I
nd
o
ne
s
ia
n J
o
urna
l o
f
E
lect
rica
l En
g
ineering
a
nd
Co
m
pu
t
er
Science
Vo
l.
37
,
No
.
1
,
J
an
u
ar
y
20
25
,
p
p
.
2
0
6
~
2
1
3
I
SS
N:
2
502
-
4
7
52
,
DOI
: 1
0
.
1
1
5
9
1
/ijee
cs
.v
37.
i
1
.
p
p
206
-
2
1
3
206
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ee
cs
.
ia
esco
r
e.
co
m
A t
hr
ee
-
pha
se
mo
del t
o
keywo
rd
de
tect
io
n i
n Arabic
co
rpo
ra
Driss
Na
m
ly
1
,
K
a
rim
B
o
uzo
ub
a
a
2
,
Rido
ua
ne
T
a
chica
rt
3
1
De
p
a
r
t
me
n
t
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
M
o
h
a
mm
e
d
V
U
n
i
v
e
r
si
t
y
i
n
R
a
b
a
t
,
R
a
b
a
t
,
M
o
r
o
c
c
o
2
M
o
h
a
mm
a
d
i
a
S
c
h
o
o
l
o
f
E
n
g
i
n
e
e
r
s,
M
o
h
a
mm
e
d
V
U
n
i
v
e
r
s
i
t
y
i
n
R
a
b
a
t
,
R
a
b
a
t
,
M
o
r
o
c
c
o
3
F
a
c
u
l
t
é
d
e
s
S
c
i
e
n
c
e
s
J
u
r
i
d
i
q
u
e
s,
Ec
o
n
o
m
i
q
u
e
s e
t
S
o
c
i
a
l
e
s
d
'E
l
-
Ja
d
i
d
a
,
C
h
o
u
a
i
b
D
o
u
k
k
a
l
i
U
n
i
v
e
r
si
t
y
,
E
l
Ja
d
i
d
a
,
M
o
r
o
c
c
o
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
May
31
,
2
0
2
4
R
ev
is
ed
Sep
3
,
2
0
2
4
Acc
ep
ted
Sep
7
,
2
0
2
4
Th
e
e
x
p
o
n
e
n
ti
a
l
g
r
o
wth
o
f
Ara
b
ic
tex
t
d
a
ta
in
re
c
e
n
t
y
e
a
rs
h
a
s
c
re
a
ted
a
n
u
rg
e
n
t
d
e
m
a
n
d
f
o
r
so
p
h
isti
c
a
ted
k
e
y
wo
r
d
d
e
tec
ti
o
n
tec
h
n
iq
u
e
s
th
a
t
a
re
sp
e
c
ifi
c
a
ll
y
tailo
re
d
to
th
e
n
u
a
n
c
e
s
o
f
t
h
e
Ara
b
ic
lan
g
u
a
g
e
.
Th
is
stu
d
y
a
d
d
re
ss
e
s
th
e
c
rit
ica
l
n
e
e
d
f
o
r
e
fficie
n
t
to
o
ls
c
a
p
a
b
le
o
f
sw
ift
ly
a
n
d
a
c
c
u
ra
tely
id
e
n
ti
fy
in
g
k
e
y
w
o
rd
s
with
in
a
c
o
ll
e
c
ti
o
n
o
f
Ara
b
ic
d
o
c
u
m
e
n
ts,
p
a
rti
c
u
larly
wh
e
n
a
n
a
l
y
z
in
g
m
u
l
ti
p
le
d
o
c
u
m
e
n
ts
i
n
a
c
o
rp
u
s.
T
o
m
e
e
t
th
is
c
h
a
ll
e
n
g
e
,
we
p
re
se
n
t
a
n
o
v
e
l
c
o
rp
u
s
sp
e
c
ifi
c
a
ll
y
d
e
sig
n
e
d
fo
r
k
e
y
w
o
rd
d
e
tec
ti
o
n
in
Ara
b
ic
tex
ts,
a
l
o
n
g
with
a
n
i
n
n
o
v
a
ti
v
e
a
p
p
r
o
a
c
h
t
h
a
t
in
teg
ra
tes
th
re
e
d
isti
n
c
t
c
a
n
d
i
d
a
te
k
e
y
w
o
rd
li
sts:
a
fre
q
u
e
n
c
y
-
b
a
se
d
li
st
,
a
v
e
c
to
r
sp
a
c
e
m
o
d
e
l
li
st
,
a
n
d
a
m
a
c
h
in
e
lea
r
n
in
g
-
b
a
se
d
li
st.
Th
is
h
y
b
ri
d
m
e
th
o
d
o
l
o
g
y
lev
e
ra
g
e
s
th
e
stre
n
g
th
s
o
f
e
a
c
h
tec
h
n
iq
u
e
,
e
n
a
b
li
n
g
a
m
o
re
c
o
m
p
re
h
e
n
siv
e
a
n
d
e
ffe
c
ti
v
e
k
e
y
wo
rd
i
d
e
n
ti
f
i
c
a
ti
o
n
p
r
o
c
e
ss
.
We
c
o
n
d
u
c
ted
e
x
ten
siv
e
e
x
p
e
rime
n
tal
v
a
li
d
a
ti
o
n
t
o
a
ss
e
ss
th
e
p
e
rfo
rm
a
n
c
e
a
n
d
c
o
m
p
u
tati
o
n
a
l
e
fficie
n
c
y
o
f
o
u
r
p
ro
p
o
se
d
p
i
p
e
li
n
e
.
T
h
e
re
su
lt
s
d
e
m
o
n
stra
te
th
a
t
o
u
r
a
p
p
ro
a
c
h
c
o
n
siste
n
tl
y
a
c
h
iev
e
s
ro
b
u
st
p
e
rfo
rm
a
n
c
e
a
c
ro
ss
a
v
a
riety
o
f
d
o
m
a
in
s,
wit
h
e
v
a
lu
a
ti
o
n
m
e
tri
c
s
in
d
ica
ti
n
g
F
1
-
sc
o
re
s
t
h
a
t
c
o
n
siste
n
tl
y
su
rp
a
ss
9
1
%
.
O
v
e
ra
ll
,
t
h
is
st
u
d
y
c
o
n
tri
b
u
tes
to
th
e
a
d
v
a
n
c
e
m
e
n
t
o
f
a
u
to
m
a
ted
k
e
y
w
o
rd
d
e
tec
ti
o
n
i
n
Ara
b
ic,
p
a
v
in
g
t
h
e
wa
y
fo
r
e
n
h
a
n
c
e
d
in
fo
rm
a
ti
o
n
re
tri
e
v
a
l
a
n
d
tex
t
a
n
a
ly
sis c
a
p
a
b
il
it
ies
.
K
ey
w
o
r
d
s
:
Ar
ab
ic
lan
g
u
a
g
e
I
n
f
o
r
m
atio
n
r
etr
ie
v
al
Key
wo
r
d
d
etec
tio
n
Ma
ch
in
e
lear
n
in
g
Natu
r
al
lan
g
u
ag
e
p
r
o
ce
s
s
in
g
T
h
is i
s
a
n
o
p
e
n
a
c
c
e
ss
a
rticle
u
n
d
e
r th
e
CC B
Y
-
SA
li
c
e
n
se
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
Dr
is
s
Nam
ly
Dep
ar
tm
en
t
o
f
C
o
m
p
u
ter
Scie
n
ce
,
Mo
h
am
m
ed
V
Un
iv
e
r
s
ity
in
R
ab
at
Av
en
u
e
I
b
n
Sin
a
B
.
