I
n
t
e
r
n
at
ion
al
Jou
r
n
a
l
of
I
n
f
o
r
m
at
ics
an
d
Com
m
u
n
icat
ion
T
e
c
h
n
ol
ogy
(
I
J
-
I
CT
)
Vo
l
.
1
4
,
N
o
.
2
,
A
ugus
t
20
2
5
,
pp.
478
~
487
I
S
S
N:
2252
-
8776
,
DO
I
:
10
.
11591/i
ji
c
t
.
v
1
4
i
2
.
pp
47
8
-
487
478
Jou
r
n
al
h
o
m
e
page
:
ht
tp:
//
ij
ict
.
iaes
c
or
e
.
c
om
In
d
oB
A
R
T
o
p
t
i
m
iz
at
io
n
f
or
q
u
e
st
io
n
an
sw
e
r
g
e
n
e
r
at
io
n
s
y
st
e
m
w
ith
l
on
gf
or
m
e
r
at
t
e
n
t
io
n
P
e
t
e
r
And
r
e
w,
Abb
a
S
u
gan
d
a
Gi
r
s
an
g
D
e
pa
r
tm
e
nt
of
C
o
mput
e
r
S
c
i
e
n
c
e
,
B
in
us
G
r
a
dua
te
P
r
o
gr
a
m
-
M
a
s
te
r
of
C
o
mput
e
r
S
c
i
e
n
c
e
,
B
in
a
N
us
a
nt
a
r
a
U
ni
ve
r
s
it
y
, J
a
ka
r
ta
, I
ndo
n
e
s
ia
Ar
t
ic
l
e
I
n
f
o
AB
S
T
RA
CT
A
r
ti
c
le
h
is
tor
y
:
R
e
c
e
i
ve
d
A
pr
30,
2024
R
e
vi
s
e
d
De
c
13,
2024
A
c
c
e
pt
e
d
J
a
n
19,
2025
T
h
e
I
n
co
rp
o
rat
i
o
n
o
f
Q
u
e
s
t
i
o
n
A
n
s
w
e
r
i
n
g
s
y
s
t
em
h
o
l
d
s
i
mme
n
s
e
p
o
t
en
t
i
al
fo
r
ad
d
r
e
s
s
i
n
g
In
d
o
n
e
s
i
a’s
e
d
u
c
at
i
o
n
al
d
i
s
p
ari
t
i
e
s
b
e
t
w
ee
n
t
h
e
ab
u
n
d
an
ce
o
f
h
i
g
h
s
c
h
o
o
l
s
t
u
d
en
t
s
an
d
t
h
e
l
i
mi
t
ed
n
u
m
b
e
r
o
f
t
e
a
ch
e
rs
i
n
I
n
d
o
n
e
s
i
a.
T
h
e
s
e
s
t
u
d
i
e
s
ai
m
t
o
e
n
h
an
ce
t
h
e
Q
u
e
s
t
i
o
n
A
n
s
w
e
r
i
n
g
S
y
s
t
em
m
o
d
el
t
ai
l
o
r
ed
f
o
r
t
h
e
I
n
d
o
n
e
s
i
an
l
an
g
u
a
g
e
d
at
as
e
t
t
h
ro
u
g
h
e
n
h
an
ceme
n
t
s
t
o
t
h
e
In
d
o
n
e
s
i
a
n
I
n
d
o
BA
RT
m
o
d
e
l
.
Im
p
ro
v
eme
n
t
w
as
d
o
n
e
b
y
i
n
co
rp
o
rat
i
n
g
L
o
n
g
fo
r
me
r’s
s
l
i
d
i
n
g
w
i
n
d
o
w
s
at
t
en
t
i
o
n
mec
h
a
n
i
s
m
i
n
t
o
t
h
e
I
n
d
o
B
A
RT
m
o
d
e
l
,
i
t
w
o
u
l
d
i
n
c
r
e
as
e
m
o
d
e
l
p
ro
fi
ci
e
n
cy
i
n
m
an
a
g
i
n
g
e
x
t
e
n
d
ed
s
e
q
u
en
ce
t
as
k
s
s
u
c
h
as
q
u
e
s
t
i
o
n
a
n
s
w
e
r
i
n
g
.
T
h
e
d
at
as
e
t
u
s
e
d
i
n
t
h
i
s
r
e
s
earc
h
w
as
T
y
D
i
Q
A
mu
l
t
i
l
i
n
g
u
al
d
at
as
e
t
an
d
t
ran
s
l
at
e
d
t
h
e
SQ
u
A
D
v
2
d
at
as
e
t
.
T
h
e
e
v
a
l
u
at
i
o
n
i
n
d
i
c
at
e
s
t
h
at
t
h
e
L
o
n
g
fo
r
me
r
-
In
d
o
BA
RT
m
o
d
e
l
o
u
t
p
e
rf
o
rm
s
i
t
s
p
re
d
ece
s
s
o
r
o
n
t
h
e
T
y
D
i
Q
A
d
at
as
e
t
,
s
h
o
w
c
as
i
n
g
an
a
v
e
rag
e
2
6
%
e
n
h
an
cemen
t
ac
r
o
s
s
F1
,
E
x
ac
t
Mat
c
h
,
BL
E
U
,
a
n
d
RO
U
G
E
me
t
ri
c
s
.
N
e
v
e
rt
h
e
l
e
s
s
,
i
t
e
x
p
e
r
i
e
n
ced
a
mi
n
o
r
s
e
t
b
ack
o
n
t
h
e
SQ
u
A
D
v
2
d
at
as
e
t
,
l
e
ad
i
n
g
t
o
a
n
av
e
rag
e
d
ec
r
e
as
e
o
f
0
.
6
%
ac
ro
s
s
al
l
me
t
ri
c
s
.
K
e
y
w
o
r
d
s
:
F
i
ne
-
t
uni
n
g
Na
t
ur
a
l
l
a
n
gua
ge
ge
n
e
r
a
t
i
o
n
Na
t
ur
a
l
l
a
n
gua
ge
pr
o
c
e
s
s
i
n
g
Que
s
t
i
o
n
a
ns
we
r
ge
ne
r
a
t
i
o
n
T
r
a
n
s
f
o
r
m
e
r
Th
i
s
i
s
a
n
o
p
en
a
c
ces
s
a
r
t
i
c
l
e
u
n
d
e
r
t
h
e
CC
B
Y
-
SA
l
i
cen
s
e.
C
or
r
e
s
pon
din
g
A
u
th
or
:
P
e
t
e
r
A
n
dr
e
w
De
pa
r
t
m
e
n
t
o
f
C
o
m
put
e
r
S
c
i
e
n
c
e
,
B
i
n
us
Gr
a
dua
t
e
P
r
o
gr
a
m
-
M
a
s
t
e
r
o
f
C
o
m
put
e
r
S
c
i
e
n
c
e
B
i
n
a
Nu
s
a
n
t
a
r
a
Uni
v
e
r
s
i
t
y
J
a
ka
r
t
a
,
I
n
do
n
e
s
i
a
,
11480
E
m
a
i
l
:
pe
t
e
r
.
a
n
dr
e
w@b
i
nu
s
.
a
c
.
i
d
1.
I
NT
RODU
C
T
I
ON
T
h
e
r
e
i
s
a
n
i
m
ba
l
a
nc
e
i
n
t
h
e
t
e
a
c
h
e
r
a
n
d
s
t
ude
nt
r
a
t
i
o
i
n
I
n
do
n
e
s
i
a
.
B
a
s
e
d
o
n
I
n
do
n
e
s
i
a
C
e
n
t
r
a
l
S
t
a
t
i
s
t
i
c
,
i
n
2021/2022,
t
h
e
n
u
m
be
r
o
f
hi
g
h
s
c
hoo
l
s
t
ude
n
t
s
i
n
I
n
do
n
e
s
i
a
r
e
a
c
h
e
d
10,
063,
926.
W
hil
e
t
h
e
a
v
a
il
a
bl
e
n
u
m
be
r
o
f
t
e
a
c
h
e
r
s
wa
s
o
n
l
y
700,
742.
On
e
t
e
a
c
h
e
r
h
a
s
to
o
v
e
r
s
e
e
a
r
o
un
d
14
s
t
ude
n
t
s
.
W
i
t
h
t
h
e
a
dv
a
nc
e
m
e
n
t
o
f
t
e
c
h
n
o
l
o
g
y
,
i
t
c
o
ul
d
a
s
s
i
s
t
t
e
a
c
h
e
r
s
i
n
t
h
e
l
e
a
r
ni
ng
pr
o
c
e
s
s
a
n
d
e
ns
ur
e
t
h
e
e
f
f
e
c
t
i
v
e
n
e
s
s
o
f
t
he
t
e
a
c
h
e
r
e
f
f
o
r
t
[
1]
.
I
n
e
duc
a
t
i
o
n
,
r
e
a
d
i
n
g
i
s
a
n
i
m
po
r
t
a
n
t
a
c
t
i
vi
t
y
.
R
e
a
d
i
n
g
e
na
bl
e
s
s
t
ude
n
t
s
to
un
de
r
s
t
a
n
d
t
h
e
t
e
x
t
or
r
e
a
d
i
n
g
m
a
t
e
r
i
a
l
a
n
d
i
s
a
c
o
gni
t
i
ve
pr
o
c
e
s
s
f
o
r
e
x
t
r
a
c
t
i
n
g
i
nf
o
r
m
a
t
i
o
n
.
R
e
a
d
i
ng
s
t
r
a
t
e
gi
e
s
,
i
n
t
e
r
pr
e
t
i
ng
wor
ds
,
a
n
d
r
e
a
d
i
ng
t
e
c
hni
que
s
a
r
e
a
l
s
o
c
r
uc
i
a
l
f
o
r
e
f
f
e
c
t
i
v
e
l
e
a
r
ni
ng
[
2]
,
[
3
]
.
Due
to
t
h
e
i
m
po
r
t
a
n
c
e
o
f
r
e
a
d
i
n
g,
t
e
a
c
hi
n
g
s
t
r
a
t
e
gi
e
s
h
a
v
e
b
e
e
n
de
v
e
l
o
pe
d
to
t
e
a
c
h
a
n
d
e
va
l
u
a
t
e
r
e
a
di
n
g
[
4]
.
On
e
o
f
t
h
e
de
v
e
l
o
pe
d
s
t
r
a
t
e
gi
e
s
i
s
que
s
t
i
o
n
ge
ne
r
a
t
i
o
n
(
QG
)
.
Ho
we
v
e
r
,
t
h
e
pr
o
c
e
s
s
o
f
c
r
e
a
t
i
n
g
que
s
t
i
o
n
s
i
s
t
i
m
e
-
c
o
n
s
u
mi
ng
[
5]
.
F
r
o
m
t
h
i
s
i
s
s
ue
,
t
h
e
r
e
s
e
a
r
c
h
o
n
QG
,
a
l
s
o
kn
o
wn
a
s
a
ut
o
m
a
t
i
c
qu
e
s
t
i
o
n
ge
ne
r
a
t
i
o
n
(
A
QG
)
[
6]
,
[
7
]
,
h
a
s
b
e
e
n
d
e
ve
l
o
pe
d
a
s
a
b
r
a
n
c
h
o
f
n
a
t
ur
a
l
l
a
n
gua
ge
ge
n
e
r
a
t
i
o
n
(
NL
G)
.
QG
i
s
t
h
e
pr
o
c
e
s
s
o
f
a
uto
m
a
t
i
n
g
t
h
e
c
r
e
a
t
i
o
n
o
f
que
s
t
i
o
ns
b
a
s
e
d
o
n
t
e
x
t
ua
l
i
nput
i
n
v
a
r
i
o
us
f
o
r
m
s
s
uc
h
a
s
s
h
o
r
t
a
n
s
we
r
,
o
pe
n
-
e
n
d
e
d
que
s
t
i
o
n
s
,
m
u
l
t
i
p
l
e
-
c
h
o
i
c
e
,
a
n
d
f
il
l
-
in
-
t
h
e
-
bl
a
n
k
[
8]
.
T
h
e
a
i
m
o
f
QG
i
s
to
c
r
e
a
t
e
n
a
t
u
r
a
l
que
s
t
i
o
n
s
t
o
t
e
s
t
t
h
e
kn
o
w
l
e
dge
a
c
q
u
i
r
e
d
f
r
o
m
r
e
a
d
i
n
g.
Que
s
t
i
o
n
An
s
w
e
r
Ge
n
e
r
a
t
i
o
n
wa
s
f
i
r
s
t
i
n
t
r
o
duc
e
d
i
n
1999
a
t
t
h
e
t
e
x
t
r
e
tr
i
e
va
l
c
o
nf
e
r
e
n
c
e
(
T
R
E
C
)
a
s
a
t
e
s
t
f
o
r
s
y
s
t
e
m
c
a
pa
bil
i
t
i
e
s
i
n
f
i
nd
i
ng
s
h
o
r
t
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t
J
I
n
f
&
C
o
m
m
u
n
T
e
c
hn
o
l
I
S
S
N:
2252
-
8776
I
ndoB
A
R
T
opti
miz
ati
on
f
or
que
s
ti
on
ans
w
e
r
ge
ne
r
ati
on
s
y
s
tem
w
it
h
longf
or
me
r
att
e
nti
on
(
P
e
ter
A
ndr
e
w
)
479
a
n
d
c
o
n
c
i
s
e
t
e
x
t
s
to
a
n
s
we
r
g
i
v
e
n
que
s
t
i
o
n
s
.
T
h
e
t
e
s
t
i
n
g
y
i
e
l
de
d
s
a
t
i
s
f
a
c
t
or
y
r
e
s
u
l
t
s
a
s
t
h
e
s
y
s
t
e
m
c
o
u
l
d
e
x
t
r
a
c
t
s
pe
c
i
f
i
c
t
e
x
t
s
t
h
a
t
we
r
e
p
r
e
di
c
t
e
d
to
b
e
s
t
a
ns
we
r
t
h
e
g
i
v
e
n
que
s
t
i
o
n
s
.
Que
s
t
i
o
n
a
n
s
we
r
r
e
s
e
a
r
c
h
h
a
s
r
a
p
i
d
ly
de
ve
l
o
pe
d
a
n
d
c
o
m
bi
ne
d
s
e
v
e
r
a
l
d
if
f
e
r
e
n
t
b
ut
r
e
l
a
t
e
d
r
e
s
e
a
r
c
h
f
i
e
l
d
s
,
i
n
c
l
ud
i
ng
i
nf
o
r
m
a
t
i
o
n
e
x
t
r
a
c
t
i
o
n
(
I
E
)
,
n
a
t
ur
a
l
l
a
n
gua
ge
pr
o
c
e
s
s
i
ng
(
NL
P
)
,
a
n
d
i
nf
o
r
m
a
t
i
o
n
r
e
t
r
i
e
v
a
l
(
I
R
)
[
9]
.
T
h
e
A
QG
s
y
s
t
e
m
t
y
p
i
c
a
ll
y
c
o
ns
i
s
t
s
o
f
t
h
r
e
e
c
o
n
c
e
pt
ua
l
pr
o
c
e
s
s
e
s
[
8]
.
W
hi
c
h
i
s
t
a
r
ge
t
s
e
l
e
c
t
i
o
n
,
t
h
e
s
t
a
ge
o
f
i
de
n
t
i
f
yi
ng
i
m
po
r
t
a
n
t
s
e
n
t
e
n
c
e
s
a
n
d
ke
y
w
o
r
ds
.
Que
s
t
i
o
n
r
e
pr
e
s
e
n
t
a
t
i
o
n
c
o
ns
t
r
uc
t
i
o
n
,
de
t
e
r
m
i
n
i
ng
t
h
e
t
y
pe
a
n
d
s
y
n
t
a
c
t
i
c
f
o
r
m
o
f
que
s
t
i
o
ns
b
a
s
e
d
o
n
t
h
e
s
e
n
t
e
n
c
e
s
a
n
d
ke
y
wo
r
ds
c
o
n
t
a
i
ne
d
i
n
t
h
e
t
e
x
t
.
Que
s
t
i
o
n
r
e
a
l
i
z
a
t
i
o
n
,
t
h
e
f
i
na
l
s
t
a
ge
o
f
que
s
t
i
o
n
c
r
e
a
t
i
o
n
.
Que
s
t
i
o
n
a
ns
we
r
i
ng
s
y
s
t
e
m
s
c
a
n
b
e
d
i
vi
de
d
i
n
t
o
two
t
y
pe
s
[
9]
.
