test data 0.00329527
training data 0.0032111839999999997
topic model 0.0028674620000000003
language model 0.002802556
data selection 0.0027602259999999997
ing data 0.0027566659999999996
random data 0.0027327519999999998
english data 0.002686407
data english 0.002686407
annotated data 0.0026319969999999996
unlabeled data 0.002543549
automatic data 0.0025414129999999997
little data 0.002530073
available data 0.0025274639999999997
related data 0.002521972
data points 0.002520647
biomedical data 0.002506259
data field 0.002505173
data selec 0.002487787
data limit 0.00248105
notated data 0.0024705589999999998
dom data 0.002468058
lated data 0.0024638489999999997
cial data 0.002461577
model selection 0.002407446
corpus model 0.002372582
baseline model 0.002358031
supervised model 0.002314663
maxent model 0.0022540670000000002
model selec 0.002135007
union model 0.00211477
model union 0.00211477
gression model 0.002111532
advanced model 0.002108955
other word 0.002051403
model 0.00188189
topic models 0.001682742
word distributions 0.001627524
language models 0.001617836
test set 0.0015959160000000002
wsj test 0.0015562980000000002
standard test 0.001516098
training set 0.00151183
random topic 0.001483654
several topic 0.001473511
test sets 0.0014268290000000001
domain models 0.001424091
random words 0.001409342
test articles 0.001371533
domain adaptation 0.001351455
document topic 0.0013244020000000001
different feature 0.001323322
test article 0.0013177850000000001
topic distributions 0.001317156
brown test 0.001316382
new domain 0.001303451
other languages 0.0012999639999999998
training section 0.001299649
adaptation results 0.0012983970000000002
genre topic 0.0012972180000000002
test files 0.001296269
randomization test 0.001294074
nia test 0.001287664
topic distribution 0.001275929
related training 0.001263816
dependency parsing 0.001262272
domain selection 0.001252477
language modeling 0.001248205
topic mod 0.0012398550000000002
domain similarity 0.0012333779999999998
wsj domain 0.0012226189999999999
dependency parser 0.001222251
different approach 0.001221253
distinct topic 0.001219482
topic markers 0.001216138
different similarity 0.0012158030000000001
parsing system 0.00121441
topic marker 0.001213155
topic distri 0.001213155
standard domain 0.0011824189999999999
plain words 0.001171015
new text 0.001162429
parse selection 0.001161567
similar domain 0.001146687
lion words 0.001139875
source domain 0.00111641
english parsing 0.001094858
similar results 0.001093629
tagging results 0.001090113
other corpora 0.0010880549999999999
source models 0.001086659
target domain 0.001080957
other tasks 0.001067943
first set 0.001062967
domain difference 0.0010365749999999999
automatic domain 0.001033664
main adaptation 0.00102947
other side 0.001026208
similarity function 0.001025836
random selection 0.001023638