P 7
6
5
,
Ag
d
al,
1
0
0
9
0
,
R
ab
at,
M
o
r
o
cc
o
E
m
ail: d
.
n
am
ly
@
u
m
5
r
.
ac
.
m
a
1.
I
NT
RO
D
UCT
I
O
N
T
h
e
r
a
p
i
d
g
r
o
w
t
h
o
f
A
r
a
b
i
c
t
e
x
t
d
a
t
a
h
a
s
c
r
e
a
t
e
d
a
n
u
r
g
e
n
t
n
e
e
d
f
o
r
a
d
v
a
n
c
e
d
t
o
o
l
s
c
a
p
a
b
l
e
o
f
q
u
i
c
k
l
y
a
n
d
a
c
c
u
r
a
t
e
l
y
d
e
t
e
c
t
i
n
g
t
h
e
m
o
s
t
s
i
g
n
i
f
ic
a
n
t
t
e
r
m
s
wi
t
h
i
n
a
c
o
r
p
u
s
[
1
]
.
A
u
t
o
m
a
t
e
d
k
e
y
w
o
r
d
d
e
t
e
c
t
i
o
n
[
2
]
,
[
3
]
i
s
a
c
r
u
c
i
a
l
p
r
o
c
e
s
s
f
o
r
v
a
r
i
o
u
s
a
p
p
l
i
c
a
t
i
o
n
s
,
i
n
c
l
u
d
i
n
g
d
o
c
u
m
e
n
t
s
u
m
m
a
r
i
z
a
t
i
o
n
[
4
]
,
s
e
a
r
c
h
e
n
g
i
n
e
o
p
t
i
m
i
z
a
t
i
o
n
[
5
]
,
a
n
d
i
n
f
o
r
m
a
t
i
o
n
r
e
t
r
i
e
v
a
l
[
6
]
.
T
h
e
l
i
t
e
r
at
u
r
e
r
e
v
i
e
w
r
e
v
ea
l
s
a
v
a
r
i
e
t
y
o
f
m
e
t
h
o
d
o
l
o
g
i
e
s
u
t
il
i
z
e
d
i
n
a
u
t
o
m
at
e
d
k
e
y
w
o
r
d
d
e
t
e
c
t
i
o
n
s
o
l
u
ti
o
n
s
,
in
c
l
u
d
i
n
g
s
t
at
is
t
i
ca
l
[
7
]
,
[
8
]
,
l
i
n
g
u
i
s
t
i
c
[
9
]
,
[
1
0
]
,
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
[
1
1
]
-
[
1
5
]
,
g
r
a
p
h
-
b
a
s
ed
[
1
6
]
-
[
1
8
]
,
h
y
b
r
i
d
a
p
p
r
o
a
c
h
e
s
[
1
9
]
,
a
n
d
l
a
r
g
e
l
a
n
g
u
a
g
e
m
o
d
e
l
s
[
2
0
]
.
Ho
wev
er
,
ex
is
tin
g
s
o
lu
tio
n
s
f
ac
e
s
ev
er
al
lim
itatio
n
s
,
esp
ec
ially
wh
en
d
ea
lin
g
with
th
e
c
o
m
p
lex
ities
o
f
t
h
e
A
r
a
b
i
c
l
a
n
g
u
a
g
e
.
C
u
r
r
en
t
a
u
t
o
m
a
t
e
d
k
e
y
w
o
r
d
d
e
t
e
c
ti
o
n
m
e
t
h
o
d
s
o
f
t
e
n
l
a
c
k
l
i
n
g
u
i
s
t
i
c
u
n
d
e
r
s
t
a
n
d
i
n
g
[
3
]
,
f
ailin
g
to
r
ec
o
g
n
ize
co
n
n
ec
tio
n
s
b
etwe
en
wo
r
d
s
th
at
s
h
ar
e
t
h
e
s
am
e
co
n
ce
p
t.
Fo
r
e
x
am
p
l
e,
th
e
Ar
ab
ic
w
o
r
d
s
“
ر
َ
ض
َ
ح
ل
ا
و
،
ي
ِ
ر
ُ
ض
ْ
ح
َ
ت
ِ
ل
َ
ف
،
ا
َ
ر
َ
ض
َ
ح
َ
أ
،
ُ
ر
ُ
ض
ْ
ح
َ
ن
َ
س
َ
و
،
ا
َ
ه
ّ
ن
ُ
ت
ْ
ر
َ
ض
َ
ح
َ
ل
”
(
y
o
u
wo
u
ld
h
a
v
e
atten
d
ed
it,
an
d
we
will
atten
d
,
ar
e
th
e
y
atten
d
,
an
d
y
o
u
let
at
te
n
d
,
a
n
d
t
h
e
u
r
b
an
)
s
h
ar
e
th
e
s
am
e
co
n
ce
p
t,
“
ر
َ
ض
َ
ح
”
(
to
atten
d
)
,
b
u
t
au
to
m
ated
m
eth
o
d
s
m
ig
h
t
m
is
s
th
is
co
n
n
ec
tio
n
.
T
h
ey
al
s
o
s
tr
u
g
g
le
with
wo
r
d
s
en
s
e
d
is
am
b
ig
u
atio
n
,
as
n
o
n
-
d
iacr
i
tized
Ar
ab
ic
wo
r
d
s
ca
n
h
av
e
m
u
ltip
le
m
ea
n
in
g
s
d
ep
en
d
i
n
g
o
n
t
h
e
co
n
tex
t
[
2
1
]
.
T
h
is
ca
n
r
esu
lt
in
th
e
in
c
lu
s
io
n
o
f
ir
r
elev
a
n
t
k
ey
wo
r
d
s
.
Fo
r
i
n
s
tan
ce
,
d
e
p
e
n
d
in
g
o
n
th
e
co
n
tex
t,
th
e
wo
r
d
“
ملو
”
(
wlm
)
ca
n
h
av
e
d
if
f
er
e
n
t
m
ea
n
in
g
s
s
u
ch
as
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
A
th
r
ee
-
p
h
a
s
e
mo
d
el
t
o
ke
ywo
r
d
d
etec
tio
n
in
A
r
a
b
ic
c
o
r
p
o
r
a
(
Dri
s
s
N
a
mly
)
207
“
م
ُ
ل
َ
و
”
(
an
d
b
e
in
s
an
e)
,
“
م
َ
ل
َ
و
”
(
a
n
d
a
g
r
o
u
p
)
,
“
م
َ
ل
َ
و
”
(
an
d
g
at
h
er
)
,
“
ْ
م
َ
ل
َ
و
”
(
an
d
n
o
t)
,
“
َ
م
ِ
ل
َ
و
”
(
an
d
wh
y
)
,
“
م
ْ
ل
َ
و
”
(
b
elt)
,
o
r
“
َ
م
ِ
ل
َ
و
”
(
to
ea
t
in
a
f
ea
s
t)
.
Fu
r
th
er
m
o
r
e
,
au
to
m
ated
m
et
h
o
d
s
also
o
f
ten
p
r
io
r
itize
f
r
e
q
u
en
t
ter
m
s
,
p
o
ten
tially
o
v
er
lo
o
k
in
g
im
p
o
r
ta
n
t
b
u
t
le
s
s
co
m
m
o
n
o
r
s
p
ec
ialized
k
e
y
wo
r
d
s
[
2
2
]
.