C
l
o
s
e
d
d
o
m
a
i
n,
t
h
e
s
y
s
t
e
m
c
a
n
o
nl
y
h
a
n
d
l
e
que
s
t
i
o
n
s
i
n
s
pe
c
if
i
c
f
i
e
l
ds
(
s
po
r
t
s
,
p
o
l
i
t
i
c
s
,
a
n
d
h
e
a
l
t
h
)
.
I
t
c
a
n
a
l
s
o
b
e
i
n
t
e
r
pr
e
t
e
d
a
s
a
c
o
n
d
i
t
i
o
n
wh
e
r
e
t
h
e
r
e
a
r
e
l
im
i
t
a
t
i
o
n
s
o
n
que
s
t
i
o
n
t
y
pe
s
,
s
uc
h
a
s
d
e
s
c
r
i
pt
i
v
e
que
s
t
i
o
ns
.
T
hi
s
t
y
pe
c
a
n
b
e
f
a
c
i
li
t
a
t
e
d
by
us
i
ng
NL
P
s
y
s
t
e
m
s
w
i
t
h
t
h
e
e
x
p
l
o
i
t
a
t
i
o
n
o
f
s
pe
c
i
f
i
c
s
c
i
e
n
t
i
f
i
c
f
i
e
l
d
s
(
o
n
to
l
o
g
i
e
s
)
.
Ope
n
d
o
m
a
i
n,
t
h
e
s
y
s
t
e
m
c
a
n
h
a
n
d
l
e
ge
n
e
r
a
l
que
s
t
i
o
n
s
t
h
a
t
a
r
e
n
ot
l
im
i
t
e
d
to
s
pe
c
i
f
i
c
f
i
e
l
ds
o
f
kn
o
w
l
e
dge
.
S
uc
h
s
y
s
t
e
m
s
us
ua
ll
y
r
e
qu
i
r
e
a
l
a
r
ge
a
m
o
u
n
t
o
f
da
t
a
to
o
b
t
a
i
n
a
c
c
ur
a
t
e
a
n
s
w
e
r
s
.
T
h
e
r
e
a
r
e
s
e
v
e
r
a
l
a
pp
r
oa
c
h
e
s
to
q
u
e
s
t
i
o
n
-
a
n
s
we
r
i
n
g
s
y
s
t
e
m
s
,
i
n
c
l
udi
n
g
[
9]
,
f
r
e
q
ue
n
t
l
y
a
s
ke
d
que
s
t
i
o
n
s
a
n
d
a
n
s
we
r
s
(
F
A
Qs
)
,
T
h
e
e
a
s
i
e
s
t
a
p
p
r
oa
c
h
i
nv
o
l
v
e
s
c
o
l
l
e
c
t
i
n
g
a
da
tas
e
t
of
q
ue
s
t
i
o
n
-
a
n
s
we
r
pa
i
r
s
s
tor
e
d
i
n
t
h
e
s
y
s
te
m
.
W
h
e
n
a
q
ue
s
t
i
o
n
i
s
gi
v
e
n
,
t
h
e
s
y
s
t
e
m
s
e
a
r
c
h
e
s
f
o
r
t
h
e
a
n
s
we
r
f
r
o
m
t
h
e
s
tor
e
d
d
a
tas
e
t.
I
n
f
or
m
a
t
i
o
n
R
e
tr
i
e
v
a
l
,
t
h
i
s
i
s
t
h
e
m
o
s
t
c
o
m
m
o
nl
y
us
e
d
a
p
p
r
oa
c
h
,
wh
e
r
e
t
h
e
m
a
i
n
c
o
n
c
e
p
t
i
s
to
s
e
a
r
c
h
f
or
a
c
c
ur
a
te
a
n
d
p
r
e
c
i
s
e
a
n
s
we
r
s
f
r
o
m
a
c
o
l
l
e
c
t
i
o
n
o
f
d
oc
um
e
n
t
s
.
T
h
e
ge
n
e
r
a
l
s
te
ps
us
e
d
i
n
t
h
i
s
a
p
pr
oa
c
h
i
n
c
l
ude
pr
e
-
p
r
oc
e
s
s
i
n
g
,
q
ue
s
t
i
o
n
a
n
a
l
y
s
i
s
,
d
oc
um
e
n
t
r
e
tr
i
e
v
a
l
,
a
n
d
a
n
s
we
r
e
x
tr
a
c
t
i
o
n
.
M
a
c
hi
n
e
l
e
a
r
ni
n
g,
t
hi
s
a
p
p
r
oa
c
h
i
s
s
i
m
i
l
a
r
to
I
n
f
or
m
a
t
i
o
n
R
e
tr
i
e
v
a
l
,
b
u
t
wi
t
h
t
h
e
a
ddi
t
i
o
n
o
f
c
l
a
s
s
i
f
i
c
a
t
i
o
n
a
l
g
or
i
t
hm
s
to
c
l
a
s
s
i
f
y
qu
e
s
t
i
o
n
t
y
pe
s
.
S
e
v
e
r
a
l
de
v
e
l
o
p
m
e
n
t
s
i
n
A
QG
s
y
s
t
e
m
s
ha
v
e
b
e
e
n
m
a
d
e
.
He
r
e
a
r
e
s
o
m
e
r
e
l
a
t
e
d
A
QG
r
e
s
e
a
r
c
h
s
t
udi
e
s
s
uc
h
a
s
,
t
h
e
de
v
e
l
o
p
m
e
n
t
o
f
t
h
e
s
t
a
n
f
o
r
d
que
s
t
i
o
n
a
n
s
we
r
i
ng
da
t
a
s
e
t
(
S
QuA
D)
by
[
10]
.
T
h
e
da
t
a
s
e
t
wa
s
c
o
l
l
e
c
t
e
d
f
r
o
m
W
i
k
i
pe
d
i
a
a
r
t
i
c
l
e
s
,
w
i
t
h
c
r
o
wds
o
ur
c
e
d
que
s
t
i
o
n
-
a
n
s
we
r
pa
i
r
s
.
T
he
h
u
m
a
n
-
v
a
li
d
a
t
e
d
t
e
s
t
r
e
s
u
l
t
s
a
c
hi
e
v
e
d
a
n
e
x
a
c
t
m
a
t
c
h
(
E
M
)
o
f
77%
a
n
d
a
n
F
1
S
c
o
r
e
o
f
86.
8%
.
T
h
e
de
v
e
l
o
p
m
e
n
t
o
f
a
d
o
c
um
e
n
t
r
e
tr
i
e
va
l
m
e
t
h
o
d
us
i
n
g
a
r
e
c
ur
r
e
n
t
g
r
a
ph
-
b
a
s
e
d
m
o
de
l
by
[
11]
.
I
t
wa
s
de
v
e
l
o
pe
d
to
s
o
l
v
e
t
h
e
pr
o
bl
e
m
o
f
e
n
t
i
t
y
-
c
e
n
t
r
i
c
que
s
t
i
o
ns
c
a
us
e
d
by
i
n
f
o
r
m
a
t
i
o
n
c
o
m
pr
e
s
s
i
o
n
.
T
h
e
m
e
t
h
o
d
a
c
hi
e
v
e
d
a
n
i
m
pr
o
v
e
d
F
1
s
c
or
e
o
f
2.
9
a
n
d
E
M
o
f
3.
5
us
i
n
g
t
h
e
S
QuA
D
da
t
a
s
e
t.
T
h
e
de
ve
l
o
p
m
e
n
t
o
f
a
d
o
c
um
e
n
t
r
e
tr
i
e
v
a
l
m
e
t
h
o
d
ut
i
li
z
i
ng
Ge
n
e
r
a
t
i
v
e
M
o
de
l
s
by
[
12]
.
I
t
a
i
m
e
d
to
t
e
s
t
t
h
e
c
a
pa
bil
i
t
y
o
f
Ge
n
e
r
a
t
i
v
e
M
o
de
l
s
i
n
s
e
a
r
c
hi
ng
f
o
r
t
e
x
t
do
c
um
e
n
t
s
c
o
n
t
a
i
ni
ng
e
vi
de
nc
e
.
T
h
e
r
e
s
u
l
t
s
s
h
o
we
d
a
n
F
1
s
c
o
r
e
o
f
63.
2
a
n
d
E
M
o
f
56.
7
o
n
t
h
e
S
QuA
D
da
t
a
s
e
t,
a
s
we
l
l
a
s
a
n
F
1
s
c
o
r
e
o
f
56.
7
a
n
d
E
M
o
f
80.
1
o
n
t
h
e
T
r
i
vi
a
Q
A
da
t
a
s
e
t
.
T
h
e
de
v
e
l
o
p
m
e
n
t
o
f
De
c
o
m
po
s
e
d
P
r
e
-
T
r
a
i
n
T
r
a
n
s
f
o
r
m
e
r
by
[
13]
,
wi
t
h
t
h
e
g
o
a
l
o
f
s
pe
e
d
i
n
g
up
t
h
e
pr
o
c
e
s
s
by
4.
3
x
c
o
m
pa
r
e
d
to
pr
e
vi
o
us
t
r
a
n
s
f
o
r
m
e
r
m
o
de
l
s
,
w
i
t
h
o
nl
y
a
1%
de
c
r
e
a
s
e
i
n
a
c
c
ur
a
c
y
.
I
n
[
14]
i
n
t
r
o
duc
e
d
I
n
do
NL
G,
a
b
e
n
c
hm
a
r
k
f
o
r
NL
G
i
n
t
h
r
e
e
c
o
m
m
o
nly
u
s
e
d
I
ndo
n
e
s
i
a
n
l
a
n
gua
ge
s
:
B
a
h
a
s
a
I
n
do
n
e
s
i
a
,
S
un
da
,
a
n
d
J
a
wa
.
I
n
do
NL
G
i
n
c
l
ude
s
s
i
x
e
v
a
l
ua
t
i
o
n
t
a
s
ks
:
m
a
c
hi
ne
t
r
a
n
s
l
a
t
i
o
n
(
M
T
)
,
QG
,
s
u
m
m
a
r
i
z
a
t
i
o
n
,
C
hi
t
-
c
h
a
t
,
a
n
d
m
o
r
e
.
T
h
e
da
t
a
s
e
t
I
n
do
4B
-
P
l
u
s
[
15]
i
s
us
e
d
t
o
p
r
e
-
t
r
a
i
n
t
h
e
I
n
do
B
A
R
T
a
n
d
I
n
do
GPT
m
o
de
l
s
,
w
hi
c
h
a
c
hi
e
v
e
c
o
m
pe
t
i
t
i
v
e
r
e
s
u
l
t
s
w
i
t
h
1/5t
h
o
f
t
h
e
pa
r
a
m
e
t
e
r
s
c
om
pa
r
e
d
to
m
u
l
t
i
-
li
ngua
l
m
o
de
l
s
li
ke
m
B
AR
T
.
Am
o
n
g
t
h
e
de
v
e
l
o
pe
d
A
QG
s
y
s
t
e
m
s
,
o
nl
y
a
f
e
w
h
a
ve
f
o
c
us
e
d
o
n
t
h
e
I
n
do
n
e
s
i
a
n
l
a
n
gua
ge
.
T
h
e
r
e
f
o
r
e
,
t
hi
s
a
r
t
i
c
l
e
a
im
s
im
pr
o
vi
n
g
t
h
e
a
c
c
ur
a
c
y
o
f
I
n
do
n
e
s
i
a
n
-
b
a
s
e
d
AQ
G
s
y
s
t
e
m
s
m
o
de
l
by
mo
di
f
y
i
ng
t
h
e
a
tt
e
n
t
i
o
n
l
a
y
e
r
o
f
t
h
e
m
o
de
l
us
i
ng
l
o
n
g
f
o
r
m
e
r
–
s
l
i
d
i
ng
w
i
n
do
ws
a
tt
e
n
t
i
o
n
.
2.
RE
L
AT
E
D
WORK
S
B
L
E
U
(
B
i
li
ngua
l
E
v
a
l
ua
t
i
o
n
U
n
de
r
s
t
ud
y
)
[
16]
c
o
m
pa
r
e
s
MT
to
h
u
m
a
n
t
r
a
n
s
l
a
t
i
o
ns
,
a
i
mi
ng
t
o
c
l
o
s
e
ly
mi
r
r
o
r
pr
o
f
e
s
s
i
o
n
a
l
h
u
m
a
n
t
r
a
n
s
l
a
t
i
o
n
s
.
B
L
E
U
s
c
or
e
s
i
n
d
i
vi
du
a
l
t
r
a
n
s
l
a
t
e
d
s
e
g
m
e
n
t
s
a
ga
i
n
s
t
r
e
f
e
r
e
n
c
e
t
r
a
n
s
l
a
t
i
o
ns
,
t
h
e
n
a
v
e
r
a
ge
s
s
c
o
r
e
s
a
c
r
o
s
s
t
h
e
c
o
r
pus
to
ga
uge
o
v
e
r
a
l
l
t
r
a
n
s
l
a
t
i
o
n
qua
l
i
t
y
.
I
t
p
r
i
o
r
i
t
i
z
e
s
pr
e
c
i
s
i
o
n
o
v
e
r
f
a
c
t
o
r
s
l
i
ke
i
n
t
e
ll
i
g
i
b
il
i
t
y
a
n
d
gr
a
m
m
a
t
i
c
a
l
c
o
r
r
e
c
t
n
e
s
s
by
c
o
m
put
i
n
g
t
h
e
pr
e
s
e
n
c
e
o
f
n
-
gr
a
m
s
i
n
t
h
e
c
a
n
d
i
da
t
e
tr
a
n
s
l
a
t
i
o
n
a
l
s
o
f
o
un
d
i
n
r
e
f
e
r
e
n
c
e
tr
a
n
s
l
a
t
i
o
n
s
.
B
L
E
U
o
f
f
e
r
s
v
a
r
i
a
n
t
s
s
uc
h
a
s
B
L
E
U
-
1
a
n
d
B
L
E
U
-
4,
wh
e
r
e
n
va
r
i
e
s
f
r
o
m
1
to
a
s
pe
c
i
f
i
e
d
N
(
e
.
g.
,
1
or
4
)
,
a
n
d
a
ggr
e
ga
t
e
s
s
c
o
r
e
s
us
i
n
g
a
ge
o
m
e
t
r
i
c
m
e
a
n
.
R
e
c
a
ll
-
o
r
i
e
n
t
e
d
un
de
r
s
t
u
dy
f
o
r
gi
s
t
i
n
g
e
va
l
ua
t
i
o
n
(
R
OU
GE
)
[
17]
i
s
a
r
o
b
us
t
m
e
t
r
i
c
us
e
d
i
n
NL
P
to
e
v
a
l
ua
t
e
a
uto
m
a
t
i
c
s
u
mm
a
r
i
z
a
t
i
o
n
a
n
d
MT
s
y
s
t
e
m
s
.
I
t
c
o
m
pa
r
e
s
ge
n
e
r
a
t
e
d
s
u
m
m
a
r
i
e
s
o
r
tr
a
n
s
l
a
t
i
o
n
s
w
i
t
h
h
u
m
a
n
r
e
f
e
r
e
n
c
e
s
,
pr
o
vi
d
i
ng
v
a
l
ua
bl
e
i
ns
i
g
h
t
s
.
N
ot
a
bl
y
c
a
s
e
-
i
ns
e
ns
i
t
i
ve
.
R
OU
GE
-
L
v
a
r
i
a
n
t
s
,
c
o
m
put
e
s
i
t
s
s
c
o
r
e
b
a
s
e
d
o
n
t
h
e
l
o
n
ge
s
t
c
o
m
m
o
n
s
u
b
s
e
que
n
c
e
(
L
C
S
)
b
e
t
we
e
n
r
e
f
e
r
e
n
c
e
a
n
d
c
a
n
d
i
da
t
e
t
e
x
t
s
,
o
f
f
e
r
i
ng
f
l
e
xi
b
i
li
t
y
w
i
t
h
o
u
t
r
e
qui
r
i
n
g
a
pr
e
de
f
i
ne
d
n
-
gr
a
m
s
ize
.
S
e
v
e
r
a
l
que
s
t
i
o
n
-
a
n
s
w
e
r
i
n
g
m
o
de
l
s
h
a
v
e
b
e
e
n
d
e
v
e
l
o
pe
d
t
o
e
n
h
a
n
c
e
a
c
c
ur
a
c
y
a
n
d
e
f
f
i
c
i
e
nc
y
i
n
h
a
n
d
li
ng
ge
n
e
r
a
l
do
m
a
i
n
t
a
s
ks
,
[
18]
p
r
o
p
o
s
e
d
u
t
i
li
z
i
ng
m
u
l
t
i
p
l
e
f
r
a
m
e
wo
r
ks
to
l
e
a
r
n
f
r
o
m
r
e
pr
e
s
e
n
t
a
t
i
o
n
s
,
whi
c
h
c
a
n
b
e
d
i
vi
de
d
i
n
t
o
s
e
v
e
r
a
l
pr
o
c
e
s
s
e
s
.
