other summarization 0.002166505
summarization system 0.002026402
function score 0.002020015
score function 0.002020015
summarization problem 0.0019439830000000003
document summarization 0.0019209560000000001
text summarization 0.001895696
extractive summarization 0.0018107400000000001
summarization task 0.001810387
summarization approaches 0.0017901360000000001
summarization tasks 0.001737064
summarization systems 0.0017222980000000001
summarization prob 0.0016937410000000001
automatic summarization 0.001681217
summarization problems 0.0016724220000000002
length function 0.001648386
new state 0.001634664
sentence set 0.001608274
tomatic summarization 0.001599773
matic summarization 0.001596612
required summarization 0.001595999
state space 0.001592752
linear function 0.001576376
value function 0.001565178
function settings 0.00155076
function approximation 0.001477621
method other 0.0014473350000000001
sentence compression 0.001398797
exponential function 0.0013959019999999999
ear function 0.0013932649999999999
new summary 0.0013858709999999999
state value 0.00138106
summarization 0.00137256
binary state 0.001367217
optimal state 0.001365381
eralization function 0.001358006
sentence level 0.001353686
action space 0.001349671
new method 0.001337172
current state 0.001318143
action set 0.001303195
optimal score 0.0012995139999999999
consideration sentence 0.001289641
new approach 0.001282647
learning algorithm 0.001280607
naive sentence 0.001279032
rouge score 0.001278641
next state 0.001270079
last sentence 0.00125862
initial state 0.001253456
word order 0.001246203
final state 0.00124056
sentence occurrences 0.001236815
score line 0.001235733
state transition 0.001231384
other sum 0.001229083
state variable 0.0012215400000000001
summary length 0.0012154750000000001
other methods 0.001213619
state variables 0.001210458
additional state 0.001204616
terminal state 0.001191318
learning task 0.0011894190000000002
search space 0.001186655
final score 0.0011746929999999999
learning methods 0.001171266
average score 0.001164282
score func 0.001154902
idf score 0.001154097
feature space 0.001147464
learning process 0.001146022
action value 0.001137979
function 0.001135
current learning 0.001118853
search problem 0.001116208
genuine score 0.0011124729999999999
ability score 0.001111009
low score 0.0011106809999999999
same feature 0.001108596
different states 0.0010762319999999999
same features 0.001072962
current summary 0.0010693500000000002
learning rate 0.001067136
efficient learning 0.001061267
learning reinforcement 0.001059338
reinforcement learning 0.001059338
ment learning 0.001049149
extractive approach 0.001037045
quality summary 0.001027096
next action 0.0010269979999999999
other peers 0.001023208
same vector 0.0010230500000000002
other meth 0.001020259
sentence 0.00101288
greedy policy 0.001005361
learning episode 9.78069E-4
forcement learning 9.75347E-4
learning repeats 9.75347E-4
inforcement learning 9.75347E-4
action comp 9.6856E-4