Ad
d
itio
n
ally
,
w
h
en
an
au
to
m
ate
d
k
ey
wo
r
d
d
etec
tio
n
m
eth
o
d
lo
o
k
s
at
a
s
in
g
le
d
o
cu
m
en
t
in
is
o
latio
n
,
s
o
m
e
wo
r
d
s
m
ay
n
o
t
ar
is
e
as
k
ey
wo
r
d
s
.
I
n
d
ee
d
,
wh
e
n
a
n
aly
zin
g
a
c
o
r
p
u
s
,
th
ese
s
am
e
wo
r
d
s
m
ig
h
t
ap
p
ea
r
ac
r
o
s
s
m
u
ltip
le
d
o
c
u
m
en
ts
,
in
d
icatin
g
th
eir
im
p
o
r
tan
ce
o
r
r
elev
a
n
ce
with
i
n
th
at
co
llectio
n
.
An
o
th
e
r
lim
i
tatio
n
is
th
at
au
to
m
ated
s
o
lu
ti
o
n
s
ca
n
m
is
tak
en
ly
id
en
tify
in
s
ig
n
if
ican
t
wo
r
d
s
as
k
ey
wo
r
d
s
wh
ile
f
ailin
g
to
d
etec
t
ce
r
tain
im
p
o
r
ta
n
t
o
n
es.
Mo
r
eo
v
er
,
th
e
p
er
f
o
r
m
an
ce
o
f
au
t
o
m
ated
k
e
y
wo
r
d
d
etec
tio
n
s
o
lu
tio
n
s
ca
n
v
ar
y
d
ep
en
d
in
g
o
n
th
e
p
r
o
ce
s
s
ed
lan
g
u
ag
e
[
2
1
]
.
W
h
ile
th
ey
m
ay
wo
r
k
well
in
E
n
g
lis
h
,
th
eir
ef
f
ec
tiv
en
ess
in
lan
g
u
ag
es lik
e
Ar
a
b
ic
m
ay
b
e
co
m
p
r
o
m
is
ed
.
T
o
ad
d
r
ess
th
e
c
o
n
s
tr
ain
ts
o
b
s
er
v
ed
i
n
p
r
ev
io
u
s
r
esear
ch
,
a
c
o
m
m
o
n
s
tr
ateg
y
in
v
o
lv
e
s
u
s
in
g
a
co
m
b
in
atio
n
o
f
k
ey
wo
r
d
d
et
ec
tio
n
m
eth
o
d
s
.
Statis
tical
m
eth
o
d
s
ca
n
q
u
ick
ly
g
e
n
er
at
e
a
wid
e
r
an
g
e
o
f
k
ey
wo
r
d
s
,
wh
ich
ca
n
s
u
b
s
eq
u
en
tly
u
n
d
er
g
o
two
r
o
u
n
d
s
o
f
r
ef
in
em
en
t
to
im
p
r
o
v
e
th
e
q
u
al
ity
an
d
r
elev
an
c
e
o
f
th
e
d
etec
ted
ter
m
s
.
T
h
e
in
it
ia
l
r
ef
in
em
en
t
in
v
o
l
v
es
em
p
lo
y
in
g
a
v
ec
t
o
r
s
p
ac
e
m
o
d
el,
f
o
l
lo
wed
b
y
a
s
ec
o
n
d
r
ef
in
em
en
t
u
tili
zin
g
a
m
ac
h
i
n
e
lear
n
in
g
ap
p
r
o
ac
h
o
n
a
n
ewly
d
ev
elo
p
ed
c
o
r
p
u
s
.
T
h
is
tr
ip
ar
tite
ap
p
r
o
ac
h
ac
h
iev
es
a
h
ar
m
o
n
io
u
s
b
alan
c
e
b
etwe
en
ef
f
icien
cy
an
d
ac
c
u
r
ac
y
,
o
f
f
er
in
g
a
r
e
s
ilien
t
r
eso
lu
tio
n
to
o
v
er
c
o
m
e
th
e
in
h
er
e
n
t
co
n
s
tr
ain
ts
o
f
a
u
to
m
ated
k
ey
wo
r
d
id
e
n
tific
atio
n
.
Par
ticu
lar
ly
,
it
ad
d
r
ess
es
th
e
ch
allen
g
e
o
f
d
etec
tin
g
a
co
m
p
r
eh
e
n
s
iv
e
lis
t
o
f
k
ey
wo
r
d
s
f
o
r
an
en
tire
co
r
p
u
s
,
r
ath
er
th
an
a
k
ey
w
o
r
d
s
lis
t
f
o
r
ea
ch
in
d
iv
id
u
al
d
o
cu
m
e
n
t in
th
e
c
o
r
p
u
s
.
2.
M
E
T
H
O
D
T
h
e
s
af
ar
k
e
y
wo
r
d
s
e
x
tr
ac
tio
n
to
o
l
(
SKET
)
,
s
h
o
wn
in
Fig
u
r
e
1
,
h
as
f
o
u
r
m
ain
s
tep
s
:
p
r
e
p
r
o
ce
s
s
in
g
,
f
r
eq
u
e
n
cy
-
b
ased
lis
t,
v
ec
to
r
s
p
ac
e
lis
t,
an
d
m
ac
h
in
e
lear
n
in
g
lis
t.
T
h
e
f
in
al
k
ey
wo
r
d
s
lis
t
is
cr
ea
ted
b
y
m
er
g
in
g
th
e
th
r
ee
s
ep
ar
at
e
lis
ts
f
r
o
m
f
r
eq
u
e
n
cy
,
v
ec
to
r
s
p
a
ce
,
an
d
m
ac
h
in
e
lear
n
in
g
m
et
h
o
d
s
.
T
h
is
m
e
r
g
in
g
u
s
es
a
lo
g
ical
“
an
d
”
t
o
p
ick
ca
n
d
id
ates
th
at
ap
p
ea
r
in
all
th
r
e
e
k
ey
wo
r
d
lis
ts
.
I
n
th
e
f
o
llo
wi
n
g
s
ec
tio
n
,
we
will
ex
p
lo
r
e
th
e
d
etails o
f
ea
ch
s
tep
in
SKET
.
Fig
u
r
e
1
.
Pro
p
o
s
ed
p
ip
elin
e
f
o
r
k
ey
wo
r
d
d
etec
tio
n
2
.
1
.
P
re
pro
ce
s
s
ing
Du
r
in
g
th
is
s
tag
e,
th
e
m
ain
o
b
jectiv
e
is
to
p
r
ep
ar
e
th
e
d
ata
f
o
r
p
ip
elin
e
u
tili
za
tio
n
b
y
r
e
m
o
v
in
g
n
o
is
e
f
r
o
m
th
e
o
r
ig
in
al
tex
t.
T
h
is
p
r
o
ce
s
s
in
clu
d
es
to
k
en
izati
o
n
a
n
d
r
em
o
v
in
g
p
u
n
ctu
ati
o
n
m
a
r
k
s
,
s
p
ec
ial
ch
ar
ac
ter
s
,
n
o
n
-
Ar
ab
ic
letter
s
,
an
d
d
ig
its
.
Su
b
s
eq
u
en
tly
,
s
to
p
-
wo
r
d
s
ar
e
r
em
o
v
ed
ev
e
n
th
o
u
g
h
th
ey
ar
e
co
m
m
o
n
l
y
f
o
u
n
d
,
as
th
ey
u
s
u
ally
m
ak
e
u
p
3
0
to
5
0
%
o
f
th
e
tex
t
d
ata
s
ize
an
d
ar
e
n
o
t
d
ee
m
ed
as
k
ey
wo
r
d
s
.