T
h
e
m
o
de
l
i
s
b
a
s
e
d
o
n
t
h
e
pr
e
-
t
r
a
i
n
e
d
m
o
de
l
(
XL
Ne
t
)
a
n
d
s
u
b
s
e
qu
e
n
t
l
y
f
i
ne
-
t
un
e
d
us
i
ng
v
a
r
i
o
us
da
t
a
s
e
t
s
.
T
h
e
e
x
pe
r
i
m
e
n
t
a
l
r
e
s
u
l
t
s
f
r
o
m
d
i
f
f
e
r
e
n
t
f
r
a
m
e
wo
r
ks
yi
e
l
de
d
a
n
a
v
e
r
a
ge
E
M
s
c
o
r
e
o
f
56.
59
a
n
d
a
n
F
1
s
c
o
r
e
o
f
68.
98
(
f
r
o
m
t
e
s
t
da
t
a
s
e
t
s
:
B
i
o
P
r
o
c
e
s
s
,
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2252
-
8776
I
n
t
J
I
n
f
&
C
o
m
m
u
n
T
e
c
hn
o
l
,
Vo
l
.
1
4
,
N
o.
2
,
A
ugus
t
20
2
5
:
478
-
487
480
C
o
m
p
l
e
xW
e
b
Que
s
t
i
o
ns
,
M
C
T
e
s
t
,
QA
M
R
,
QA
S
T
,
T
R
E
C
)
,
i
n
d
i
c
a
t
i
n
g
a
n
i
m
pr
o
v
e
m
e
n
t
i
n
a
c
c
ur
a
c
y
c
o
m
pa
r
e
d
to
t
h
e
B
E
R
T
-
l
a
r
ge
b
a
s
e
l
i
ne
m
o
de
l
.
De
c
o
m
po
s
e
d
t
r
a
n
s
f
o
r
m
e
r
m
o
de
l
[
13]
e
nh
a
nc
e
s
t
i
m
e
a
n
d
m
e
m
o
r
y
e
f
f
i
c
i
e
nc
y
,
i
n
o
r
de
r
to
r
e
duc
e
t
h
e
c
o
m
p
l
e
xi
t
y
o
f
t
h
e
t
r
a
n
s
f
o
r
m
e
r
f
u
n
c
t
i
o
n
,
i
t
i
s
de
c
o
m
po
s
e
d
b
a
s
e
d
o
n
i
n
put
s
e
g
m
e
n
t
a
t
i
o
n
.
E
v
a
l
u
a
t
i
o
n
us
i
n
g
t
h
e
S
QuA
D
v
1.
1,
R
A
C
E
,
B
oo
l
Q,
M
NL
I
,
a
n
d
QQ
P
d
a
t
a
s
e
t
s
de
m
o
n
s
t
r
a
t
e
s
i
g
ni
f
i
c
a
n
t
i
m
pr
o
v
e
m
e
n
t
i
n
s
pe
e
d
a
n
d
m
e
m
o
r
y
e
f
f
i
c
i
e
n
c
y
up
t
o
4x
i
n
c
r
e
a
s
e
s
.
B
A
R
T
pr
e
-
tr
a
i
ne
d
m
o
de
l
[
19]
,
whi
c
h
c
o
m
bi
ne
s
B
i
-
d
i
r
e
c
t
i
o
n
a
l
a
nd
A
ut
o
-
R
e
gr
e
s
s
i
v
e
T
r
a
ns
f
o
r
m
e
r
m
o
de
l
s
i
s
a
de
n
o
i
s
i
ng
a
ut
o
e
n
c
o
de
r
wi
t
h
a
s
e
qu
e
n
c
e
-
to
-
s
e
que
n
c
e
m
o
de
l
.
T
h
e
m
o
de
l
a
c
hi
e
ve
s
t
h
e
hi
g
h
e
s
t
pe
r
f
o
r
m
a
n
c
e
o
n
t
h
e
S
QuA
D
da
t
a
s
e
t
us
i
n
g
t
e
x
t
i
nf
il
li
ng
de
n
o
i
s
i
ng
m
e
t
h
o
d
wi
t
h
pr
e
c
i
s
i
o
n
o
f
90.
8
F
1
s
c
o
r
e
.
C
h
u
n
g
e
t
al
.
[
20]
pr
o
p
o
s
e
s
a
pr
o
c
e
dur
e
f
o
r
c
r
e
a
t
i
n
g
m
u
l
t
i
li
ngua
l
v
o
c
a
b
u
l
a
r
i
e
s
by
c
o
m
bi
n
i
ng
s
e
pa
r
a
t
e
l
y
t
r
a
i
ne
d
v
o
c
a
b
u
l
a
r
i
e
s
f
r
o
m
m
u
l
t
i
p
l
e
l
a
n
g
ua
ge
c
l
us
t
e
r
de
r
i
v
a
t
i
o
n
s
.
T
hi
s
a
ppr
o
a
c
h
a
i
m
s
t
o
b
a
l
a
n
c
e
t
h
e
e
x
c
ha
n
ge
b
e
t
we
e
n
c
r
o
s
s
-
l
i
ngua
l
s
u
b
wo
r
ds
a
n
d
l
a
n
gua
ge
-
s
p
e
c
i
f
i
c
v
o
c
a
b
u
l
a
r
y
.
T
he
e
v
a
l
ua
t
i
o
n
r
e
s
u
l
t
s
o
f
t
hi
s
m
e
t
h
o
d
us
i
n
g
t
h
e
T
y
D
i
Q
A
,
XN
L
I
,
a
n
d
W
i
k
i
Ann
NE
R
da
t
a
s
e
t
s
s
h
o
w
v
a
r
yi
ng
pe
r
f
o
r
m
a
n
c
e
s
c
o
r
e
s
de
pe
n
d
i
ng
o
n
t
h
e
l
a
n
gu
a
ge
.
Ho
we
v
e
r
,
o
n
a
v
e
r
a
ge
,
t
h
e
m
e
t
h
o
d
a
c
hi
e
v
e
s
a
n
F
1
s
c
o
r
e
o
f
70.
1,
whi
c
h
i
s
2.
1
p
o
i
n
t
s
hi
g
h
e
r
t
h
a
n
t
h
e
i
ni
t
i
a
l
j
o
i
n
t
m
e
t
h
o
d'
s
F
1
s
c
o
r
e
o
f
68.
0.
Opt
i
mi
z
a
t
i
o
n
o
n
t
r
a
n
s
f
o
r
m
e
r
s
e
l
f
a
t
t
e
n
t
i
o
n
l
a
y
e
r
to
a
c
c
o
m
m
o
da
t
e
l
o
n
ge
r
s
e
que
n
c
e
s
l
e
n
gt
h
by
c
h
a
n
g
i
ng
t
h
e
dot
pr
o
duc
t
m
e
c
h
a
ni
s
m
o
n
t
h
e
s
e
l
f
a
tt
e
n
t
i
o
n
l
a
y
e
r
w
i
t
h
s
l
i
d
i
ng
w
i
ndo
ws
t
e
c
hni
qu
e
pr
opo
s
e
d
i
n
L
o
n
g
f
o
r
m
e
r
[
21]
.
T
h
e
s
e
l
f
a
t
t
e
n
t
i
o
n
m
e
c
h
a
ni
s
m
h
a
s
t
h
e
c
o
m
p
l
e
xi
t
y
o
f
O(
n
2)
,
whil
e
t
h
e
pr
o
p
o
s
e
d
l
o
ng
f
o
r
m
e
r
m
o
de
l
h
a
d
t
h
e
l
i
ne
a
r
c
o
m
p
l
e
xi
t
y
o
f
O(
n
)
.
T
h
e
e
v
a
l
ua
t
i
o
n
s
h
o
ws
a
n
i
m
pr
o
v
e
m
e
n
t
by
3
p
o
i
n
t
s
o
n
W
i
k
i
h
o
p,
1
po
i
n
t
o
n
T
r
i
vi
a
Q
A
a
n
d
Ho
t
p
ot
QA
c
o
m
pa
r
e
d
to
th
e
R
o
B
E
R
T
a
-
b
a
s
e
m
o
de
l
.
I
n
do
NL
G
[
14]
,
a
b
e
n
c
hm
a
r
k
f
o
r
NL
G
i
n
t
h
r
e
e
c
o
m
m
o
nly
u
s
e
d
I
n
do
n
e
s
i
a
n
l
a
n
gua
ge
s
:
B
a
h
a
s
a
I
n
do
n
e
s
i
a
,
S
un
d
a
,
a
n
d
J
a
wa
.
I
n
do
NL
G
i
n
c
l
ude
s
s
ix
e
v
a
l
ua
t
i
o
n
t
a
s
ks
:
MT
,
QG
,
S
um
m
a
r
i
z
a
t
i
o
n
,
C
hi
t
-
c
h
a
t
,
a
n
d
m
o
r
e
.
T
h
e
da
t
a
s
e
t
I
n
do
4B
-
P
l
us
i
s
us
e
d
to
p
r
e
-
t
r
a
i
n
t
h
e
I
n
do
B
AR
T
a
n
d
I
n
do
G
P
T
m
o
de
l
s
,
whi
c
h
a
c
hi
e
v
e
c
o
m
pe
t
i
t
i
v
e
r
e
s
u
l
t
s
w
i
t
h
1/5t
h
o
f
t
h
e
pa
r
a
m
e
t
e
r
s
c
om
pa
r
e
d
to
m
u
l
t
i
-
li
ngua
l
m
o
de
l
s
li
ke
m
B
AR
T
.
A
Q
G
s
y
s
tem
d
e
v
e
l
opm
e
n
t
f
or
th
e
I
n
d
on
e
s
i
a
n
l
a
n
g
u
a
g
e
[
2
2
]
u
s
i
n
g
th
e
S
Q
uA
D
v
2
d
a
ta
s
e
t,
w
h
i
c
h
h
a
s
b
e
e
n
tr
a
n
s
l
a
te
d
u
s
i
n
g
th
e
G
o
og
l
e
T
r
a
n
s
l
a
te
A
P
I
,
a
l
on
g
wi
t
h
a
d
di
t
i
on
a
l
T
y
Di
QA
d
e
v
d
a
ta
.
T
h
e
p
r
op
os
e
d
m
e
th
o
d
u
ti
l
i
z
e
s
a
s
e
q
u
e
n
c
e
-
to
-
s
e
q
u
e
n
c
e
a
p
p
r
oa
c
h
a
n
d
i
m
pl
e
m
e
n
ts
B
i
G
R
U
,
B
i
L
S
T
M
,
a
n
d
T
r
a
n
s
f
or
m
e
r
m
od
e
l
s
.
3.
M
E
T
HO
D
T
hi
s
s
t
udy
a
im
s
to
e
n
ha
n
c
e
t
h
e
s
t
a
t
e
-
of
-
t
h
e
-
a
r
t
I
n
do
B
A
R
T
m
o
de
l
f
o
r
t
h
e
Que
s
t
i
o
n
An
s
w
e
r
G
e
n
e
r
a
t
i
o
n
t
a
s
k.
T
hi
s
e
nh
a
nc
e
m
e
n
t
i
nv
o
l
v
e
s
t
h
e
s
ub
s
t
i
t
ut
i
o
n
o
f
I
n
do
B
AR
T
s
e
l
f
-
a
tt
e
n
t
i
o
n
m
e
c
h
a
ni
s
m
w
i
t
h
a
s
l
i
d
i
ng
w
i
n
do
w
a
tt
e
n
t
i
o
n
i
n
s
p
i
r
e
d
by
L
o
n
g
f
o
r
m
e
r
[
21]
.
T
h
e
r
e
s
e
a
r
c
h
i
s
o
r
ga
ni
z
e
d
i
n
t
o
t
h
r
e
e
s
e
que
n
t
i
a
l
s
t
a
ge
s
:
Da
t
a
P
r
e
p
r
o
c
e
s
s
i
ng,
M
o
de
l
M
o
di
f
i
c
a
t
i
o
n
,
a
n
d
T
r
a
i
ni
ng
a
n
d
E
v
a
l
ua
t
i
o
n
.
T
h
e
h
o
l
i
s
t
i
c
wo
r
kf
l
o
w
i
s
vi
s
ua
ll
y
de
p
i
c
t
e
d
i
n
F
i
gur
e
1.
C
o
l
l
e
c
t
i
n
g
da
t
a
:
B
a
s
e
d
o
n
F
i
gur
e
1,
S
QuA
D
V2
[
10]
a
n
d
T
y
D
i
Q
A
[
23]
publ
i
c
da
t
a
t
s
e
t
w
o
ul
d
be
c
o
l
l
e
c
t
e
d
f
r
o
m
publi
c
we
b
s
i
t
e
s
uc
h
a
s
ka
gg
l
e
o
r
h
ugg
i
nf
a
c
e
.
S
QuA
D
v
2
c
o
n
s
i
s
t
o
f
130.
000
t
r
a
i
n
a
nd
11.
900
v
a
li
da
t
i
o
n
que
s
t
i
o
n
-
a
ns
we
r
da
t
a
,
T
y
D
i
Q
A
o
n
t
h
e
ot
h
e
r
h
a
n
d
c
o
n
s
i
s
t
o
f
151.
000
tr
a
i
n
a
n
d
18.
700
v
a
l
i
da
t
i
o
n
que
s
t
i
o
n
-
a
ns
we
r
da
t
a
.
S
QuA
D
v
2
da
t
a
s
e
t
i
s
a
n
e
ng
l
i
s
h
da
t
a
s
e
t
,
t
h
e
r
e
f
o
r
e
tr
a
n
s
l
a
t
i
o
n
t
o
I
n
do
n
e
s
i
a
l
a
n
gua
ge
is
co
m
p
l
e
t
l
y
n
e
e
de
d.
I
n
c
o
n
t
r
a
s
t
T
y
D
i
Q
A
i
s
a
m
u
l
t
il
li
ngua
l
da
t
a
s
e
t
t
h
a
t
c
o
n
s
i
s
t
o
f
11
l
a
n
gua
ge
s
(
t
e
l
ugu
,
a
r
a
bi
c
,
s
wa
hil
i
,
j
a
p
a
n
e
s
e
,
f
i
nn
i
s
h
,
I
n
do
n
e
s
i
a
,
r
us
s
i
a
n
,
t
h
a
i
,
ko
r
e
a
n
,
b
e
n
ga
li
,
e
n
g
l
i
s
h)
.
T
h
e
pe
r
c
e
n
t
a
ge
o
f
I
n
do
n
e
s
i
a
l
a
n
gua
ge
i
n
t
y
d
i
qa
i
s
9%
,
a
ppr
o
xi
m
a
t
e
l
y
13.
000
t
r
a
i
n
a
n
d
1683
e
v
a
l
ua
t
i
o
n
.
He
n
c
e
,
f
o
r
T
y
D
i
Q
A
da
t
a
s
e
t
t
r
a
n
s
l
a
t
i
o
n
s
t
e
p
a
r
e
o
m
mi
t
e
d
a
n
d
o
nl
y
I
n
do
n
e
s
i
a
n
da
t
a
s
e
t
b
e
i
n
g
us
e
d.
T
r
a
n
s
l
a
t
i
n
g
e
n
g
l
i
s
h
d
a
t
a
:
S
QuA
D
v
2
da
t
a
s
e
t
w
o
ul
d
b
e
t
r
a
n
s
l
a
t
e
d
us
i
n
g
goo
gl
e
t
r
a
n
s
l
a
t
e
A
P
I
.
S
i
nc
e
t
h
e
da
t
a
s
e
t
que
s
t
i
o
n
,
a
n
s
w
e
r
a
n
d
c
o
n
t
e
x
t
pa
r
a
gr
a
ph
a
t
t
r
i
b
ut
e
a
r
e
t
r
a
n
s
l
a
t
e
d
s
e
pe
r
a
t
e
l
y
,
s
o
m
e
o
f
t
h
e
q
ue
s
t
i
o
n
-
a
ns
we
r
c
o
n
t
e
x
t
s
we
r
e
m
i
s
s
i
ng.
T
h
a
t
b
e
i
n
g
t
h
e
c
a
s
e
,
a
n
s
we
r
c
o
n
t
e
x
t
m
a
t
c
hi
ng
m
e
c
h
a
ni
s
m
[
24]
a
r
e
a
pp
l
i
e
d
a
s
s
e
e
n
i
n
F
i
gur
e
2.
