source data 0.0025883169999999997
target data 0.0023921999999999997
domain data 0.002354932
prior model 0.002249813
data set 0.0022128679999999998
same data 0.002105691
first model 0.0020863410000000002
second model 0.002053675
new feature 0.00200584
single model 0.002000448
model con 0.001984835
srconly model 0.001934667
ond model 0.001933042
conly model 0.001928704
model outper 0.001927102
main data 0.001923536
labeled data 0.001907405
development data 0.001886589
ace data 0.001873705
data points 0.001845839
ner data 0.0018427
data demands 0.001834479
feature space 0.001834196
original feature 0.001822992
feature augmentation 0.001785905
augmented feature 0.001766992
source domain 0.0017662889999999999
model 0.00168063
target domain 0.0015701719999999999
target learning 0.001540439
feature 0.00151326
target corpus 0.001415533
source classifier 0.0013765189999999999
source examples 0.0013475149999999999
target ing 0.00130356
same domain 0.001283663
source example 0.0012829909999999998
additional features 0.001280803
source points 0.001257196
standard learning 0.0012542780000000002
augmented source 0.001253569
test target 0.0012412769999999998
learning algorithm 0.00122707
target classifier 0.0011804019999999999
domain adaptation 0.001178462
target examples 0.0011513979999999999
ing problem 0.001125327
target development 0.001101829
annotated target 0.0010992229999999999
target example 0.0010868739999999998
single domain 0.00108627
different domains 0.00108391
general domain 0.0010746100000000001
augmented target 0.001057452
wsj domain 0.001055451
switchboard domain 0.001052425
unannotated target 0.001049533
adaptation problem 0.001037497
small corpus 0.001036564
augmentation method 0.001026339
supervised learning 0.001024505
other words 0.001015895
domain adapta 0.0010148280000000002
standard algorithm 0.0010079099999999999
parsing task 0.001007715
source 9.99837E-4
learning scenario 9.95819E-4
tagging problem 9.83925E-4
extraction task 9.71956E-4
tion problem 9.70537E-4
experimental results 9.617790000000001E-4
prior work 9.6029E-4
training 9.46061E-4
potential problem 9.393979999999999E-4
baseline approaches 9.38965E-4
original problem 9.352189999999999E-4
recognition task 9.207639999999999E-4
features 9.1648E-4
separate models 9.1292E-4
annotated corpus 9.07316E-4
weight vector 8.926750000000001E-4
asr system 8.78259E-4
tonly models 8.77701E-4
prior variance 8.755480000000001E-4
single task 8.747519999999999E-4
problem formalization 8.72775E-4
brown corpus 8.72285E-4
zero vector 8.63244E-4
ware corpus 8.59898E-4
real vector 8.52744E-4
generalized prior 8.440920000000001E-4
regularization term 8.335689999999999E-4
standard perceptron 8.3351E-4
ing algorithms 8.30844E-4
first case 8.27465E-4
binary vector 8.26603E-4
output space 8.247670000000001E-4
function 8.2373E-4
new algorithms 8.235839999999999E-4
tgtonly baseline 8.17544E-4