T
h
e
to
k
e
n
s
th
at
r
em
ain
ar
e
le
m
m
atize
d
,
as
it
is
ad
v
is
ed
to
wo
r
k
with
th
e
lem
m
a
o
f
th
e
wo
r
d
s
r
ath
er
th
an
t
h
e
s
tem
,
r
o
o
t,
o
r
th
e
wo
r
d
its
elf
.
T
h
e
p
r
ep
r
o
ce
s
s
in
g
s
tep
s
ar
e
p
er
f
o
r
m
e
d
u
s
in
g
SAFAR
to
o
ls
[
2
3
]
.
T
h
e
p
r
ep
r
o
ce
s
s
in
g
p
r
o
ce
s
s
in
clu
d
es
s
ev
er
al
cr
itical
s
tag
es:
f
ir
s
t,
t
h
e
d
o
cu
m
e
n
ts
u
n
d
er
g
o
to
k
en
izatio
n
,
wh
ich
b
r
ea
k
s
th
e
tex
t
in
to
m
an
ag
ea
b
l
e
u
n
its
.
T
h
is
is
f
o
llo
wed
b
y
n
o
r
m
aliza
tio
n
,
wh
er
e
s
p
ec
ial
ch
ar
ac
ter
s
,
n
o
n
-
Ar
a
b
ic
letter
s
,
an
d
to
k
en
s
th
at
co
n
s
is
t
s
o
lely
o
f
d
ig
its
o
r
c
o
n
tain
b
o
th
d
ig
its
an
d
letter
s
ar
e
r
em
o
v
ed
.
Su
b
s
eq
u
en
tly
,
s
to
p
-
w
o
r
d
s
ar
e
elim
in
ated
to
f
o
c
u
s
o
n
t
h
e
m
o
s
t
m
e
a
n
i
n
g
f
u
l
t
e
r
m
s
,
a
n
d
t
h
e
r
e
m
a
i
n
i
n
g
t
o
k
e
n
s
a
r
e
l
e
m
m
a
t
i
z
e
d
u
s
i
n
g
t
h
e
S
A
F
A
R
l
e
m
m
a
t
i
z
e
r
[
2
4
]
.
T
h
is
p
r
o
ce
s
s
in
g
s
tep
p
la
y
s
a
cr
u
cial
r
o
le
in
ad
d
r
ess
in
g
ch
a
llen
g
es
ass
o
ciate
d
with
lin
g
u
i
s
tic
u
n
d
er
s
tan
d
in
g
an
d
n
o
n
-
d
iacr
itized
Ar
ab
ic.
T
h
is
is
b
ec
au
s
e
lem
m
atiza
tio
n
b
r
in
g
s
to
g
eth
e
r
to
k
e
n
s
with
th
e
s
am
e
m
ea
n
in
g
u
n
d
er
a
s
in
g
le
lem
m
a,
th
e
r
eb
y
en
h
an
cin
g
lin
g
u
is
tic
u
n
d
e
r
s
tan
d
in
g
.
Mo
r
eo
v
e
r
,
th
e
lem
m
a
tizer
u
s
ed
p
r
o
d
u
ce
s
d
iacr
itized
lem
m
as,
f
u
r
t
h
er
c
o
n
tr
ib
u
tin
g
to
th
e
o
v
er
all
e
f
f
ec
tiv
en
ess
o
f
th
e
p
r
o
ce
s
s
.
On
ce
p
r
ep
r
o
ce
s
s
in
g
is
co
m
p
lete,
we
v
alid
ate
th
e
k
e
y
wo
r
d
d
etec
tio
n
p
r
o
ce
s
s
th
r
o
u
g
h
t
h
r
ee
ex
p
er
im
en
ts
c
o
n
d
u
cted
o
n
8
0
%
o
f
th
e
co
r
p
u
s
,
wh
ile
th
e
r
em
ain
in
g
2
0
% is
u
s
ed
f
o
r
ev
al
u
atio
n
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
37
,
No
.
1
,
J
an
u
ar
y
20
25
:
206
-
2
1
3
208
2
.
2
.
F
re
qu
ency
lis
t
I
n
th
e
s
u
b
s
eq
u
en
t
p
h
ase
o
f
SKET
,
a
f
r
e
q
u
en
c
y
-
b
ased
a
p
p
r
o
ac
h
is
em
p
lo
y
ed
to
g
en
e
r
ate
a
r
o
s
ter
o
f
p
o
ten
tial
k
ey
wo
r
d
s
b
y
co
n
s
id
e
r
in
g
th
eir
f
r
eq
u
en
cy
.
I
n
o
r
d
er
t
o
ac
h
iev
e
t
h
is
,
ter
m
f
r
e
q
u
en
c
y
(
T
F)
is
u
tili
ze
d
as
a
p
r
o
b
ab
ilit
y
f
u
n
ctio
n
f
o
r
ev
er
y
lem
m
atize
d
to
k
en
.
T
h
e
to
k
e
n
s
with
th
e
h
ig
h
est
p
r
o
b
ab
ilit
y
ar
e
r
ec
o
g
n
ized
as
p
o
ten
tial
k
e
y
wo
r
d
s
.
T
h
e
T
F
s
tatis
t
ic
g
au
g
es
th
e
ap
p
ea
r
an
ce
f
r
eq
u
en
cy
o
f
a
to
k
e
n
'
s
in
th
e
c
o
r
p
u
s
an
d
i
s
co
m
p
u
ted
b
y
d
i
v
id
in
g
th
e
n
u
m
b
er
o
f
o
cc
u
r
r
en
ce
s
o
f
th
e
t
o
k
en
“
f
”
b
y
th
e
to
tal
n
u
m
b
er
o
f
to
k
en
s
“
N
”
as
f
o
llo
ws:
=
(
1
)
C
o
n
s
eq
u
en
tly
,
in
o
r
d
e
r
to
id
e
n
tify
th
e
in
itial
lis
t,
u
n
iq
u
e
le
m
m
as
ar
e
f
ir
s
t
id
en
tifie
d
an
d
th
eir
f
r
eq
u
e
n
cies
in
th
e
wh
o
le
co
r
p
u
s
ar
e
co
u
n
ted
,
we
s
o
r
t
th
em
f
r
o
m
h
ig
h
to
lo
w
,
th
en
,
we
s
elec
t
th
e
f
ir
s
t 5
0
t
o
k
en
s
as
k
e
y
wo
r
d
’
s
ca
n
d
id
ates.
2
.
3
.
Vec
t
o
r
s
pa
ce
lis
t
I
n
o
r
d
er
to
p
r
ev
e
n
t
th
e
d
ete
ctio
n
o
f
in
s
ig
n
if
ican
t
wo
r
d
s
,
an
d
to
p
r
ev
e
n
t
th
e
d
etec
tio
n
in
s
in
g
le
d
o
cu
m
e
n
t
in
is
o
latio
n
,
we
im
p
r
o
v
e
th
e
r
esu
lts
o
b
tain
ed
f
r
o
m
th
e
f
r
e
q
u
en
c
y
-
b
ased
s
tep
b
y
i
n
teg
r
atin
g
a
v
ec
to
r
s
p
ac
e
ap
p
r
o
a
ch
in
t
o
th
e
SKE
T
f
r
am
ewo
r
k
.