F
uz
z
y
s
t
r
i
n
g
m
a
t
c
hi
ng
a
r
e
be
i
n
g
us
e
d
to
f
i
n
d
t
h
e
t
r
a
n
s
l
a
t
e
d
a
ns
we
r
o
n
t
h
e
tr
a
n
s
l
a
t
e
d
c
o
n
t
e
x
t
pa
r
a
gr
a
ph
,
unm
a
t
c
h
a
ns
we
r
wo
ul
d
b
e
r
e
p
l
a
c
e
wi
t
h
e
m
pt
y
s
t
r
i
n
g
a
n
d
-
1
v
a
l
u
e
a
r
e
a
ppe
n
d
to
t
h
e
t
r
a
n
s
l
a
t
e
d_a
n
s
we
r
_s
t
a
r
t
_p
o
s
i
t
i
o
n
ke
y
,
m
a
t
c
h
a
n
s
we
r
l
o
c
a
t
i
o
n
wo
u
l
d
b
e
a
ppe
n
d
e
d
to
t
h
e
t
r
a
n
s
l
a
t
e
d_a
n
s
we
r
_s
t
a
r
t
_p
o
s
i
t
i
o
n
ke
y
.
Da
t
a
pr
e
pr
o
c
e
s
s
i
n
g
:
I
n
da
t
a
pr
e
pr
o
c
e
s
s
i
n
g,
b
o
t
h
T
y
D
i
Q
A
a
n
d
t
r
a
n
s
l
a
t
e
d
S
QuA
D
v
2
w
i
t
h
o
ut
a
n
a
ns
we
r
o
r
h
a
vi
ng
-
1
v
a
l
ue
o
n
a
n
s
w
e
r
s
t
a
r
t
p
o
s
i
t
i
o
n
wo
u
l
d
b
e
r
e
m
o
v
e
d.
S
pe
c
i
a
l
t
o
ke
n
wo
ul
d
b
e
a
dd
e
d
to
a
dd
m
o
r
e
c
o
n
t
e
x
t
b
e
f
o
r
e
t
h
e
tr
a
i
ni
ng,
<
B
OS>
to
ke
n
wa
s
us
e
d
to
m
a
r
k
b
e
g
i
nn
i
ng
o
f
s
e
n
t
e
n
c
e
,
<
E
OS>
token
wa
s
us
e
d
to
m
a
r
k
e
n
d
o
f
s
e
n
t
e
n
c
e
,
<
S
E
P
>
token
wa
s
us
e
d
to
s
e
pe
r
a
t
e
e
a
c
h
c
o
n
t
e
x
t
o
n
t
h
e
s
e
n
t
e
n
c
e
.
T
he
o
v
e
r
a
l
l
s
t
r
uc
t
ur
e
o
f
t
h
e
i
n
put
t
e
x
t
wa
s
<
B
OS>
[
pa
r
a
gr
a
ph
c
o
n
t
e
x
t
]
<
S
E
P
>
[
que
s
t
i
o
n
]
<
E
OS>.
I
n
put
wo
ul
d
b
e
t
r
un
c
a
t
e
d
i
f
t
h
e
l
e
n
gt
h
e
x
c
e
e
ds
m
a
x
_
l
e
n
gt
h
hy
pe
r
pa
r
a
m
e
t
e
r
,
o
n
t
h
e
ot
h
e
r
h
a
n
d
pa
dd
i
ng
wo
ul
d
b
e
a
d
de
d
w
i
t
h
to
ke
e
p
c
o
n
s
i
s
t
e
n
t
l
e
n
gt
h
o
f
t
h
e
i
n
put
us
i
n
g
m
a
x
_
len
gt
h
s
t
r
a
t
e
g
y
to
t
h
e
r
e
s
t
o
f
t
h
e
da
t
a
s
e
t
.
P
r
o
c
c
e
s
s
e
d
da
t
a
s
e
t
wo
ul
d
b
e
t
o
ke
ni
z
e
d
o
n
wo
r
d
uni
t
us
i
n
g
I
n
do
NL
G
to
ke
ni
z
e
r
(
i
ndo
B
A
R
T
t
o
ke
ni
z
e
r
)
.
F
i
gur
e
3
i
ll
u
s
t
r
a
t
e
t
h
e
da
t
a
p
r
o
c
e
s
s
i
ng
o
f
m
o
de
l
i
nput
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t
J
I
n
f
&
C
o
m
m
u
n
T
e
c
hn
o
l
I
S
S
N:
2252
-
8776
I
ndoB
A
R
T
opti
miz
ati
on
f
or
que
s
ti
on
ans
w
e
r
ge
ne
r
ati
on
s
y
s
tem
w
it
h
longf
or
me
r
att
e
nti
on
(
P
e
ter
A
ndr
e
w
)
481
F
i
gur
e
1.
R
e
s
e
a
r
c
h
f
l
o
w
d
i
a
gr
a
m
F
i
gur
e
2
.
A
ns
we
r
-
c
o
n
t
e
x
t
m
a
t
c
hi
ng
f
l
o
w
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2252
-
8776
I
n
t
J
I
n
f
&
C
o
m
m
u
n
T
e
c
hn
o
l
,
Vo
l
.
1
4
,
N
o.
2
,
A
ugus
t
20
2
5
:
478
-
487
482
F
i
gur
e
3
.
Da
t
a
pr
o
c
e
s
s
i
n
g
e
xa
m
p
l
e
L
o
n
g
f
or
m
e
r
–
s
l
i
d
i
n
g
w
i
n
d
o
w
a
t
t
e
n
t
i
o
n
:
O
n
th
i
s
s
te
p
,
s
l
i
di
n
g
wi
n
d
ow
a
t
te
n
ti
on
m
odi
f
i
c
a
t
i
on
w
e
r
e
i
m
pl
e
m
e
n
te
d
b
a
s
e
d
on
L
on
gf
or
m
e
r
[
1
]
.
C
on
v
e
n
t
i
on
a
l
tr
a
n
s
f
or
m
e
r
s
e
l
f
-
a
t
te
n
ti
on
[
2
5
]
e
m
pl
o
y
s
th
e
m
a
tr
i
x
d
o
t
p
r
od
u
c
t
c
om
p
u
ta
ti
on
,
d
e
pi
c
te
d
i
n
(
1
)
,
r
e
s
ul
ti
n
g
i
n
O
(
n
2
)
c
om
pu
ta
ti
on
c
om
pl
e
x
i
t
y
f
or
e
a
c
h
l
a
y
e
r
.
I
n
(
1
)
a
t
te
n
ti
on
s
c
or
e
.
(
,
,
)
=
(
√
)
C
o
n
ve
r
s
e
ly
,
t
h
e
s
li
d
i
ng
w
i
n
do
ws
a
tt
e
n
t
i
o
n
pa
t
t
e
r
n
c
o
m
put
e
s
o
nl
y
n
e
i
g
hb
o
r
i
n
g
t
o
ke
n
s
w
i
t
h
t
h
e
f
i
xe
d
-
s
i
z
e
w
i
n
do
w
(
w
)
,
r
e
s
ul
t
i
n
g
i
n
O(
n
*
w)
or
O(
n
)
c
om
put
a
t
i
o
n
c
o
m
p
l
e
xi
t
y
.
T
hi
s
f
i
xe
d
-
s
i
z
e
w
i
ndo
w
s
c
a
l
e
do
wn
f
r
o
m
hi
g
h
e
r
l
a
y
e
r
t
o
l
o
we
r
l
a
y
e
r
.
F
o
r
t
hi
s
pa
r
t
i
c
u
l
a
r
r
e
s
e
a
r
c
h
,
t
h
e
w
i
ndo
w
s
i
z
e
wa
s
h
a
l
ve
d
(
1/2
w)
w
i
t
h
e
a
c
h
de
s
c
e
n
t
i
n
l
a
y
e
r
.
I
n
t
h
e
hi
g
h
e
r
l
a
y
e
r
s
,
a
l
a
r
ge
r
w
i
n
d
o
w
s
i
z
e
wa
s
a
pp
ly
t
o
c
a
p
t
ur
e
hi
g
h
-
l
e
ve
l
i
n
f
o
r
m
a
t
i
o
n
,
while
t
h
e
l
o
we
r
l
a
y
e
r
s
f
o
c
us
e
d
o
n
c
a
pt
u
r
i
n
g
l
o
c
a
l
c
o
n
t
e
x
t
ua
l
i
nf
o
r
m
a
t
i
o
n
.
A
dd
i
t
i
o
n
a
ll
y
,
T
h
e
r
e
duc
t
i
o
n
i
n
w
i
n
do
w
s
i
z
e
s
e
r
v
e
s
to
m
a
i
n
t
a
i
n
t
h
e
e
qu
i
li
br
i
u
m
be
t
we
e
n
e
f
f
i
c
i
e
n
c
y
a
n
d
pe
r
f
o
r
m
a
n
c
e
,
s
m
a
ll
e
r
w
i
n
do
w
s
i
z
e
s
i
n
c
ur
l
o
we
r
c
o
m
put
a
t
i
o
n
a
l
c
o
s
t
b
e
c
a
us
e
t
h
e
y
c
o
n
t
a
i
n
f
e
we
r
n
o
n
z
e
r
o
v
a
l
ue
s
,
t
h
us
e
nh
a
n
c
i
ng
e
f
f
i
c
i
e
nc
y
,
w
hil
e
l
a
r
ge
r
w
i
n
do
w
s
i
z
e
s
po
s
s
e
s
s
gr
e
a
t
e
r
r
e
pr
e
s
e
n
t
a
t
i
o
n
c
a
pa
c
i
t
y
a
n
d
o
f
t
e
n
r
e
s
u
l
t
i
n
pe
r
f
o
r
m
a
n
c
e
im
pr
o
v
e
m
e
n
t
s
.
T
h
e
c
o
m
put
a
t
i
o
n
c
o
m
pa
r
i
s
o
n
b
e
t
we
e
n
s
e
lf
-
a
tt
e
n
t
i
o
n
a
n
d
s
li
d
i
ng
w
i
ndo
w
a
tt
e
n
t
i
o
n
c
o
u
l
d
b
e
s
e
e
n
i
n
F
i
gur
e
4,
F
i
gur
e
4
(
a
)
i
ll
u
s
t
r
a
t
e
o
pe
r
a
t
i
o
n
o
n
c
o
m
put
i
n
g
a
tt
e
n
t
i
o
n
us
i
n
g
s
e
lf
-
a
tt
e
n
t
i
o
n
w
h
e
r
e
a
s
,
F
i
gur
e
4
(
b
)
s
h
o
wn
o
pe
r
a
t
i
o
n
o
n
c
o
m
put
i
n
g
a
tt
e
n
t
i
o
n
us
i
ng
s
li
d
i
ng
w
i
ndo
w
a
tt
e
n
t
i
o
n
.
(
a
)
(
b
)
F
i
gur
e
4
.
A
tt
e
n
t
i
o
n
m
e
c
h
a
ni
s
m
c
o
m
pa
r
i
s
o
n
i
ll
u
s
t
r
a
t
i
o
n
(
a
)
s
e
l
f
-
a
t
t
e
n
t
i
o
n
–
n
2
a
n
d
(
b
)
s
l
e
d
i
ng
w
i
ndo
w
a
tt
e
n
t
i
o
n
–
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t
J
I
n
f
&
C
o
m
m
u
n
T
e
c
hn
o
l
I
S
S
N:
2252
-
8776
I
ndoB
A
R
T
opti
miz
ati
on
f
or
que
s
ti
on
ans
w
e
r
ge
ne
r
ati
on
s
y
s
tem
w
it
h
longf
or
me
r
att
e
nti
on
(
P
e
ter
A
ndr
e
w
)
483
I
n
do
B
A
R
T
m
o
de
l
m
o
d
i
f
i
c
a
t
i
o
n
:
I
n
do
B
A
R
T
c
o
n
s
is
t
o
f
s
i
x
l
a
y
e
r
s
e
a
c
h
f
o
r
t
h
e
e
n
c
o
de
r
a
n
d
de
c
o
de
r
,
w
i
t
h
e
a
c
h
l
a
y
e
r
po
s
s
e
s
s
i
ng
i
t
s
o
wn
s
e
lf
-
a
t
t
e
n
t
i
o
n
m
o
du
l
e
.
T
h
e
r
e
f
o
r
e
,
t
h
e
L
o
n
g
f
o
r
m
e
r
s
li
d
i
ng
w
i
n
do
w
a
tt
e
n
t
i
o
n
m
o
du
l
e
i
s
e
m
p
l
o
y
e
d
to
r
e
pl
a
c
e
e
a
c
h
o
f
t
h
e
s
e
l
a
y
e
r
s
.
T
o
pr
e
s
e
r
v
e
t
h
e
pr
e
-
tr
a
i
ne
d
w
e
i
g
h
t
s
o
f
t
h
e
I
n
do
B
A
R
T
s
e
lf
-
a
tt
e
n
t
i
o
n
m
o
du
l
e
,
t
h
e
we
i
g
h
t
v
a
l
u
e
s
a
r
e
c
o
pi
e
d
to
e
a
c
h
L
o
n
g
f
o
r
m
e
r
a
tt
e
n
t
i
o
n
m
o
du
l
e
b
e
f
o
r
e
t
h
e
r
e
pl
a
c
e
m
e
n
t
o
c
c
ur
s
.
B
ot
h
t
h
e
b
a
s
e
m
o
de
l
a
n
d
t
h
e
L
o
n
g
f
o
r
m
e
r
-
m
o
d
i
f
i
e
d
m
o
de
l
a
r
e
f
i
ne
-
t
un
e
d
u
s
i
n
g
t
h
e
pr
o
c
e
s
s
e
d
da
t
a
s
e
t
,
que
s
t
i
o
n
s
a
n
d
c
o
n
t
e
x
t
pa
r
a
gr
a
ph
s
s
e
r
v
e
a
s
i
n
put
,
whi
l
e
a
n
s
we
r
s
a
r
e
us
e
d
a
s
o
u
t
pu
t.
F
i
ne
-
t
un
e
m
o
de
l
:
B
ot
h
t
h
e
b
a
s
e
a
n
d
m
o
d
i
f
i
e
d
m
o
de
l
s
a
r
e
b
e
i
ng
f
i
ne
-
t
un
e
d
s
e
pa
r
a
t
e
l
y
f
o
r
e
a
c
h
da
t
a
s
e
t.
Dur
i
n
g
t
h
e
f
i
ne
-
t
uni
n
g
p
h
a
s
e
,
t
h
e
t
r
a
i
ni
n
g
da
t
a
s
e
t
i
s
s
p
li
t
w
i
t
h
a
n
80:20
r
a
t
i
o
b
e
t
we
e
n
t
r
a
i
ni
ng
a
n
d
t
e
s
t
i
n
g
da
t
a
.
Da
t
a
h
a
s
a
l
r
e
a
d
y
b
e
e
n
to
ke
ni
z
e
d
i
n
a
pr
i
o
r
pr
o
c
e
s
s
u
t
i
li
z
i
ng
I
n
do
NL
GT
o
ke
ni
z
e
r
,
m
a
k
i
n
g
i
t
r
e
a
dy
to
b
e
d
i
r
e
c
t
l
y
us
e
d
a
s
i
nput
f
o
r
t
h
e
m
o
de
l
.
T
h
e
m
o
de
l
ge
n
e
r
a
t
e
s
to
ke
ni
z
e
d
o
ut
pu
t,
whi
c
h
u
n
d
e
r
go
e
s
a
de
to
ke
ni
z
a
t
i
o
n
pr
o
c
e
s
s
us
i
n
g
I
n
do
N
L
G
to
c
o
n
v
e
r
t
i
t
i
n
t
o
s
t
r
i
n
g
f
o
r
m
a
t
.
T
o
e
n
s
ur
e
f
a
i
r
b
e
nc
hm
a
r
k
i
n
g,
b
ot
h
m
o
de
l
s
a
r
e
f
i
ne
-
t
un
e
d
us
i
ng
t
h
e
s
a
m
e
hy
pe
r
pa
r
a
m
e
t
e
r
s
a
s
pr
e
s
e
n
t
e
d
i
n
T
a
bl
e
1.
T
h
e
L
o
n
g
f
o
r
m
e
r
-
m
o
d
i
f
i
e
d
m
o
de
l
h
a
s
t
h
e
a
ut
or
e
gr
e
s
s
i
v
e
f
e
a
t
ur
e
di
s
a
bl
e
d
by
de
f
a
u
l
t
,
whi
l
e
I
n
do
B
AR
T
po
s
s
e
s
s
e
s
t
h
e
a
ut
or
e
gr
e
s
s
i
v
e
f
e
a
t
ur
e
.
