
high accuracy 0.001463266
adaptation experiment 0.001457547
wsj adaptation 0.001455055
ing approach 0.00144071
dso corpus 0.001435131
accuracy increase 0.001424968
enough training 0.0014244610000000001
initial training 0.001423749
different percentage 0.0014192629999999998
adaptation experiments 0.0014122140000000002
supervised learning 0.001407459
general corpus 0.001405996
particular corpus 0.0013994
brown corpus 0.0013930700000000002
training exam 0.001382987
mfs accuracy 0.001382659
different contexts 0.001380126
available training 0.00137933
different meanings 0.001376507
final accuracy 0.0013765000000000001
different weights 0.0013685499999999998
different factors 0.001366481
different percentages 0.001366481
accuracy improvement 0.001355609
sufficient training 0.001350192
adaptation process 0.0013406070000000002
annotated training 0.00133828
additional training 0.001338269
ent senses 0.001337308
balanced corpus 0.001333516