T
h
is
s
tep
aim
s
to
r
ef
in
e
t
h
e
d
etec
tio
n
o
f
ca
n
d
id
ate
k
ey
w
o
r
d
s
b
y
p
in
p
o
in
tin
g
t
o
k
en
s
t
h
at
ex
h
i
b
it
a
c
o
n
s
is
ten
t
d
is
tr
ib
u
tio
n
th
r
o
u
g
h
o
u
t
th
e
en
tire
co
r
p
u
s
.
T
o
k
en
s
th
at
ar
e
f
r
eq
u
e
n
tly
en
co
u
n
ter
ed
b
u
t
ar
e
co
n
f
in
e
d
to
is
o
lated
p
ar
ag
r
ap
h
s
with
in
a
s
in
g
le
d
o
c
u
m
en
t
ar
e
d
ee
m
ed
in
ap
p
r
o
p
r
iate
as
k
ey
wo
r
d
s
f
o
r
th
e
o
v
er
all
co
r
p
u
s
.
B
y
em
p
lo
y
in
g
th
is
s
tr
ateg
y
,
we
s
ee
k
to
im
p
r
o
v
e
th
e
p
r
ec
is
io
n
an
d
r
el
ev
an
ce
o
f
th
e
k
ey
wo
r
d
s
ex
t
r
ac
ted
f
r
o
m
th
e
t
ex
tu
al
d
ata.
Fro
m
an
o
r
g
an
izatio
n
al
s
tan
d
p
o
in
t,
a
co
r
p
u
s
co
n
s
is
ts
o
f
a
co
llectio
n
o
f
d
iv
e
r
s
e
d
o
cu
m
en
ts
,
ea
ch
co
n
tain
in
g
m
u
ltip
le
p
ar
ag
r
a
p
h
s
.
I
n
th
is
f
r
am
ewo
r
k
,
a
to
k
e
n
is
co
n
s
id
er
ed
u
n
if
o
r
m
ly
d
is
tr
ib
u
ted
ac
r
o
s
s
t
h
e
co
r
p
u
s
if
it
a
p
p
ea
r
s
in
th
e
m
ajo
r
ity
o
f
b
o
th
d
o
c
u
m
en
ts
an
d
p
ar
a
g
r
ap
h
s
.
T
o
o
p
er
atio
n
ali
ze
th
is
co
n
ce
p
t,
w
e
ap
p
ly
th
e
c
o
n
v
e
n
tio
n
al
v
ec
to
r
s
p
ac
e
m
o
d
el
to
r
ep
r
esen
t
t
h
e
o
cc
u
r
r
en
ce
o
f
to
k
e
n
s
in
s
tead
o
f
e
n
tire
tex
t
d
o
cu
m
e
n
ts
.
I
n
th
is
r
ev
is
ed
m
o
d
el,
ea
ch
to
k
en
is
co
n
ce
p
tu
alize
d
as
a
v
ec
to
r
with
d
is
tin
ct
co
m
p
o
n
en
ts
in
d
icatin
g
its
p
r
esen
ce
o
r
a
b
s
en
ce
in
ea
ch
p
a
r
ag
r
a
p
h
.
T
o
id
en
tify
p
o
te
n
tial
k
ey
wo
r
d
s
,
we
h
av
e
estab
lis
h
ed
a
p
r
o
to
ty
p
e
to
k
e
n
th
at
is
p
r
esen
t
in
ev
e
r
y
p
ar
ag
r
ap
h
.
T
h
e
s
im
ilar
ity
b
etwe
en
a
t
o
k
en
an
d
th
e
p
r
o
to
ty
p
e
is
ass
es
s
ed
b
y
m
ea
s
u
r
in
g
th
e
d
is
tan
ce
in
th
is
v
ec
to
r
s
p
ac
e,
u
tili
zin
g
co
s
in
e
s
im
ilar
ity
t
o
co
m
p
ar
e
th
e
two
v
ec
to
r
s
.
T
o
k
e
n
s
th
at
ex
h
i
b
it p
r
o
x
im
ity
to
th
e
p
r
o
t
o
ty
p
e
a
r
e
id
en
tifie
d
as c
an
d
id
ate
k
ey
wo
r
d
s
.
Du
r
in
g
th
e
c
o
n
s
tr
u
ctio
n
o
f
th
e
m
o
d
el,
we
esti
m
ate
th
e
v
al
u
e
o
f
a
r
esp
o
n
s
e
v
ar
iab
le
b
ased
o
n
two
ex
p
lan
ato
r
y
v
a
r
iab
les,
X
1
an
d
X
2
,
wh
ich
r
ep
r
esen
t
th
e
p
r
esen
ce
r
ate
i
n
a
s
p
ec
if
ic
s
ec
tio
n
o
f
a
d
o
cu
m
en
t
an
d
th
e
p
r
esen
ce
r
ate
ac
r
o
s
s
p
ar
a
g
r
ap
h
s
,
r
esp
ec
tiv
ely
.
T
h
e
r
esu
ltin
g
f
u
n
ctio
n
is
f
o
r
m
u
late
d
as
a
weig
h
ted
s
u
m
o
f
th
ese
ex
p
lan
ato
r
y
v
ar
iab
les b
y
(
2
)
.
(
)
=
1
×
1
+
2
×
2
(
2
)
I
n
o
r
d
er
to
d
eter
m
in
e
t
h
e
weig
h
ts
w
1
an
d
w
2
,
th
e
s
ig
n
if
ican
c
e
o
f
ea
ch
v
ar
iab
le
is
ev
alu
ate
d
b
y
test
in
g
d
if
f
er
en
t
weig
h
t
co
m
b
in
atio
n
s
an
d
a
n
aly
zin
g
th
eir
im
p
ac
t
o
n
th
e
in
f
er
r
ed
f
u
n
ctio
n
.
T
h
e
weig
h
t
p
air
s
test
ed
in
clu
d
e
[
0
.
5
,
0
.
5
]
,
[
0
.
3
,
0
.
7
]
,
[
0
.
7
,
0
.
3
]
,
[
0
.
1
,
0
.
9
]
,
an
d
[
0
.
9
,
0
.
1
]
f
o
r
[
w
1
,
w
2
]
.
T
h
r
o
u
g
h
th
is
ex
p
er
im
e
n
tatio
n
,
it
is
f
o
u
n
d
th
at
th
e
m
ax
im
u
m
a
v
er
ag
e
v
ar
iatio
n
in
th
e
in
f
er
r
e
d
f
u
n
ctio
n
is
2
.
3
3
%,
o
b
s
er
v
e
d
b
etwe
en
t
h
e
p
air
s
[
0
.
5
,
0
.
5
]
an
d
[
0
.
7
,
0
.
3
]
.
As a
r
esu
lt,
it is
d
ec
id
ed
to
allo
ca
te
id
en
tical
weig
h
ts
to
ev
er
y
ex
p
l
an
ato
r
y
f
ac
t
o
r
.
T
h
e
f
in
al
in
f
er
r
e
d
f
u
n
ctio
n
is
a
s
u
m
o
f
th
e
e
x
p
lan
ato
r
y
v
ar
iab
les with
eq
u
al
weig
h
ts
b
y
(
3
)
.
(
)
=
1
+
2
2
(
3
)
T
o
f
o
r
m
o
u
r
l
is
t
o
f
ca
n
d
id
ate
s
,
we
o
r
g
an
ize
th
e
to
k
e
n
s
b
ased
o
n
th
eir
p
r
o
b
ab
ilit
ies
in
a
d
escen
d
in
g
m
a
n
n
er
.