T
h
e
r
e
f
o
r
e
,
t
hi
s
r
e
s
e
a
r
c
h
w
i
ll
c
o
n
duc
t
L
o
n
g
f
o
r
m
e
r
-
m
o
d
i
f
i
e
d
t
r
a
i
ni
n
g
t
w
i
c
e
,
o
n
c
e
w
i
t
h
a
n
d
o
n
c
e
w
i
t
h
o
ut
t
h
e
a
uto
r
e
g
r
e
s
s
i
ve
f
e
a
t
ur
e
,
to
e
n
s
ur
e
t
h
o
r
ough
s
t
ud
y
.
T
a
bl
e
1
.
Hy
p
e
r
pa
r
a
m
e
t
e
r
H
y
p
e
r
pa
r
a
m
e
t
e
r
V
a
lu
e
T
o
k
e
ni
z
e
r
e
mb
e
ddi
ng s
iz
e
1024
L
e
a
r
ni
ng
r
a
te
2e
-
5
D
r
o
p
o
ut
r
a
te
0.1
T
r
a
in
in
g ba
tc
h
3
E
v
a
lu
a
ti
o
n ba
t
c
h
4
T
r
a
in
in
g e
p
oc
h
2
E
val
u
at
ion
:
E
a
c
h
m
o
de
l
w
il
l
u
n
de
r
go
s
e
pa
r
a
t
e
t
r
a
i
ni
ng
a
n
d
e
v
a
l
u
a
t
i
o
n
u
s
i
ng
t
h
e
r
e
s
pe
c
t
i
v
e
da
t
a
s
e
t
s
.
M
o
de
l
a
c
c
ur
a
c
y
w
il
l
be
a
s
s
e
s
s
e
d
us
i
n
g
F
1,
E
x
a
c
t
M
a
t
c
h
,
B
L
E
U,
a
n
d
R
OU
GE
m
e
t
r
i
c
s
.
T
r
a
c
k
i
n
g
t
r
a
i
ni
ng
t
i
m
e
w
i
ll
b
e
im
p
l
e
m
e
n
t
e
d
to
b
e
nc
hm
a
r
k
t
h
e
o
p
t
i
m
i
z
a
t
i
o
n
o
f
a
tt
e
n
t
i
o
n
l
a
y
e
r
c
o
m
p
l
e
xi
t
y
.
F
ur
t
h
e
r
e
va
l
ua
t
i
o
n
de
t
a
i
l
s
a
r
e
a
v
a
il
a
bl
e
i
n
s
e
c
t
i
o
n
4.
3.
4.
R
E
S
U
L
T
A
N
D
D
I
S
C
U
S
S
I
O
N
4.
1.
Dat
a
p
r
e
p
r
o
c
e
s
s
in
g
T
h
e
S
QuA
D
v
2
da
t
a
s
e
t
a
r
e
t
r
a
n
s
l
a
t
e
d
f
r
o
m
e
n
g
l
is
h
l
a
n
gua
g
e
to
I
n
do
n
e
s
i
a
l
a
n
gua
g
e
us
i
ng
goo
gl
e
t
r
a
n
s
l
a
t
e
A
P
I
,
E
x
a
m
p
l
e
o
f
t
r
a
n
s
l
a
t
e
d
S
QuA
D
v
2
a
n
d
T
y
D
i
Q
A
c
o
u
l
d
b
e
s
e
e
n
i
n
T
a
bl
e
2.
T
h
e
n
t
r
a
n
s
l
a
t
e
d
to
m
a
ke
s
ur
e
tr
a
n
s
l
a
t
e
d
a
n
s
we
r
a
n
d
que
s
t
i
o
n
h
a
v
e
a
m
a
c
t
hi
ng
c
o
n
t
e
x
t
o
n
t
h
e
c
o
n
t
e
x
t
p
a
r
a
gr
a
ph
,
F
uz
z
y
s
t
r
i
ng
m
a
t
c
hi
ng
a
r
e
pe
r
f
o
r
m
e
d,
to
c
o
m
pa
r
e
t
h
e
a
ns
we
r
w
i
t
h
c
o
n
t
e
x
t
pa
r
a
gr
a
ph
.
W
h
e
n
t
h
e
a
n
s
w
e
r
do
e
s
n
’
t
m
a
t
c
h
a
ny
s
t
r
i
n
g
i
n
t
h
e
c
o
n
t
e
x
t
pa
r
a
gr
a
ph
t
h
e
da
t
a
r
o
w
a
r
e
de
l
e
t
e
d.
Af
t
e
r
pe
r
f
o
r
m
i
ng
f
uz
z
y
s
t
r
i
n
g
m
a
t
c
hi
ng,
t
h
e
r
e
i
s
a
l
o
t
o
f
da
t
a
p
o
i
n
t
t
h
a
t
di
d
n’
t
h
a
ve
m
a
c
t
hi
ng
a
n
s
w
e
r
on
t
h
e
c
o
n
t
e
x
t
pa
r
a
gr
a
ph
,
r
e
s
u
l
t
i
n
g
i
n
da
t
a
s
e
t
s
i
z
e
r
e
duc
t
i
o
n
f
r
o
m
130.
000
tr
a
i
n
da
t
a
to
82
.
000
da
t
a
a
n
d
11.
900
v
a
li
da
t
i
o
n
da
t
a
to
10
.
900
da
t
a
.
F
o
r
t
h
e
T
y
D
i
Q
A
da
t
a
s
e
t
,
o
r
i
g
i
na
l
da
t
a
s
e
t
a
l
r
e
a
d
y
pr
o
vi
de
d
s
o
m
e
da
t
a
i
n
I
n
do
n
e
s
i
a
l
a
n
gu
a
ge
,
h
e
n
c
e
da
t
a
s
e
t
t
h
a
t
a
r
e
us
e
d
i
n
t
hi
s
r
e
s
e
a
r
c
h
o
nly
t
oo
k
t
h
e
i
ndo
n
e
s
i
a
n
l
a
n
gu
a
ge
po
r
t
i
o
n
o
f
t
h
e
da
t
a
s
e
t
.
T
h
e
n
u
m
be
r
o
f
da
t
a
i
n
I
n
do
ne
s
i
a
l
a
n
gua
ge
a
r
e
13.
500
t
r
a
i
n
da
t
a
a
n
d
1.
800
v
a
li
da
t
i
o
n
da
t
a
.
A
ns
we
r
v
a
li
da
t
i
o
n
a
r
e
p
e
r
f
o
r
m
e
d
to
m
a
ke
s
ur
e
e
v
e
r
y
da
t
a
p
o
i
n
t
h
a
v
e
a
n
a
n
s
w
e
r
o
n
th
e
c
o
n
t
e
x
t
pa
r
a
gr
a
ph
.
Up
o
n
v
a
l
i
da
t
i
n
g,
t
h
e
n
u
m
b
e
r
o
f
da
t
a
t
h
a
t
di
d
n
’
t
ha
d
a
n
a
n
s
w
e
r
a
r
e
a
l
o
t
,
r
e
s
u
l
t
i
n
g
in
qu
i
t
e
h
uge
da
t
a
r
e
duc
t
i
o
n
t
o
5
.
700
t
r
a
i
n
da
t
a
a
n
d
550
v
a
li
da
t
i
o
n
da
t
a
.
T
h
e
n
t
h
e
da
t
a
a
r
e
b
e
i
ng
f
o
r
m
a
t
t
e
d
to
s
pe
s
i
f
i
c
f
o
r
m
a
t
to
m
a
k
e
a
unif
o
r
m
l
e
a
r
ni
ng
p
i
pe
li
ne
w
i
t
h
S
QuA
D
Da
t
a
s
e
t
.
E
x
a
m
p
l
e
o
f
T
y
D
i
Q
A
da
t
a
s
e
t
t
h
a
t
a
r
e
b
e
i
ng
us
e
d
i
n
t
hi
s
r
e
s
e
a
r
c
h
c
o
u
l
d
b
e
s
e
e
n
i
n
T
a
bl
e
3.
T
a
bl
e
2
.
T
r
a
n
s
l
a
t
e
d
S
QuA
D
v
2
e
x
a
m
p
l
e
T
it
l
e
C
o
nt
e
x
t
Q
ue
s
ti
o
n
I
ndo
n
e
s
ia
n_a
ns
w
e
r
B
e
y
on
c
e
B
e
y
onc
é
G
is
e
ll
e
K
now
le
s
-
C
ar
te
r
(
/
bi
ːˈ
jɒ
ns
e
ɪ
/
be
e
-
Y
O
N
-
s
ay
)
(
la
hi
r
4 Se
pt
e
m
be
r
1981)
adalah
pe
ny
any
i,
pe
nul
is
l
agu, pr
odu
s
e
r
dan ak
tr
is
r
e
k
am
an A
m
e
r
i
k
a...
K
apan B
e
y
onc
e
m
ul
ai
m
e
nj
adi
popule
r
?
{ "
ans
w
e
r
_s
ta
r
t"
:
291,
"
te
x
t"
:
"
pada ak
hi
r
1990
-
an"
}
K
o
ta
N
e
w
Y
o
r
k
N
e
w
Y
or
k
—
s
e
r
in
g di
s
e
but
N
e
w
Y
or
k
C
it
y
at
au
K
ot
a N
e
w
Y
or
k
unt
uk
m
e
m
be
dak
anny
a dar
i
N
e
gar
a B
agi
an N
e
w
Y
or
k
...
K
ot
a apa di A
m
e
r
ik
a Se
r
ik
at
y
ang me
m
il
ik
i
populas
i
te
r
ti
nggi
?
{ "
ans
w
e
r
_s
ta
r
t"
:
0,
"
te
x
t"
:
"
N
e
w
Y
or
k
"
}
F
r
é
dé
r
ic
C
ho
pi
n
F
r
é
dé
r
ic
F
r
anç
oi
s
C
hopi
n (
22
F
e
br
uar
i
at
au 1
M
ar
e
t
1810
-
17 O
k
to
be
r
1849)
, k
e
la
hi
r
an
F
r
y
de
r
y
k
F
r
anc
is
z
e
k
C
hopi
n ...
B
agai
m
ana k
e
w
ar
gane
gar
aan
F
r
é
dé
r
ic
?
{ "
ans
w
e
r
_s
ta
r
t"
:
201,
"
te
x
t"
:
"
P
ol
andi
a dan k
om
pos
e
r
P
r
anc
is
"
}
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2252
-
8776
I
n
t
J
I
n
f
&
C
o
m
m
u
n
T
e
c
hn
o
l
,
Vo
l
.
1
4
,
N
o.
2
,
A
ugus
t
20
2
5
:
478
-
487
484
T
a
bl
e
3
.
T
y
D
i
Q
A
I
n
do
n
e
s
i
a
e
x
a
m
p
l
e
T
it
l
e
C
o
nt
e
x
t
Q
ue
s
ti
o
n
I
ndo
n
e
s
ia
n a
ns
w
e
r
F
e
r
na
nd
o
d
e
M
a
ge
lh
a
e
ns
Say
angny
a R
aj
a P
or
tu
gi
s
J
ohn, te
r
bunuh
pada tahun 1495 da
n
P
ange
r
an M
anue
l,
y
ang le
bi
h be
r
m
in
at
ak
an ha
r
ta
s
e
bal
ik
ny
a
dar
ip
ada pe
nj
e
la
ja
han, naik
t
ak
ht
a...
K
apan pe
r
dagangan me
la
lu
i
ar
m
ada mulai di
la
k
uk
an ole
h
bang
s
a E
r
opa ?
{ "
ans
w
e
r
_s
ta
r
t"
:
453,
"
te
x
t"
:
"
1505
"
}
B
a
nda
r
P
a
s
ir
M
a
ndo
ge
,
A
s
a
ha
n
B
andar
P
as
ir
M
andoge
adalah s
e
buah
k
e
c
am
at
an di K
abupate
n A
s
ahan, Sumate
r
a
U
ta
r
a, I
ndone
s
ia
.
D
imana le
ta
k
dae
r
ah
"
P
ar
de
m
banan"
?
{ "
ans
w
e
r
_s
ta
r
t"
:
49,
"
te
x
t"
:
"
K
abupate
n
A
s
ahan, Sumate
r
a
U
ta
r
a, I
ndone
s
ia
"
}
G
ur
un
S
a
ha
r
a
Sahar
a t
e
r
le
ta
k
di
ut
ar
a A
f
r
ik
a dan b
e
r
u
s
ia
2,5 j
ut
a t
ahun.
P
adang pas
ir
i
ni
m
e
m
be
nt
ang
dar
i
Sam
udr
a A
tl
ant
ik
k
e
L
aut
M
e
r
ah...
B
e
r
apak
ah L
uas
G
ur
un
Sahar
a ?
{ "
ans
w
e
r
_s
ta
r
t"
:
437,
"
te
x
t"
:
"
9.000.000k
m
2"
}
4.
2
.
M
od
e
l
f
in
e
-
t
u
n
in
g
T
h
e
i
n
put
a
n
d
o
ut
pu
t
s
a
m
p
l
e
s
f
o
r
e
a
c
h
m
o
de
l
a
r
e
pr
e
s
e
n
t
e
d
i
n
T
a
bl
e
4
f
o
r
t
h
e
S
QuA
D
v
2
da
t
a
s
e
t
a
n
d
T
a
bl
e
5
f
o
r
t
h
e
T
y
D
i
Q
A
da
t
a
s
e
t
.
I
n
b
ot
h
i
ns
t
a
n
c
e
s
,
t
h
e
i
n
put
c
o
m
pr
i
s
e
s
t
wo
pr
i
m
a
r
y
a
tt
r
i
b
ut
e
s
:
t
h
e
"
c
o
n
t
e
x
t
pa
r
a
gr
a
ph
"
a
n
d
t
h
e
"
que
s
t
i
o
n
,
"
w
hi
c
h
a
r
e
de
li
ne
a
t
e
d
by
a
<
s
e
p>
to
ke
n
to
f
a
c
il
i
t
a
t
e
s
e
pa
r
a
t
i
o
n
.
C
o
nv
e
r
s
e
ly
,
t
h
e
o
u
t
pu
t
pe
r
t
a
i
ns
to
t
h
e
"
a
n
s
we
r
"
a
t
t
r
i
b
ut
e
.
T
a
bl
e
4
.
S
QuA
D
v
2
i
n
put
,
t
a
r
ge
t
a
n
d
o
u
t
pu
t
c
o
m
p
a
r
i
s
o
n
e
x
a
m
p
l
e
M
o
de
l
E
x
a
mpl
e
I
nput
<
B
O
S
>
Se
ge
r
a s
e
te
la
h N
or
m
andi
a m
ul
ai
m
e
m
as
uk
i
I
ta
li
a, m
e
r
e
k
a m
e
m
as
u
k
i
K
e
k
ai
s
ar
an
B
iz
ant
iu
m
dan k
e
m
udi
an A
r
m
e
ni
a, be
r
te
m
pu
r
m
e
la
w
an P
e
c
he
ne
g, B
ul
gar
ia
, dan te
r
ut
am
a T
ur
k
i
Se
lj
uk
. T
e
nt
ar
a bay
ar
an
N
or
m
an pe
r
ta
m
a k
al
i
di
dor
ong untuk
dat
ang k
e
s
e
la
ta
n ol
e
h or
ang
-
or
ang L
om
bar
d untuk
be
r
ti
ndak
m
e
la
w
an B
iz
ant
iu
m
, t
e
ta
pi
m
e
r
e
k
a s
e
ge
r
a b
e
r
pe
r
ang dalam
di
nas
B
iz
ant
iu
m
di
Si
s
il
ia
. M
e
r
e
k
a m
e
nonj
ol
di
s
am
pi
ng
k
ont
in
ge
n V
ar
angi
an dan L
om
bar
di
a
dal
am
k
am
pany
e
Si
s
il
ia
G
e
o
r
ge
M
ani
ac
e
s
pada 1038
–
40. A
da
pe
r
de
bat
an apak
ah or
ang
N
or
m
andi
a dalam dinas
Y
unani s
e
be
n
ar
ny
a b
e
r
as
al
da
r
i
N
or
m
an I
ta
li
a, dan s
e
k
ar
ang tampak
ny
a
hany
a s
e
di
k
it
y
ang datang dar
i
s
ana. J
uga ti
dak
di
k
e
ta
hui
be
r
a
pa bany
ak
"
k
aum
F
r
ank
"
,
s
e
bagaimana or
ang
-
or
ang B
iz
ant
iu
m
m
e
n
y
e
but
ny
a, adalah or
a
ng
-
or
ang N
or
m
andi
a dan buk
an
or
ang P
r
anc
is
l
ai
nny
a.<SE
P
>
Si
apa y
ang be
r
pe
r
ang me
la
w
an N
or
m
andi
a di
I
ta
li
a?<
E
O
S
>
T
a
r
ge
t
P
e
c
he
ne
gs
, par
a B
ul
gar
ia
, dan te
r
ut
am
a or
ang
-
or
ang T
ur
k
i
Se
l
ju
k
I
ndoB
A
R
T
-
ba
s
e
o
u
tp
ut
pe
c
he
n
e
g, bulga
r
ia
L
o
ng
f
or
m
e
r
-
I
nd
oB
A
R
T
o
ut
put
pe
c
he
n
e
g
L
o
ng
f
or
m
e
r
-
I
nd
oB
A
R
T
–
a
ut
o
r
e
gr
e
s
s
iv
e
o
ut
put
pe
c
he
n
e
g, bulga
r
ia
T
a
bl
e
5
.
