domain training 0.002789243
other domain 0.002736572
training data 0.0026943930000000002
features words 0.00266707
word features 0.002654436
source domain 0.002634573
source features 0.002575993
test data 0.002574239
target domain 0.002554289
source data 0.0025397230000000002
domain adaptation 0.002534497
labeled data 0.002485007
domain classifier 0.002470066
work domain 0.002425288
pivot features 0.002405644
new domain 0.002362085
domain sentences 0.002350267
new features 0.002303505
scl features 0.002290894
new data 0.0022672350000000003
domain tagger 0.002258542
single domain 0.00222758
biomedical domain 0.00221863
shared features 0.0022135979999999998
news domain 0.002212474
financial domain 0.0022034439999999997
tagger features 0.002199962
ing data 0.002181192
unlabeled data 0.002179021
domain sen 0.002169683
data tagger 0.002163692
wsj data 0.002157434
feature representation 0.002155689
medline data 0.002144534
correspondence features 0.002130098
biomedical data 0.00212378
pivot feature 0.002122854
original features 0.002111305
tion features 0.002111223
financial data 0.002108594
projection features 0.002107021
data sets 0.002103669
feature vector 0.002094379
aso features 0.002076822
dard features 0.002056279
arbitrary features 0.002049394
features θxt 0.00204727
data avail 0.00201023
heldout data 0.00201023
learning models 0.002005273
learning algorithm 0.001987328
feature space 0.0019665999999999998
shared feature 0.001930808
common feature 0.001908182
feature type 0.001844728
domain 0.001839
original feature 0.001828515
feature types 0.001823626
learning problem 0.001800505
structural learning 0.0017888079999999998
learning structural 0.0017888079999999998
learning methods 0.0017845419999999999
feature represen 0.001780637
features 0.00178042
feature spaces 0.001780136
augmented feature 0.001774164
learning method 0.001770926
inal feature 0.001770594
finite feature 0.001765994
feature correspondences 0.001764798
source training 0.001745816
discriminative learning 0.001705414
labeled training 0.0016911
target training 0.001665532
correspondence learning 0.001664248
words model 0.0016500529999999998
semisupervised learning 0.001588179
semisupservised learning 0.001581976
fer learning 0.001581976
dence learning 0.001581976
learning curves 0.001581976
task training 0.001525202
training set 0.001512768
feature 0.00149763
training sentences 0.00146151
labeled target 0.0014561460000000002
target labeled 0.0014561460000000002
source corpus 0.001454306
different distribution 0.001452416
training instance 0.0014160660000000001
test set 0.001392614
supervised training 0.00138092
target corpus 0.001374022
other methods 0.001367544
wsj training 0.001363527
medline training 0.001350627
test instances 0.001342368
test sentences 0.0013413560000000001
parsing model 0.001322305
learning 0.00131457