T
h
en
,
we
s
elec
t th
e
to
p
5
0
t
o
k
en
s
as p
o
ten
tial k
ey
wo
r
d
s
.
2
.
4
.
M
a
chine le
a
rning
lis
t
I
n
th
is
s
tag
e,
th
e
ef
f
icac
y
o
f
th
e
f
r
e
q
u
en
c
y
an
d
v
ec
t
o
r
s
p
a
ce
m
eth
o
d
o
lo
g
ies
o
f
SKET
is
en
h
an
ce
d
th
r
o
u
g
h
th
e
ap
p
licatio
n
o
f
a
class
if
icatio
n
alg
o
r
ith
m
,
wh
ich
aid
s
in
id
en
tify
in
g
th
is
th
ir
d
s
et
o
f
k
ey
wo
r
d
ca
n
d
id
ates.
T
h
is
s
tag
e
aim
s
to
av
o
id
t
h
e
o
m
is
s
io
n
o
f
cr
u
ci
al
b
u
t
less
co
m
m
o
n
o
r
s
p
ec
ia
lized
k
ey
wo
r
d
s
b
y
in
teg
r
atin
g
d
o
m
ain
-
s
p
ec
i
f
ic
k
n
o
wled
g
e.
T
h
e
i
n
teg
r
atio
n
o
f
d
o
m
ai
n
ex
p
er
tis
e
is
ex
p
ec
t
ed
to
e
n
h
an
ce
th
e
ac
cu
r
ac
y
an
d
ef
f
icie
n
cy
o
f
th
e
k
ey
wo
r
d
id
en
tific
atio
n
p
r
o
ce
s
s
ac
r
o
s
s
d
if
f
er
en
t d
atasets
.
T
o
d
eter
m
in
e
t
h
e
m
o
s
t
s
u
itab
le
alg
o
r
ith
m
f
o
r
SKET
,
v
a
r
io
u
s
class
if
ier
s
ar
e
ev
alu
ated
b
as
e
d
o
n
th
eir
ac
cu
r
ac
y
an
d
ex
ec
u
tio
n
tim
e
(
E
T
)
.
C
o
n
s
id
er
in
g
ET
is
ess
en
tial
as
k
ey
wo
r
d
d
etec
tio
n
task
s
o
f
ten
in
v
o
lv
e
r
ea
l
-
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
A
th
r
ee
-
p
h
a
s
e
mo
d
el
t
o
ke
ywo
r
d
d
etec
tio
n
in
A
r
a
b
ic
c
o
r
p
o
r
a
(
Dri
s
s
N
a
mly
)
209
tim
e
p
r
o
ce
s
s
in
g
o
r
h
an
d
lin
g
la
r
g
e
am
o
u
n
ts
o
f
d
ata.
A
m
etr
ic
is
ca
lcu
lated
th
at
c
o
m
b
in
es
ET
an
d
p
r
o
p
o
r
tio
n
o
f
er
r
o
r
s
(
PE
=
1
-
Acc
u
r
ac
y
)
.
T
h
e
in
v
er
s
e
ef
f
icien
cy
s
co
r
e
(
I
E
S)
is
d
ef
in
ed
as
th
e
ET
ad
ju
s
t
ed
f
o
r
th
e
n
u
m
b
er
o
f
er
r
o
r
s
m
ad
e
.
A
lo
wer
v
al
u
e
o
f
I
E
S in
d
icate
s
s
u
p
er
io
r
p
er
f
o
r
m
an
ce
.
=
1
−
(
)
(
4
)
T
ab
le
1
p
r
esen
ts
th
e
r
esu
lts
o
f
th
e
class
if
ier
s
as
s
es
s
ed
u
s
i
n
g
a
co
n
s
tr
ain
ed
d
ataset
co
m
p
r
is
in
g
1
0
n
ews
ar
ticles
o
b
tain
ed
f
r
o
m
th
e
h
esp
r
ess
.
co
m
n
ews
p
latf
o
r
m
.
T
h
is
d
ataset
in
clu
d
ed
a
to
t
al
o
f
4
6
,
9
2
4
to
k
en
s
,
wh
ich
wer
e
m
an
u
ally
an
n
o
tated
with
k
ey
wo
r
d
tag
s
.
Fo
llo
win
g
th
is
p
r
elim
in
ar
y
p
r
o
o
f
o
f
c
o
n
ce
p
t,
th
e
f
in
d
in
g
s
ca
n
b
e
ex
t
r
ap
o
lated
t
o
a
m
o
r
e
ex
ten
s
iv
e
co
r
p
u
s
.
T
h
e
I
E
S
r
esu
lts
o
f
f
er
th
e
p
o
s
s
ib
ilit
y
o
f
s
el
ec
tin
g
eith
er
Naïv
e
B
ay
es
o
r
L
o
g
is
tic
R
eg
r
ess
io
n
as
th
e
alg
o
r
ith
m
o
f
ch
o
ice.
Nev
er
th
eless
,
g
iv
en
th
e
s
ig
n
if
ican
t
d
if
f
er
en
ce
in
ac
cu
r
ac
y
a
n
d
th
e
n
eg
lig
i
b
le
v
ar
iati
o
n
in
ET
,
it
is
clea
r
th
at
L
o
g
is
tic
R
eg
r
ess
io
n
em
er
g
es
as
th
e
m
o
s
t
ap
p
r
o
p
r
iate
o
p
tio
n
to
class
if
y
t
o
k
en
s
in
to
two
d
is
tin
ct
class
es
,
n
am
ely
k
ey
wo
r
d
an
d
n
o
n
-
k
e
y
wo
r
d
.
T
h
u
s
,
to
g
e
n
er
ate
th
e
th
ir
d
lis
t
o
f
k
ey
w
o
r
d
ca
n
d
id
ates,
we
u
tili
ze
th
e
lo
g
is
tic
r
eg
r
ess
io
n
alg
o
r
ith
m
f
r
o
m
th
e
W
E
KA
lib
r
a
r
y
.
T
h
e
co
r
p
u
s
is
ca
teg
o
r
ized
in
to
two
class
es:
“
0
”
f
o
r
n
o
n
-
k
ey
wo
r
d
s
an
d
“
1
”
f
o
r
k
ey
wo
r
d
s
.
Up
o
n
lo
ad
in
g
th
e
d
ata
f
ile,
a
“
Strin
g
T
o
W
o
r
d
Vec
to
r
”
f
ilter
is
ap
p
lied
to
co
n
v
er
t
s
tr
in
g
s
in
to
N
-
g
r
am
s
,
en
a
b
lin
g
a
m
o
r
e
n
u
a
n
ce
d
a
n
aly
s
is
o
f
th
e
te
x
t.
T
h
e
m
o
d
el
is
th
e
n
c
o
n
s
tr
u
cte
d
u
s
in
g
th
e
lo
g
is
tic
r
eg
r
ess
io
n
class
if
ier
.
T
h
e
last
s
tag
e
o
f
SKET
en
tails
m
er
g
in
g
th
e
th
r
ee
ca
n
d
id
ate
lis
ts
in
to
a
u
n
if
ie
d
lis
t
th
r
o
u
g
h
a
lo
g
ical
“
an
d
”
o
p
er
a
tio
n
,
wh
ich
d
etec
ts
to
k
en
s
th
at
ex
is
t
in
al
l
th
r
ee
lis
ts
.
