emotion features 0.003739731
utterance emotion 0.003675627
emotion response 0.003542431
specific emotion 0.003216921
emotion success 0.003210753
emotion this 0.003202986
emotion prediction 0.003188868
goal emotion 0.003161963
ordinary emotion 0.003121272
emotion recog 0.003117364
prespecified emotion 0.003117364
salient emotion 0.003117364
emotion 0.00285302
dialogue data 0.002483708
dialogue corpus 0.002027181
training data 0.0018772099999999998
dialogue systems 0.001866652
dialogue history 0.001822121
dialogue length 0.001792102
dialogue situation 0.0017808379999999999
data set 0.001608614
utterance pairs 0.001573849
dialogue 0.00151651
such features 0.0013853099999999998
ing data 0.001365842
new features 0.001359777
test data 0.00134533
language model 0.001337202
training methods 0.001307176
data quality 0.001306425
training classifiers 0.001297838
same utterance 0.001290136
last utterance 0.001285601
training example 0.0012743239999999999
input utterance 0.001267773
emotional category 0.001261837
phrase pairs 0.001260074
such pairs 0.0012498409999999998
data sparseness 0.0012437289999999998
alogue data 0.0012421519999999998
tion model 0.001231581
input utterances 0.001217928
second utterance 0.001215967
such information 0.0012137939999999998
translation model 0.001199074
reliable training 0.0011898899999999999
training exam 0.001186875
pairs anger 0.0011776389999999999
discriminative training 0.001176499
emotional expressions 0.00117387
general model 0.0011569409999999999
unique utterances 0.001150594
human work 0.001141581
tagging utterances 0.001126169
model adaptation 0.001115987
example pairs 0.001115554
unlabeled utterances 0.001114377
lation model 0.0011129549999999999
model inter 0.001107226
model interpolation 0.001107226
utterances precision 0.00107398
response generation 0.001062386
emotional categories 0.00105449
statistical response 0.001044355
classification problem 0.0010403740000000002
cluded utterances 0.001040068
paraphrase pairs 0.0010183459999999998
class classification 0.001011659
emotional cate 9.916600000000001E-4
emotional expres 9.88026E-4
response generator 9.87465E-4
response post 9.81747E-4
response gen 9.760109999999999E-4
feature weights 9.74151E-4
human worker 9.68676E-4
such research 9.638209999999999E-4
tistical response 9.5948E-4
joy table 9.57641E-4
response generators 9.57074E-4
classification scenario 9.4662E-4
human workers 9.383519999999999E-4
human effort 9.33393E-4
microblog posts 9.302799999999999E-4
speaker 9.18772E-4
previous study 9.18245E-4
multiple models 9.17033E-4
experimental results 9.10672E-4
training 9.10012E-4
learning scenario 9.099269999999999E-4
pervised learning 9.088219999999999E-4
tional category 8.95918E-4
features 8.86711E-4
related tasks 8.844289999999999E-4
first author 8.83338E-4
same sentence 8.83163E-4
expressions anger 8.77307E-4
translation table 8.75868E-4
indirect speech 8.70453E-4
ditional responses 8.68792E-4
phrase translation 8.67621E-4