T
y
D
i
Q
A
i
n
put
,
t
a
r
ge
t
,
a
n
d
o
u
t
pu
t
c
o
m
pa
r
is
o
n
e
x
a
m
p
l
e
M
o
de
l
E
x
a
mpl
e
I
nput
<
B
O
S
>
H
ir
a
ga
na
(
K
a
na
:
ひ
ら
が
な
;
K
a
nj
i:
平仮名
)
ada
la
h s
uat
u c
ar
a pe
nul
is
an baha
s
a J
e
pang
dan me
w
ak
il
i
s
e
but
an s
uk
uk
at
a. P
ada mas
a s
il
am
, i
a j
uga dik
e
nal
i
s
e
bagai
o
nna
de
(
女手
)
at
au
'
tu
li
s
an w
ani
ta
'
k
ar
e
na bias
a di
gunak
an ol
e
h k
aum
w
ani
ta
. K
aum
l
e
la
k
i
pada mas
a i
tu
m
e
nul
is
m
e
nggunak
an t
ul
is
an K
anj
i
dan K
at
ak
ana. Hi
r
agana mulai di
gunak
an s
e
c
a
r
a l
uas
pada abad k
e
-
10 M
as
e
hi
.<
S
E
P
>
apak
ah y
ang dimak
s
ud d
e
ngan Hir
ag
ana
?
<
E
O
S
>
T
a
r
ge
t
c
ar
a pe
nul
is
an baha
s
a J
e
pang dan me
w
ak
il
i
s
e
but
an
s
uk
uk
at
a
I
ndoB
A
R
T
-
ba
s
e
o
u
tp
ut
pe
nul
is
an abad k
e
-
10 m
as
e
hi
L
o
ng
f
or
m
e
r
-
I
nd
oB
A
R
T
o
ut
put
c
ar
a pe
nul
is
an baha
s
a j
e
pang
L
o
ng
f
or
m
e
r
-
I
nd
oB
A
R
T
–
a
ut
o
r
e
gr
e
s
s
iv
e
o
ut
put
c
ar
a pe
nul
is
an baha
s
a
je
pang
4.
3.
E
val
u
at
ion
T
h
e
e
v
a
l
ua
t
i
o
n
pha
s
e
we
r
e
b
e
n
c
hm
a
r
k
us
i
n
g
t
h
e
F
1
-
s
c
o
r
e
,
E
x
a
c
t
M
a
t
c
h
,
B
L
E
U,
a
n
d
R
OU
GE
e
v
a
l
ua
t
i
o
n
m
e
t
r
i
c
f
o
r
e
a
c
h
m
o
de
l
a
n
d
da
t
a
s
e
t
.
E
v
a
l
ua
t
i
o
n
r
e
s
u
l
t
c
o
u
l
d
be
s
e
e
n
i
n
T
a
bl
e
6
f
o
r
S
QuA
D
da
t
a
s
e
t
a
n
d
T
a
bl
e
7
f
o
r
T
y
D
i
Q
A
da
t
a
s
e
t
.
I
n
do
B
A
R
T
m
o
de
l
b
a
s
e
o
n
m
B
A
R
T
m
o
de
l
w
hi
c
h
by
de
f
a
u
l
t
we
r
e
us
i
n
g
a
uto
-
r
e
gr
e
s
s
i
v
e
f
e
a
t
ur
e
o
f
B
A
R
T
,
On
t
h
e
o
t
h
e
r
h
a
n
d
t
h
e
l
o
n
g
f
o
r
m
e
r
a
t
t
e
n
t
i
o
n
h
a
d
t
h
e
o
pt
i
o
n
to
di
s
a
bl
e
d
t
h
e
a
uto
-
r
e
gr
e
s
s
i
v
e
o
f
t
h
e
m
o
de
l
,
t
h
e
r
e
f
o
r
e
a
utor
e
gr
e
s
s
i
ve
wo
u
l
d
b
e
o
n
o
f
t
h
e
v
a
r
i
a
t
i
o
n
o
f
t
h
e
m
o
d
i
f
i
e
d
mo
de
l
.
T
a
bl
e
6
.
S
QuA
D
V2
e
v
a
l
ua
t
i
o
n
r
e
s
u
l
t
M
o
de
l
na
m
e
E
x
a
c
t
ma
t
c
h
F1
B
L
E
U
R
O
U
G
E
-
L
R
O
U
G
E
-
1
R
O
U
G
E
-
2
I
ndoB
A
R
T
-
ba
s
e
35.06
54.04
0.054
0.529
0.53
0.282
L
on
gf
o
r
m
e
r
-
I
n
d
o
B
A
R
T
34.81
53.48
0.0531
0.524
0.525
0.277
L
on
gf
o
r
m
e
r
-
I
n
d
o
B
A
R
T
-
a
u
t
o
r
e
gr
e
s
s
iv
e
34.91
53.68
0.0536
0.526
0.527
0.28
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t
J
I
n
f
&
C
o
m
m
u
n
T
e
c
hn
o
l
I
S
S
N:
2252
-
8776
I
ndoB
A
R
T
opti
miz
ati
on
f
or
que
s
ti
on
ans
w
e
r
ge
ne
r
ati
on
s
y
s
tem
w
it
h
longf
or
me
r
att
e
nti
on
(
P
e
ter
A
ndr
e
w
)
485
T
a
bl
e
7
.
T
y
D
i
Q
A
e
v
a
l
ua
t
i
o
n
r
e
s
u
l
t
M
o
de
l
na
m
e
E
x
a
c
t
ma
t
c
h
F1
B
L
E
U
R
O
U
G
E
-
L
R
O
U
G
E
-
1
R
O
U
G
E
-
2
I
ndoB
A
R
T
-
ba
s
e
28.49
39.94
0.061
0.39
0.39
0.27
L
on
gf
o
r
m
e
r
-
I
n
d
o
B
A
R
T
34.69
48.92
0.081
0.48
0.48
0.31
L
on
gf
o
r
m
e
r
-
I
n
d
o
B
A
R
T
-
a
u
t
o
r
e
gr
e
s
s
iv
e
34.86
50.81
0.1
0.50
0.50
0.34
B
a
s
e
d
o
n
T
a
bl
e
6,
b
a
s
e
-
i
n
do
B
A
R
T
m
o
de
l
pe
r
f
o
r
m
s
l
i
g
h
t
l
y
b
e
t
t
e
r
t
h
a
n
l
o
n
g
f
o
r
m
e
r
-
i
ndo
B
A
R
T
m
o
de
l
a
c
r
o
s
s
a
l
l
e
v
a
l
ua
t
i
o
n
m
e
t
r
i
c
o
n
t
r
a
n
s
l
a
t
e
d
S
QuA
D
v
2
da
t
a
s
e
t
,
m
o
s
t
s
i
g
ni
f
i
c
a
n
t
d
i
f
f
e
r
e
n
c
e
o
f
0.
4
s
e
e
n
i
n
F
1
-
s
c
o
r
e
.
W
h
e
r
e
a
s
,
l
o
n
g
f
o
r
m
e
r
-
I
n
do
B
A
R
T
a
c
hi
e
v
e
d
o
u
t
s
t
a
n
d
i
n
g
r
e
s
u
l
t
o
n
T
y
D
i
Q
A
da
t
a
s
e
t
(
T
a
bl
e
7)
i
n
c
o
n
t
r
a
s
t
to
b
a
s
e
-
i
n
do
B
AR
T
.
L
o
n
g
f
o
r
m
e
r
-
I
n
do
B
A
R
T
o
u
tm
a
t
c
h
b
a
s
e
-
i
n
do
B
A
R
T
m
o
de
l
o
n
e
v
e
r
y
e
v
a
l
ua
t
i
o
n
m
e
t
r
i
c
,
l
o
n
g
f
o
r
m
e
r
-
I
n
do
B
A
R
T
m
o
s
t
n
ot
a
bl
e
a
d
v
a
n
c
e
m
e
n
t
s
h
o
wn
i
n
F
1
-
s
c
o
r
e
,
i
t
o
u
t
pe
r
f
o
r
m
ba
s
e
-
i
ndo
B
A
R
T
b
y
25%
.
L
o
n
g
f
o
r
m
e
r
-
i
ndo
B
A
R
T
m
o
de
l
w
i
t
h
a
uto
r
e
g
r
e
s
s
i
ve
a
ppe
a
r
to
pe
r
f
o
r
m
b
e
t
t
e
r
t
h
e
n
wi
t
h
o
ut
a
uto
r
e
gr
e
s
s
i
v
e
o
n
b
ot
h
da
t
a
s
e
t,
I
t
s
h
o
wn
a
uto
r
e
gr
e
s
s
i
ve
f
e
a
t
ur
e
ge
n
e
r
a
l
ly
p
e
r
f
o
r
m
b
e
tt
e
r
o
n
Que
s
t
i
o
n
Ans
we
r
i
n
g
t
a
s
k.
T
y
D
i
Q
A
ge
n
e
r
a
ll
y
h
a
d
l
o
n
ge
r
i
n
put
pa
r
a
g
r
a
ph
s
e
que
n
c
e
a
n
d
o
u
t
pu
t
a
n
s
we
r
s
e
que
n
c
e
,
i
n
t
h
o
s
e
c
o
n
d
i
t
i
o
n
l
o
n
g
f
o
r
m
e
r
-
i
n
do
B
AR
T
m
o
de
l
c
o
u
l
d
pe
r
f
o
r
m
b
e
t
t
e
r
t
h
a
n
b
a
s
e
-
i
ndo
B
A
R
T
m
o
de
l
.
M
o
r
e
o
v
e
r
,
s
o
m
e
c
o
n
t
e
x
t
m
i
g
h
t
l
o
s
t
i
n
tr
a
n
s
l
a
t
i
o
n
f
o
r
S
QuA
D
v
2
da
t
a
s
e
t
.
I
n
t
h
i
s
c
a
s
e
s
,
b
a
s
e
-
i
ndo
B
AR
T
f
u
ll
s
e
l
f
-
a
tt
e
n
t
i
o
n
pr
e
s
u
m
a
bly
h
a
v
e
b
e
t
t
e
r
c
o
n
t
e
x
t
un
de
r
s
t
a
n
d
i
n
g
th
e
n
s
li
d
i
ng
-
w
i
n
do
w
a
tt
e
n
t
i
o
n
o
n
l
o
n
g
f
o
r
m
e
r
-
i
nd
o
B
A
R
T
m
o
de
l
,
a
s
i
t
c
h
e
c
k
a
l
l
o
f
t
h
e
s
e
que
n
c
e
s
c
o
m
pa
r
e
d
to
c
h
e
c
k
i
n
g
o
n
t
h
e
s
l
i
d
i
ng
w
i
n
do
w
r
a
n
ge
.
T
h
e
gr
a
ph
i
n
F
i
gur
e
s
5
a
n
d
6
i
ll
us
t
r
a
t
e
s
a
c
o
m
pa
r
i
s
o
n
o
f
t
r
a
i
ni
ng
t
i
m
e
s
a
c
r
o
s
s
a
l
l
m
o
de
l
s
f
o
r
e
a
c
h
da
t
a
s
e
t.
F
i
gur
e
6
i
n
d
i
c
a
t
e
t
h
e
t
r
a
i
ni
ng
t
i
m
e
f
o
r
t
h
e
S
QuA
D
da
t
a
s
e
t
,
wh
e
r
e
t
h
e
I
n
do
B
A
R
T
-
b
a
s
e
m
o
de
l
t
r
a
i
n
e
d
a
ppr
o
xi
m
a
t
e
l
y
1.
5
t
i
m
e
s
f
a
s
t
e
r
t
h
a
n
t
h
e
m
o
d
i
f
i
e
d
L
o
n
g
f
o
r
m
e
r
-
I
n
do
B
A
R
T
m
o
de
l
,
t
h
e
a
uto
r
e
g
r
e
s
s
i
ve
f
e
a
t
ur
e
i
n
L
o
n
g
f
o
r
m
e
r
i
n
c
ur
r
e
d
a
s
l
i
g
h
t
l
y
l
o
n
ge
r
t
r
a
i
ni
ng
ti
m
e
t
h
a
n
i
t
s
n
o
n
-
a
ut
or
e
gr
e
s
s
i
v
e
c
o
un
t
e
r
pa
r
t
.
T
u
r
ni
ng
to
F
i
gur
e
5,
whi
c
h
il
l
u
s
t
r
a
t
e
s
t
h
e
tr
a
i
ni
n
g
t
i
m
e
f
o
r
t
h
e
T
y
D
i
Q
A
d
a
t
a
s
e
t
,
r
e
v
e
a
l
t
he
I
n
do
B
A
R
T
-
b
a
s
e
m
o
de
l
t
r
a
i
n
e
d
ne
a
r
l
y
t
w
i
c
e
a
s
qu
i
c
k
ly
a
s
t
h
e
L
o
n
g
f
o
r
m
e
r
-
I
n
do
B
A
R
T
m
o
d
i
f
i
c
a
t
i
o
n
,
w
i
t
h
t
h
e
L
o
n
g
f
o
r
m
e
r
's
a
uto
r
e
gr
e
s
s
i
v
e
f
e
a
t
ur
e
t
a
k
i
n
g
a
f
r
a
c
t
i
o
n
o
f
a
s
e
c
o
n
d
l
o
n
g
e
r
t
h
a
n
i
t
s
n
o
n
-
a
ut
or
e
gr
e
s
s
i
v
e
c
o
un
t
e
r
pa
r
t.
F
i
gur
e
5.
T
y
D
i
Q
A
t
r
a
i
ni
ng
t
i
m
e
c
o
m
pa
r
i
s
o
n
F
i
gur
e
6
.
S
QuA
D
tr
a
i
ni
ng
t
i
m
e
c
o
m
pa
r
i
s
o
n
I
n
t
h
e
or
y
,
t
h
e
L
o
n
gf
o
r
m
e
r
m
o
d
i
f
i
c
a
t
i
o
n
b
o
a
s
t
s
s
upe
r
i
o
r
c
o
m
put
a
t
i
o
n
a
l
c
o
m
p
l
e
xi
t
y
o
f
O(
n)
c
o
m
pa
r
e
d
to
t
h
e
I
n
do
B
A
R
T
-
ba
s
e
s
e
l
f
-
a
t
t
e
n
t
i
o
n
,
w
hi
c
h
s
t
a
n
d
s
a
t
O(
n
2
)
.
Ho
we
v
e
r
,
e
m
p
i
r
i
c
a
l
f
i
nd
i
ng
s
f
r
o
m
t
r
a
i
ni
ng
t
i
m
e
e
v
a
l
ua
t
i
o
ns
r
e
v
e
a
l
t
h
a
t
t
h
e
L
o
n
gf
o
r
m
e
r
m
o
d
i
f
i
c
a
t
i
o
n
a
c
t
ua
l
ly
t
oo
k
l
o
n
ge
r
t
h
a
n
t
h
e
b
a
s
e
I
n
do
B
AR
T
.
T
hi
s
d
i
s
c
r
e
pa
n
c
y
c
a
n
b
e
a
t
t
r
i
b
ut
e
d
to
t
h
e
o
p
t
i
mi
z
e
d
im
p
l
e
m
e
n
t
a
t
i
o
n
o
f
m
a
t
r
i
x
do
t
pr
o
duc
t
c
o
m
put
a
t
i
o
n
s
i
n
t
h
e
I
n
do
B
A
R
T
-
b
a
s
e
,
w
hi
c
h
pr
o
v
e
d
t
o
b
e
f
a
s
t
e
r
t
h
a
n
t
h
e
u
n
o
pt
i
mi
z
e
d
s
l
i
d
i
ng
w
i
n
do
ws
t
e
c
hni
que
ut
i
li
z
e
d
i
n
t
h
e
L
o
n
g
f
o
r
m
e
r
m
o
d
i
f
i
c
a
t
i
o
n
.