T
o
g
a
u
g
e
th
e
ef
f
icac
y
o
f
SKET
,
th
e
s
u
b
s
eq
u
en
t sectio
n
o
u
tlin
es th
e
ex
p
e
r
im
en
tal
r
esu
lts
f
o
r
ev
alu
atin
g
its
p
er
f
o
r
m
a
n
ce
.
T
ab
le
1
.
T
h
e
o
u
tc
o
m
es o
f
th
e
co
m
p
ar
is
o
n
b
etwe
en
th
e
class
if
ier
s
A
l
g
o
r
i
t
h
m
A
c
c
u
r
a
c
y
(
%)
Ex
e
c
u
t
i
o
n
t
i
m
e
(
s)
I
ES
B
a
y
e
s
i
a
n
l
o
g
i
s
t
i
c
r
e
g
r
e
ss
i
o
n
1
0
0
5
4
.
2
4
5
4
,
2
4
J4
8
d
e
c
i
si
o
n
t
r
e
e
9
6
.
8
8
1
6
3
7
.
5
5
1
6
9
0
,
7
5
Lo
g
i
s
t
i
c
r
e
g
r
e
ssi
o
n
1
0
0
1
1
.
2
3
1
1
,
2
3
N
a
ï
v
e
B
a
y
e
s
8
9
.
3
4
8
7
9
.
8
1
1
0
,
9
7
R
a
n
d
o
m f
o
r
e
s
t
9
9
.
9
5
2
1
3
.
1
2
2
1
3
,
1
1
S
u
p
p
o
r
t
v
e
c
t
o
r
ma
c
h
i
n
e
1
0
0
1
2
1
.
9
8
1
2
1
,
9
8
3.
RE
SU
L
T
S
AND
D
I
SCU
SS
I
O
N
T
h
e
s
ec
tio
n
s
tar
ts
with
a
d
eta
iled
o
v
er
v
iew
o
f
th
e
co
r
p
u
s
u
tili
ze
d
.
Su
b
s
eq
u
en
tly
,
an
an
al
y
s
is
o
f
th
e
ex
p
er
im
en
t
ca
r
r
ied
o
u
t
an
d
its
f
in
d
in
g
s
is
p
r
esen
ted
.
T
h
is
is
th
en
f
o
llo
wed
b
y
a
co
m
p
ar
ati
v
e
an
aly
s
is
an
d
a
n
o
v
er
ar
c
h
in
g
d
is
cu
s
s
io
n
.
3
.
1
.
T
he
CAK
E
co
rpus
Ou
r
aim
is
to
ev
alu
ate
o
u
r
r
esear
ch
b
y
u
tili
zin
g
co
r
p
o
r
a
f
r
o
m
p
r
io
r
s
tu
d
ies;
h
o
wev
er
,
u
n
f
o
r
tu
n
ately
,
th
o
s
e
co
r
p
o
r
a
ar
e
u
n
av
ailab
le
ex
ce
p
t f
o
r
th
e
o
n
es lis
ted
b
elo
w:
−
Ar
ab
ic
k
ey
p
h
r
ase
e
x
tr
ac
tio
n
co
r
p
u
s
(
AKE
C
)
co
n
s
is
tin
g
o
f
1
6
0
Ar
ab
ic
d
o
c
u
m
en
t
s
f
r
o
m
a
v
a
r
iety
o
f
s
o
u
r
ce
s
an
d
th
eir
k
ey
p
h
r
ases
co
llected
u
s
in
g
a
lar
g
e
-
s
ca
le
cr
o
wd
s
o
u
r
cin
g
ex
p
e
r
im
en
t;
−
Ar
ab
ic
d
ataset
f
o
r
a
u
to
m
atic
k
ey
p
h
r
ase
ex
tr
ac
tio
n
(
ADAK
E
)
co
n
tain
s
4
0
0
d
o
cu
m
e
n
t
s
(
1
,
7
0
8
,
1
6
8
to
k
en
s
)
co
v
er
in
g
1
8
to
p
ics.
T
e
n
Key
p
h
r
ases
p
er
d
o
c
u
m
en
t a
r
e
ex
tr
ac
ted
a
r
ea
d
er
;
−
Ar
ab
ic
W
ik
ip
ed
ia
C
o
r
p
u
s
(
AW
C
)
co
m
p
o
s
ed
o
f
a
d
u
m
p
f
il
e
o
f
1
0
0
Ar
ab
ic
W
ik
ip
ed
ia
p
a
g
es
.
Key
wo
r
d
s
ar
e
o
b
tain
ed
f
r
o
m
th
e
k
e
y
wo
r
d
m
eta
-
tag
ass
o
ciate
d
with
ea
c
h
p
ag
e.
T
h
u
s
,
ass
ess
in
g
SKET
th
r
o
u
g
h
th
e
u
s
e
o
f
AKE
C
,
ADA
KE
,
o
r
AW
C
is
in
ap
p
r
o
p
r
ia
te
d
u
e
to
in
d
iv
id
u
al
d
o
cu
m
en
t
lim
itatio
n
.
I
n
co
n
tr
ast,
SKET
is
tailo
r
ed
to
i
d
en
tify
a
s
in
g
u
la
r
lis
t
o
f
k
ey
w
o
r
d
s
ap
p
licab
le
to
th
e
e
n
tire
co
r
p
u
s
d
o
m
ain
.
As
a
r
esu
lt,
we
h
av
e
cr
ea
te
d
t
h
e
C
o
r
p
u
s
f
o
r
Ar
ab
ic
k
e
y
wo
r
d
s
ex
t
r
ac
tio
n
(
C
AKE
)
to
tac
k
le
th
is
is
s
u
e.
I
t
co
n
s
is
ts
o
f
2
7
7
8
n
ews
ar
ticles,
e
n
co
m
p
ass
in
g
ap
p
r
o
x
i
m
ately
4
m
illi
o
n
to
k
en
s
in
f
o
u
r
d
if
f
er
en
t
ca
teg
o
r
ies:
Ar
t,
E
co
n
o
m
y
,
Po
liti
cs,
an
d
Sp
o
r
t.
T
h
e
c
o
r
p
u
s
was
s
o
u
r
ce
d
f
r
o
m
a
n
ews
web
s
ite
th
at
was
u
s
ed
b
ef
o
r
e
an
d
k
e
y
wo
r
d
s
wer
e
ass
ig
n
ed
s
em
i
-
au
t
o
m
atica
lly
u
s
in
g
lex
ico
n
s
f
r
o
m
th
e
s
p
ec
if
ic
d
o
m
ain
s
o
u
tlin
ed
in
T
ab
le
2
.
Fig
u
r
e
2
s
h
o
ws
p
ar
t
o
f
C
AKE
,
h
ig
h
lig
h
tin
g
h
o
w
it
i
s
d
iv
id
ed
in
to
d
o
m
ain
s
.
E
ac
h
d
o
m
ai
n
h
as a
g
r
o
u
p
o
f
ar
ticles an
d
a
lis
t o
f
k
e
y
wo
r
d
s
.
E
v
e
r
y
ar
ticle
in
clu
d
es a
titl
e
an
d
a
tex
t.
T
ab
le
3
d
is
p
lay
s
a
v
ar
iety
o
f
s
tatis
t
ics
co
m
p
ar
in
g
th
e
ex
is
tin
g
co
r
p
o
r
a
with
th
e
d
ev
elo
p
e
d
o
n
e.