T
h
us
,
whil
e
t
h
e
L
o
n
g
f
o
r
m
e
r
m
o
d
i
f
i
c
a
t
i
o
n
i
nde
e
d
i
nv
o
l
ve
s
a
l
o
we
r
n
u
m
be
r
o
f
o
pe
r
a
t
i
o
n
s
,
i
t
s
u
n
o
pt
i
m
i
z
e
d
i
m
p
l
e
m
e
n
t
a
t
i
o
n
r
e
s
u
l
t
e
d
i
n
l
o
n
ge
r
t
r
a
i
ni
ng
t
i
m
e
s
c
o
m
pa
r
e
d
t
o
I
n
do
B
A
R
T
s
e
l
f
-
a
tt
e
n
t
i
o
n
.
5.
CONC
L
USI
ON
T
o
c
o
n
c
l
ude
,
i
n
a
c
c
o
r
da
n
c
e
o
f
t
h
e
e
vi
de
n
c
e
pr
e
s
e
n
t
e
d
i
n
t
hi
s
r
e
s
e
a
r
c
h
,
ut
i
li
z
a
t
i
o
n
o
f
L
o
n
g
f
o
r
m
e
r
a
tt
e
n
t
i
o
n
m
o
d
i
f
i
c
a
t
i
o
n
t
o
i
m
pr
o
v
e
I
n
do
n
e
s
i
a
-
b
a
s
e
d
A
QG
s
y
s
t
e
m
m
o
de
l
s
i
s
n
ot
a
bly
be
n
e
f
i
c
i
a
l
,
e
s
pe
c
i
a
ll
y
wh
e
n
h
a
n
d
li
ng
l
o
n
ge
r
s
e
que
n
c
e
c
o
n
t
e
x
t
i
n
put
a
n
d
o
ut
pu
t.
T
h
r
o
ugh
o
u
t
t
hi
s
r
e
s
e
a
r
c
h
,
t
h
e
L
o
n
g
f
o
r
m
e
r
-
I
n
do
B
A
R
T
m
o
de
l
s
h
o
wc
a
s
e
d
r
e
m
a
r
ka
bl
e
pr
e
c
i
s
i
o
n
a
c
r
o
s
s
a
l
l
e
v
a
l
ua
t
i
v
e
m
e
t
r
i
c
s
o
n
t
h
e
T
y
D
i
Q
A
d
a
t
a
s
e
t
i
n
c
o
n
t
r
a
s
t
to
i
t
s
pr
e
de
c
e
s
s
o
r
,
t
h
e
I
n
do
B
A
R
T
-
ba
s
e
m
o
de
l
.
W
hil
e
,
t
h
e
L
o
n
g
f
o
r
m
e
r
-
I
n
do
B
A
R
T
m
o
de
l
Evaluation Warning : The document was created with Spire.PDF for Python.
I
S
S
N
:
2252
-
8776
I
n
t
J
I
n
f
&
C
o
m
m
u
n
T
e
c
hn
o
l
,
Vo
l
.
1
4
,
N
o.
2
,
A
ugus
t
20
2
5
:
478
-
487
486
de
m
o
ns
t
r
a
t
e
d
i
m
pr
e
s
s
i
ve
pe
r
f
o
r
m
a
n
c
e
,
i
t
e
x
pe
r
i
e
n
c
e
d
a
s
l
i
g
h
t
s
e
t
b
a
c
k
wh
e
n
e
v
a
l
ua
t
e
d
o
n
t
h
e
tr
a
ns
l
a
t
e
d
S
QuA
D
v
2
da
t
a
s
e
t
c
o
m
pa
r
e
d
to
t
h
e
I
n
do
B
AR
T
m
o
de
l
,
b
e
c
a
us
e
o
f
s
o
m
e
c
o
n
t
e
x
t
we
n
t
m
i
s
s
i
ng
i
n
t
r
a
n
s
l
a
t
i
o
n
.
F
o
r
f
ut
ur
e
s
t
udi
e
s
,
i
t
i
s
a
d
vi
s
a
bl
e
to
c
o
n
duc
t
tr
a
i
ni
ng
w
i
t
h
QG
a
s
t
h
e
t
a
r
ge
t
i
n
s
t
e
a
d
o
f
a
ns
we
r
ge
n
e
r
a
t
i
o
n
.
F
ur
t
h
e
r
m
o
r
e
,
e
m
p
l
o
yi
ng
a
n
uns
upe
r
vi
s
e
d
l
e
a
r
ni
ng
a
ppr
o
a
c
h
to
ge
n
e
r
a
t
e
b
ot
h
que
s
t
i
o
n
s
a
nd
a
ns
we
r
s
f
r
o
m
a
c
o
n
t
e
x
t
ua
l
pa
r
a
gr
a
ph
c
o
ul
d
s
t
r
e
a
ml
i
ne
t
h
e
m
a
n
ua
l
pr
o
c
e
s
s
o
f
t
e
a
c
h
e
r
-
l
e
d
que
s
t
i
o
n
-
a
n
s
w
e
r
ge
n
e
r
a
t
i
o
n
.
T
h
e
da
t
a
s
e
t
s
e
m
p
l
o
y
e
d
i
n
t
hi
s
s
t
ud
y
we
r
e
s
o
ur
c
e
d
f
r
o
m
e
i
t
h
e
r
m
u
l
t
i
li
ngua
l
o
r
E
n
g
l
i
s
h
da
t
a
s
e
t
s
t
h
a
t
r
e
qui
r
e
d
t
r
a
n
s
l
a
t
i
o
n
.
T
hi
s
c
o
u
l
d
po
s
e
c
h
a
ll
e
n
g
e
s
a
s
s
o
m
e
c
o
n
t
e
x
t
m
a
y
b
e
l
o
s
t
i
n
t
r
a
ns
l
a
t
i
o
n
o
r
t
h
e
da
t
a
s
e
t
s
i
z
e
m
a
y
b
e
l
im
i
t
e
d.
T
h
e
r
e
f
o
r
e
,
t
h
e
c
r
e
a
t
i
o
n
o
f
a
n
I
n
do
n
e
s
i
a
n
l
a
n
gu
a
ge
que
s
t
i
o
n
-
a
n
s
we
r
i
ng
da
t
a
s
e
t
i
s
e
s
s
e
n
t
i
a
l
to
de
v
e
l
o
p
m
o
r
e
r
o
b
us
t
m
o
de
l
s
a
n
d
b
e
n
c
hm
a
r
ks
.
F
UN
DI
NG
I
N
F
ORM
AT
I
ON
A
ut
h
o
r
s
s
t
a
t
e
n
o
f
u
n
d
i
ng
i
nv
o
l
v
e
d.
AU
T
HO
R
CONT
RI
B
UT
I
ONS
S
T
AT
E
M
E
NT
Nam
e
of
Aut
h
or
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
P
e
t
e
r
A
n
dr
e
w
Abb
a
S
uga
n
da
G
i
r
s
a
n
g
C
:
C
o
n
c
e
pt
ua
li
z
a
ti
o
n
M
:
M
e
th
o
d
o
l
o
g
y
So
:
So
f
twa
r
e
Va
:
Va
li
da
ti
o
n
Fo
:
Fo
r
ma
l
a
na
l
y
s
is
I
:
I
nve
s
ti
ga
ti
o
n
R
:
R
e
s
o
u
r
c
e
s
D
:
D
a
ta
C
ur
a
ti
o
n
O
:
W
r
it
in
g
-
O
r
ig
in
a
l
D
r
a
f
t
E
:
W
r
it
in
g
-
R
e
v
i
e
w
&
E
di
ti
ng
Vi
:
Vi
s
ua
li
z
a
ti
o
n
Su
:
Su
pe
r
v
is
io
n
P
:
P
r
o
j
e
c
t
a
dmi
ni
s
tr
a
ti
o
n
Fu
:
Fu
ndi
ng a
c
qui
s
it
i
o
n
CONF
L
I
CT
OF
I
NT
E
RE
S
T
S
T
AT
E
M
E
NT
A
ut
h
o
r
s
s
t
a
t
e
n
o
c
o
nf
li
c
t
o
f
i
n
t
e
r
e
s
t
DA
T
A
AV
AI
L
AB
I
L
I
T
Y
T
h
e
a
ut
h
o
r
s
c
o
nf
i
r
m
t
h
a
t
t
h
e
da
t
a
s
upp
o
r
t
i
n
g
t
h
e
f
in
d
i
ngs
o
f
t
hi
s
s
t
ud
y
a
r
e
a
va
i
l
a
bl
e
w
i
t
hi
n
t
h
e
a
r
t
i
c
l
e
RE
F
E
R
E
NC
E
S
[
1]
N
.
T
.
L
e
,
T
.
K
o
ji
r
i,
a
nd
N
.
P
in
kw
a
r
t,
“
A
ut
o
ma
ti
c
qu
e
s
ti
o
n
ge
n
e
r
a
ti
o
n
f
o
r
e
du
c
a
ti
o
na
l
a
ppl
ic
a
ti
o
ns
-
th
e
s
ta
te
of
a
r
t,
”
in
A
dv
anc
e
s
in
I
nt
e
ll
ig
e
nt
Sy
s
te
m
s
and C
om
put
in
g
, v
o
l.
282, S
p
r
in
ge
r
I
nt
e
r
n
a
ti
o
na
l
P
ubl
is
hi
ng, 2014, pp. 325
–
338.
[
2]
R
.
S
mi
th
,
P
.
S
n
o
w
,
T
.
S
e
r
r
y
,
a
nd
L
.
H
a
mm
o
nd,
“
T
h
e
R
o
le
of
ba
c
kgr
o
und
kn
o
w
l
e
dg
e
in
r
e
a
di
ng
c
o
mpr
e
he
ns
i
o
n:
a
c
r
it
ic
a
l
r
e
v
i
e
w
,”
R
e
adi
ng
P
s
y
c
hol
ogy
, vo
l.
42
, n
o
. 3, pp. 214
–
240,
F
e
b.
2021, do
i:
10.1080/02702711.
2021.1888348.
[
3]
E
. B
. M
o
j
e
, P
. P
. A
f
f
le
r
ba
c
h,
P
. E
n
c
is
o
, a
nd N
.
K
.
L
e
s
a
ux
,
H
an
dbook
of
r
e
adi
ng r
e
s
e
ar
c
h, v
ol
um
e
V
, v
o
l.
V
. R
o
ut
l
e
dg
e
, 2020.
[
4]
M
.
L
e
a
s
a
,
A
.
A
be
dn
e
g
o
,
a
nd
J
.
R
.
B
a
tl
o
l
o
na
,
“
P
r
o
bl
e
m
-
ba
s
e
d
le
a
r
ni
ng
(
P
B
L
)
w
it
h
r
e
a
di
ng
qu
e
s
ti
o
ni
ng
a
nd
a
ns
w
e
r
in
g
(
R
Q
A
)
of
pr
e
s
e
r
v
i
c
e
e
l
e
m
e
nt
a
r
y
s
c
h
oo
l
t
e
a
c
h
e
r
s
,”
I
nt
e
r
nat
io
nal
J
our
nal
of
L
e
a
r
ni
ng,
T
e
ac
hi
ng
and
E
duc
at
io
nal
R
e
s
e
a
r
c
h
,
v
o
l.
22,
n
o
.
6,
pp. 245
–
261, J
un. 2023, do
i:
10.26803/i
jl
t
e
r
.22.6.14.
[
5]
V
.
R
a
ma
da
y
a
nt
i
a
nd
J
a
mi
lu
ddi
n,
“
D
e
ve
l
o
pi
ng
s
tu
de
nt
s
’
r
e
a
di
ng
c
o
mp
r
e
h
e
ns
i
o
n
th
r
o
ugh
qu
e
s
ti
o
n
g
e
ne
r
a
ti
o
n
s
tr
a
t
e
g
y
,”
E
-
J
our
nal
of
E
ngl
is
h L
anguage
T
e
ac
hi
ng Soc
ie
ty
, v
o
l.
8, 2020.
[
6]
X
.
D
u,
J
.
S
ha
o
,
a
nd
C
.
C
a
r
di
e
,
“
L
e
a
r
ni
ng
t
o
A
s
k:
N
e
ur
a
l
Q
ue
s
ti
o
n
G
e
ne
r
a
ti
o
n
f
o
r
R
e
a
di
ng
C
o
mp
r
e
he
ns
i
o
n,”
C
o
R
R
,
vo
l.
a
bs
/1
705.00106, 2017, [
O
nl
in
e
]
. A
v
a
il
a
bl
e
:
ht
tp
:/
/a
r
x
i
v
.
or
g/
a
bs
/1
705.00106
[
7]
D
.
S
uha
r
to
n
o
,
M
.
R
.
N
.
M
a
ji
id
,
a
nd
R
.
F
r
e
d
y
a
n,
“
T
o
w
a
r
ds
a
ut
o
ma
ti
c
qu
e
s
ti
o
n
ge
n
e
r
a
ti
o
n
us
in
g
pr
e
-
tr
a
in
e
d
m
o
d
e
l
in
a
c
a
de
mi
c
f
i
e
ld
f
or
B
a
ha
s
a
I
nd
o
n
e
s
ia
,”
E
duc
at
io
n
and
I
nf
or
m
at
io
n
T
e
c
hnol
ogi
e
s
,
v
o
l.
29,
n
o
.
16,
pp.
21295
–
21330,
A
pr
.
2024,
do
i:
10.1007/s
10639
-
024
-
12717
-
9.
[
8]
V
.
H
a
r
r
is
o
n
a
nd
M
.
W
a
lk
e
r
,
“
N
e
ur
a
l
ge
ne
r
a
ti
o
n
of
di
ve
r
s
e
qu
e
s
ti
o
ns
us
in
g
a
n
s
w
e
r
f
oc
us
,
c
o
nt
e
xt
ua
l
a
nd
li
ngui
s
ti
c
f
e
a
tu
r
e
s
,”
i
n
I
N
L
G
2018
-
11t
h
I
nt
e
r
nat
io
nal
N
at
ur
al
L
anguage
G
e
ne
r
at
io
n
C
onf
e
r
e
nc
e
,
P
r
oc
e
e
di
ngs
o
f
th
e
C
on
f
e
r
e
nc
e
,
2018,
pp.
296
–
306,
do
i:
10.18653/
v
1/
w
18
-
6536.
[9
T
.
S
ul
ta
na
a
nd
S
.
B
a
dugu,
“
A
r
e
v
i
e
w
o
n
di
f
f
e
r
e
nt
qu
e
s
ti
on
a
ns
w
e
r
in
g
s
y
s
t
e
m
a
ppr
o
a
c
h
e
s
,”
in
L
e
ar
ni
ng
and
A
nal
y
ti
c
s
in
I
nt
e
ll
ig
e
nt
Sy
s
te
m
s
, v
o
l.
4, S
p
r
in
g
e
r
I
nt
e
r
na
ti
o
na
l
P
ubl
is
hi
ng, 2020, pp. 579
–
586.
[
10]
P
.
R
a
j
p
u
r
k
a
r
,
J
.
Z
h
a
n
g
,
K
.
L
o
py
r
e
v
,
a
n
d
P
.
L
i
a
n
g
,
“
S
Q
u
a
d
:
1
0
0
,
00
0
+
q
u
e
s
t
i
o
n
s
f
o
r
m
a
c
h
i
ne
c
o
m
p
r
e
he
n
s
i
o
n
o
f
t
e
x
t
,
”
i
n
E
M
N
L
P
2
01
6
-
C
o
n
fe
r
e
n
c
e
o
n
E
m
p
i
r
i
c
a
l
M
e
t
h
o
d
s
i
n
N
a
t
u
r
a
l
L
a
n
g
u
a
g
e
P
r
o
c
e
s
s
i
n
g
,
P
r
o
c
e
e
d
i
n
g
s
, 2016, pp. 2383
–
2392, do
i:
10.18653/
v
1/d16
-
1264.
[
11]
A
.
A
s
a
,
K
.
H
a
s
hi
mo
t
o
,
H
.
H
a
ji
s
hi
r
z
i,
R
.
S
oc
h
e
r
,
a
nd
C
.
X
io
n
g,
“
L
e
a
r
ni
ng
t
o
r
e
tr
ie
ve
r
e
a
s
o
n
in
g
pa
th
s
ove
r
w
ik
ip
e
di
a
gr
a
ph
f
or
que
s
ti
o
n a
ns
w
e
r
in
g,”
ar
X
iv
.
, 2019.
[
12]
G
.
I
z
a
c
a
r
d
a
nd
E
.
G
r
a
ve
,
“
L
e
ve
r
a
gi
ng
pa
s
s
a
ge
r
e
t
r
i
e
v
a
l
w
it
h
g
e
n
e
r
a
ti
ve
m
o
d
e
ls
f
o
r
o
p
e
n
d
o
ma
in
qu
e
s
ti
o
n
a
ns
w
e
r
in
g,”
in
E
A
C
L
2021
-
16t
h
C
onf
e
r
e
n
c
e
o
f
th
e
E
ur
ope
an
C
hapt
e
r
o
f
th
e
A
s
s
oc
ia
ti
on
f
o
r
C
om
put
at
io
nal
L
in
gui
s
ti
c
s
,
P
r
oc
e
e
di
ngs
of
th
e
C
on
f
e
r
e
nc
e
, 2021, pp. 874
–
880, do
i:
10.18653/
v
1/
2021.
e
a
c
l
-
m
a
in
.74.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t
J
I
n
f
&
C
o
m
m
u
n
T
e
c
hn
o
l
I
S
S
N:
2252
-
8776
I
ndoB
A
R
T
opti
miz
ati
on
f
or
que
s
ti
on
ans
w
e
r
ge
ne
r
ati
on
s
y
s
tem
w
it
h
longf
or
me
r
att
e
nti
on
(
P
e
ter
A
ndr
e
w
)
487
[
13]
Q
.
C
a
o
,
H
.
T
r
i
ve
di
,
A
.
B
a
la
s
ubr
a
ma
ni
a
n,
a
nd
N
.
B
a
la
s
ubr
a
ma
ni
a
n,
“
D
e
F
o
r
m
e
r
:
D
e
c
o
mp
o
s
in
g
pr
e
-
tr
a
in
e
d
tr
a
ns
f
o
r
m
e
r
s
f
or
f
a
s
te
r
que
s
ti
o
n
a
ns
w
e
r
in
g,”
in
P
r
oc
e
e
di
ngs
of
th
e
A
nnual
M
e
e
ti
ng
of
th
e
A
s
s
oc
ia
ti
on
f
or
C
o
m
put
at
io
nal
L
in
gui
s
ti
c
s
,
2020,
pp.
4487
–
4497, do
i:
10.18653/
v
1/
2020.a
c
l
-
ma
in
.411.
[
14]
S
.
C
a
h
y
a
w
ij
a
y
a
e
t
a
l.
,
“
I
nd
o
N
L
G
:
b
e
n
c
hma
r
k
a
nd
r
e
s
o
ur
c
e
s
f
o
r
e
v
a
lu
a
ti
ng
in
d
o
n
e
s
ia
n
na
tu
r
a
l
la
ngua
ge
ge
n
e
r
a
ti
o
n,”
in
E
M
N
L
P
2021
-
2021
C
onf
e
r
e
nc
e
on
E
m
pi
r
ic
al
M
e
th
ods
in
N
at
ur
al
L
anguage
P
r
oc
e
s
s
in
g,
P
r
oc
e
e
di
ngs
,
2021,
pp.
8875
–
8898,
do
i:
10.18653/v
1/
2021.
e
mnl
p
-
ma
in
.699.
[
15]
B
.
W
il
ie
e
t
al
.,
“
I
nd
o
N
L
U
:
B
e
nc
hma
r
k
a
nd
r
e
s
o
ur
c
e
s
f
or
e
v
a
lu
a
ti
ng
I
ndo
n
e
s
ia
n
na
tu
r
a
l
la
ngua
ge
unde
r
s
ta
ndi
ng,”
P
r
oc
e
e
di
ngs
o
f
th
e
1s
t
C
on
f
e
r
e
nc
e
o
f
th
e
A
s
ia
-
P
ac
if
ic
C
hapt
e
r
o
f
th
e
A
s
s
oc
ia
ti
on
f
or
C
om
put
at
io
nal
L
in
gui
s
ti
c
s
and
th
e
10t
h
I
nt
e
r
nat
io
nal
J
oi
nt
C
onf
e
r
e
nc
e
on N
at
ur
al
L
anguage
P
r
oc
e
s
s
in
g
, pp. 843
–
857, 2020.
[
16]
K
.
P
a
pi
n
e
ni
,
S
.
R
o
uk
o
s
,
T
.
W
a
r
d,
a
nd
W
.
J
.
Z
hu,
“
B
L
E
U
:
A
me
th
o
d
f
o
r
a
ut
o
ma
ti
c
e
v
a
lu
a
ti
o
n
of
ma
c
hi
n
e
tr
a
ns
la
ti
o
n,
”
in
P
r
oc
e
e
di
ngs
of
th
e
A
nnual
M
e
e
ti
ng
of
th
e
A
s
s
oc
ia
ti
on
f
or
C
o
m
put
at
io
nal
L
in
gui
s
ti
c
s
,
2002,
vo
l.
2002
-
J
ul
y
,
pp.
311
–
318,
do
i:
10.3115/1073083.10
73135.
[
17]
C.
-
Y
.
L
in
,
“
R
O
U
G
E
:
a
pa
c
ka
g
e
f
or
a
ut
o
ma
ti
c
e
v
a
lu
a
ti
o
n
of
s
umm
a
r
ie
s
,”
T
e
x
t
Sum
m
ar
iz
at
io
n
B
r
anc
he
s
O
ut
,
B
ar
c
e
lo
na,
Sp
ai
n:
A
s
s
oc
ia
ti
on f
o
r
C
om
put
at
io
nal
L
in
gui
s
ti
c
s
, pp. 74
–
81, 2019.
[
18]
D
.
S
u
e
t
al
.
,
“
G
e
n
e
r
a
li
z
in
g
qu
e
s
ti
o
n
a
ns
w
e
r
in
g
s
y
s
te
m
w
it
h
pr
e
-
t
r
a
in
e
d
la
ngua
g
e
m
o
d
e
l
f
in
e
-
tu
ni
ng,”
in
M
R
Q
A
@
E
M
N
L
P
20
19
-
P
r
oc
e
e
di
ngs
of
t
he
2nd W
or
k
s
hop on M
ac
hi
ne
R
e
adi
ng
f
or
Q
ue
s
ti
on A
ns
w
e
r
in
g
, 2019, pp. 203
–
211, do
i:
10.18653/
v
1/
d19
-
582
7.
[
19]
M
.
L
e
w
is
e
t
al
.
,
“
B
A
R
T
:
D
e
n
o
is
in
g
s
e
que
n
c
e
-
to
-
s
e
qu
e
n
c
e
pr
e
-
t
r
a
in
in
g
f
o
r
na
tu
r
a
l
la
ngua
ge
g
e
n
e
r
a
ti
o
n,
tr
a
ns
la
ti
o
n,
a
nd
c
o
mpr
e
h
e
ns
io
n
,”
in
P
r
oc
e
e
di
ngs
of
th
e
A
nnual
M
e
e
ti
ng
o
f
th
e
A
s
s
oc
ia
ti
on
f
or
C
om
put
at
io
nal
L
in
gui
s
ti
c
s
,
2020,
pp.
7871
–
7
880,
do
i:
10.18653/
v
1/
2020.a
c
l
-
ma
in
.703.
[
20]
H
.
W
.
C
hung,
D
.
G
a
r
r
e
tt
e
,
K
.
C
.
T
a
n,
a
nd
J
.
R
ie
s
a
,
“
I
mpr
ovi
ng
mul
ti
li
ngua
l
m
o
de
ls
w
i
th
la
ngua
ge
-
c
lu
s
te
r
e
d
voc
a
bul
a
r
i
e
s
,
”
in
E
M
N
L
P
2020
-
2020
C
onf
e
r
e
nc
e
on
E
m
pi
r
ic
al
M
e
th
ods
in
N
at
ur
al
L
anguage
P
r
oc
e
s
s
in
g,
P
r
oc
e
e
di
ngs
of
th
e
C
on
f
e
r
e
nc
e
,
2020,
pp. 4536
–
4546, do
i:
10.18653/
v
1/
2020.
e
mnl
p
-
ma
in
.367.
[
21]
I
. B
e
lt
a
g
y
, M
. E
. P
e
t
e
r
s
, a
nd A
. C
o
ha
n, “
L
o
ng
f
o
r
me
r
:
th
e
l
o
ng
-
doc
um
e
nt
t
r
a
ns
f
o
r
m
e
r
,”
ar
X
iv
pr
e
pr
in
t
ar
X
iv
.
[
22]
F
.
J
.
M
ui
s
a
nd
A
.
P
ur
w
a
r
ia
nt
i,
“
S
e
que
nc
e
-
to
-
s
e
qu
e
n
c
e
l
e
a
r
ni
ng
f
o
r
I
nd
o
n
e
s
ia
n
a
ut
o
ma
ti
c
que
s
ti
o
n
ge
n
e
r
a
t
or
,”
in
2020
7t
h
I
nt
e
r
nat
io
nal
C
onf
e
r
e
nc
e
on
A
dv
anc
e
d
I
nf
or
m
at
ic
s
:
C
onc
e
pt
s
,
T
he
or
y
and
A
ppl
ic
at
io
ns
,
I
C
A
I
C
T
A
2020
,
S
e
p.
2020,
pp.
1
–
6,
do
i:
10.1109/I
C
A
I
C
T
A
49861.2020.9429032.
[
23]
J
.
H
.
C
la
r
k
e
t
al
.
,
“
T
y
di
qa
:
A
b
e
n
c
hma
r
k
f
or
in
f
or
ma
ti
o
n
-
s
e
e
ki
ng
qu
e
s
ti
o
n
a
ns
w
e
r
in
g
in
t
y
p
o
l
o
g
ic
a
ll
y
di
v
e
r
s
e
la
ngua
g
e
s
,”
T
r
ans
ac
ti
ons
o
f
t
he
A
s
s
oc
ia
ti
on f
o
r
C
om
put
at
io
nal
L
in
gui
s
ti
c
s
,
vo
l.
8, pp. 454
–
470, D
e
c
. 2020, d
o
i:
10.1162/t
a
c
l_
a
_00317.
[
24]
K
.
V
in
c
e
nt
i
o
a
nd
D
.
S
uha
r
t
o
n
o
,
“
A
ut
o
ma
ti
c
qu
e
s
ti
o
n
ge
n
e
r
a
ti
o
n
us
in
g
R
N
N
-
ba
s
e
d
a
nd
p
r
e
-
tr
a
in
e
d
tr
a
ns
f
o
r
m
e
r
-
ba
s
e
d
m
o
d
e
l
s
in
l
o
w
r
e
s
o
ur
c
e
in
d
o
ne
s
ia
n l
a
ngua
ge
,”
I
nf
or
m
at
ic
a (
Sl
ov
e
ni
a)
, vo
l
. 46, no
. 7, pp. 103
–
118, N
ov
. 2022, d
o
i:
10.31449/i
n
f
.
v
46i
7.42
36.
[
25]
A
. V
a
s
w
a
ni
, “
A
tt
e
nt
i
o
n i
s
a
ll
y
o
u n
e
e
d,”
A
dv
anc
e
s
i
n N
e
ur
al
I
n
f
or
m
at
io
n P
r
oc
e
s
s
in
g Sy
s
te
m
s
, 2017.
B
I
OG
RA
P
HI
E
S
OF
AU
T
HO
RS
P
eter
A
n
drew
i
s
c
u
rr
en
t
l
y
fr
eel
an
ce
d
e
v
el
o
p
e
r
s
p
e
ci
al
i
zi
n
g
i
n
w
e
b
,
m
o
b
i
l
e
,
d
e
s
k
t
o
p
,
a
n
d
c
ro
s
s
-
p
l
at
fo
rm
d
e
v
el
o
p
me
n
t
s
i
n
ce
2
0
2
4
,
H
e
h
o
l
d
s
a
b
ach
el
o
r
's
d
e
g
r
ee
i
n
i
n
fo
r
m
at
i
c
s
fr
o
m
Bi
n
a
N
u
s
an
t
ara
U
n
i
v
e
rs
i
t
y
2
0
2
1
.
H
e
h
as
an
i
n
t
e
rn
s
h
i
p
at
t
h
e
A
p
p
l
e
D
ev
e
l
o
p
e
r
A
c
a
d
emy
i
n
2
0
1
9
as
an
i
O
S
d
ev
e
l
o
p
e
r,
fo
l
l
o
w
ed
b
y
a
t
ran
s
i
t
i
o
n
t
o
F
l
as
h
Co
ff
ee
i
n
2
0
2
1
,
w
h
e
r
e
h
e
d
em
o
n
s
t
rat
e
d
p
ro
f
i
c
i
en
cy
i
n
mo
b
i
l
e
,
w
e
b
,
an
d
b
a
c
k
en
d
d
e
v
el
o
p
me
n
t
,
al
o
n
g
s
i
d
e
ad
e
p
t
n
e
s
s
i
n
b
u
i
l
d
au
t
o
m
at
i
o
n
a
n
d
d
at
a
re
p
o
rt
i
n
g
.
h
i
s
ar
e
a
o
f
i
n
t
e
r
e
s
t
i
s
m
a
ch
i
n
e
l
e
ar
n
i
n
g
an
d
d
at
a
s
c
i
en
ce
.
H
e
c
an
b
e
co
n
t
a
c
t
ed
at
em
ai
l
:
p
e
t
e
r.
a
n
d
r
ew
@
b
i
n
u
s
.
a
c
.
i
d
.
A
bba
Su
g
a
n
da
G
i
rs
a
n
g
i
s
c
u
rr
en
t
l
y
a
l
ec
t
u
r
e
r
at
Mas
t
e
r
i
n
C
o
m
p
u
t
e
r
S
c
i
en
ce
,
Bi
n
a
N
u
s
an
t
ara
U
n
i
v
e
rs
i
t
y
,
J
ak
art
a,
In
d
o
n
e
s
i
a
Si
n
ce
2
0
1
5
.
H
e
g
o
t
Ph
.
D
.
d
e
g
r
ee
i
n
2
0
1
5
at
t
h
e
I
n
s
t
i
t
u
t
e
o
f
C
o
m
p
u
t
e
r
an
d
Co
mmu
n
i
c
at
i
o
n
E
n
g
i
n
ee
ri
n
g
,
D
e
p
art
men
t
o
f
E
l
ec
t
ri
c
a
l
E
n
g
i
n
ee
ri
n
g
,
N
at
i
o
n
a
l
Ch
en
g
K
u
n
g
U
n
i
v
e
rs
i
t
y
,
T
ai
n
an
,
T
ai
w
a
n
.
H
e
g
ra
d
u
at
e
d
b
ach
e
l
o
r
fr
o
m
t
h
e
D
e
p
art
men
t
o
f
E
l
ec
t
ri
c
a
l
E
n
g
i
n
ee
ri
n
g
,
G
ad
j
a
h
Ma
d
a
U
n
i
v
e
rs
i
t
y
(
U
G
M),
Y
o
g
y
ak
art
a,
I
n
d
o
n
e
s
i
a,
i
n
2
0
0
0
.
H
e
t
h
en
c
o
n
t
i
n
u
e
d
h
i
s
m
as
t
e
r’s
d
eg
ree
i
n
t
h
e
D
e
p
art
men
t
o
f
Co
m
p
u
t
e
r
Sci
en
ce
at
t
h
e
s
ame
u
n
i
v
e
rs
i
t
y
i
n
2
0
0
6
–
2
0
0
8
.
H
e
w
as
a
s
t
aff
c
o
n
s
u
l
t
an
t
p
ro
g
ra
mme
r
i
n
Be
t
h
e
s
d
a
H
o
s
p
i
t
al
,
Y
o
g
y
ak
art
a,
i
n
2
0
0
1
an
d
al
s
o
w
o
rk
e
d
as
a
w
e
b
d
ev
e
l
o
p
e
r
i
n
2
0
0
2
–
2
0
0
3
.
H
e
t
h
e
n
j
o
i
n
ed
t
h
e
fa
cu
l
t
y
o
f
t
h
e
D
e
p
art
me
n
t
o
f
In
fo
r
m
at
i
c
s
E
n
g
i
n
ee
r
i
n
g
i
n
J
an
ab
ad
ra
U
n
i
v
e
rs
i
t
y
as
a
l
ec
t
u
r
e
r
i
n
2
0
0
3
-
2
0
1
5
.
H
i
s
r
e
s
e
ar
ch
i
n
t
e
r
e
s
t
s
i
n
c
l
u
d
e
s
w
ar
m
,
i
n
t
el
l
i
g
en
ce,
c
o
m
b
i
n
at
o
ri
a
l
o
p
t
i
m
i
zat
i
o
n
,
an
d
d
ec
i
s
i
o
n
s
u
p
p
o
rt
s
y
s
t
e
m.
H
e
c
a
n
b
e
c
o
n
t
ac
t
e
d
at
e
m
ai
l
:
ag
i
rs
an
g
@
b
i
n
u
s
.
e
d
u
.
Evaluation Warning : The document was created with Spire.PDF for Python.