T
h
e
Ar
ab
ic
W
ik
ip
ed
ia
C
o
r
p
u
s
h
as
a
m
o
d
er
ate
n
u
m
b
er
o
f
d
o
cu
m
en
ts
,
f
o
llo
wed
b
y
AKE
C
,
Ar
ab
ic
Data
s
et,
an
d
C
AKE
,
t
o
talin
g
2
7
7
8
d
o
c
u
m
e
n
ts
.
T
h
e
k
ey
w
o
r
d
s
tatis
tics
ar
e
o
f
u
tm
o
s
t
im
p
o
r
tan
ce
f
o
r
o
u
r
r
esear
ch
.
AKE
C
,
Ar
ab
ic
W
ik
ip
ed
ia
C
o
r
p
u
s
,
a
n
d
Ar
ab
ic
Data
s
et
p
r
o
v
id
e
a
s
et
o
f
k
ey
w
o
r
d
s
f
o
r
ea
ch
d
o
c
u
m
en
t,
wh
ile
C
AKE
o
f
f
er
s
a
s
in
g
le
lis
t
o
f
k
e
y
wo
r
d
s
f
o
r
all
d
o
c
u
m
en
ts
in
ea
c
h
d
o
m
ain
.
C
AKE
will
b
e
ac
ce
s
s
ib
le
f
o
r
f
r
ee
to
r
esear
ch
er
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
37
,
No
.
1
,
J
an
u
ar
y
20
25
:
206
-
2
1
3
210
T
ab
le
2
.
L
e
x
ico
n
s
u
s
ed
f
o
r
tag
g
in
g
p
r
o
ce
s
s
Le
x
i
c
o
n
a
u
t
h
o
r
Y
e
a
r
D
o
ma
i
n
U
R
L
م
د
ق
ل
ا
ةر
ك
ت
ا
ح
لطص
م
د
ر
س
م
ي
وا
ن
ش
لا
ر
ي
م
س
2
0
0
7
S
p
o
r
t
h
t
t
p
s
:
/
/
w
w
w
.
n
o
o
r
-
b
o
o
k
.
c
o
m
Th
e
S
p
o
r
t
s
D
i
c
t
i
o
n
a
r
y
-
-
S
p
o
r
t
h
t
t
p
s
:
/
/
w
w
w
.
l
e
x
i
c
o
o
l
.
c
o
m
A
r
a
b
i
c
s
p
o
r
t
s &
h
o
b
b
i
e
s
v
o
c
a
b
u
l
a
r
y
d
e
s
e
r
t
-
sk
y
2
0
0
7
S
p
o
r
t
h
t
t
p
s
:
/
/
a
r
a
b
i
c
.
d
e
s
e
r
t
-
s
k
y
.
n
e
t
ةي
لا
م
لا
و
ةي
د
ا
ص
ت
ق
او
ةي
ر
ا
ج
ت
لا
ت
ا
ح
لطص
م
لا
سوم
ا
ق
ح
ي
ر
ج
ى
ن
م
2
0
0
0
Ec
o
n
o
my
h
t
t
p
s
:
/
/
w
w
w
.
mk
t
b
t
y
-
e
n
g
.
c
o
m
ﻝوا
د
ت
لا
ت
ا
ح
لط
ص
م
و
ت
ﻼ
م
ﻌ
لا
ت
ا
ح
لطص
م
A
r
a
b
i
c
t
r
a
d
e
r
-
Ec
o
n
o
my
h
t
t
p
s
:
/
/
w
w
w
.
a
r
a
b
i
c
t
r
a
d
e
r
.
c
o
m
A
r
a
b
i
c
me
d
i
a
a
n
d
t
h
e
a
r
t
v
o
c
a
b
u
l
a
r
y
d
e
s
e
r
t
-
sk
y
2
0
0
7
Art
h
t
t
p
s
:
/
/
a
r
a
b
i
c
.
d
e
s
e
r
t
-
s
k
y
.
n
e
t
ةي
لي
ك
ش
ت
و
ةي
ن
ف
ت
ا
ح
لطص
م
a
r
c
h
d
i
c
t
i
o
n
a
r
y
2
0
0
8
Art
h
t
t
p
s
:
/
/
a
r
c
h
d
i
c
.
b
l
o
g
s
p
o
t
.
c
o
m
ةي
س
ا
ي
س
ل
ا
ت
ا
ح
لطص
م
لا
م
ج
ﻌ
م
ن
ي
ر
ح
ب
لا
د
ه
ﻌ
م
ةي
س
ا
ي
س
لا
ةي
م
ن
ت
لل
2
0
1
4
P
o
l
i
t
i
c
s
h
t
t
p
s
:
/
/
w
w
w
.
b
i
p
d
.
o
r
g
ةي
س
ا
ي
س
ل
او
ةي
ن
د
م
لا
ت
ا
ح
لطص
م
لا
سوم
ا
ق
ﻝا
ح
ر
ر
م
ع
،
فس
وي
ن
م
ي
أ
،
ي
لا
ب
ج
لا
ر
ق
ص
2
0
1
4
P
o
l
i
t
i
c
s
h
t
t
p
s
:
/
/
w
w
w
.
sh
a
ms
-
p
a
l
.
o
r
g
ةي
د
ا
ص
ت
ق
ا
ت
ا
ح
لطص
م
سوم
ا
ق
د
م
ح
أ
ي
د
ج
م
د
م
ح
م
2
0
1
9
Ec
o
n
o
my
h
t
t
p
s
:
/
/
w
w
w
.
n
o
o
r
-
b
o
o
k
.
c
o
m
Fig
u
r
e
2
.
E
x
tr
ac
t o
f
C
AKE
T
ab
le
3
.
C
o
r
p
o
r
a
s
tatis
tics
C
o
r
p
u
s
D
o
ma
i
n
s
N
b
r
o
f
D
o
c
u
m
e
n
t
s
A
v
g
n
b
r
o
f
t
o
k
e
n
s
N
b
r
o
f
t
o
k
e
n
s
N
b
r
o
f
k
e
y
w
o
r
d
s
C
A
K
E
4
2
,
7
7
8
1
,
4
4
0
4
,
0
0
0
,
0
0
0
2
3
5
A
K
E
C
9
1
6
0
7
5
7
1
2
1
,
0
7
4
9
,
9
4
9
A
r
a
b
i
c
D
a
t
a
s
e
t
18
4
0
0
4
,
2
7
0
1
,
7
0
8
,
1
6
8
4
,
0
0
0
A
r
a
b
i
c
W
i
k
i
p
e
d
i
a
C
o
r
p
u
s
-
1
0
0
2
,
2
3
0
2
,
1
2
3
,
1
8
2
7
,
6
0
6
3
.
2
.
E
v
a
lua
t
i
o
n r
esu
lt
s
I
n
th
e
ex
p
er
im
en
t,
we
a
d
h
er
e
to
SKET
,
lev
er
ag
in
g
a
6
-
c
o
r
e
W
in
d
o
ws
co
m
p
u
ter
e
q
u
ip
p
ed
with
an
I
n
tel(
R
)
C
o
r
e
i7
2
.
6
GHz
C
PU
an
d
1
6
GB
m
em
o
r
y
.
T
o
e
v
alu
ate
th
e
p
er
f
o
r
m
an
ce
o
f
o
u
r
k
ey
wo
r
d
d
etec
tio
n
ap
p
r
o
ac
h
,
ea
ch
t
o
k
en
i
n
th
e
test
s
et
—
co
m
p
r
is
in
g
2
0
%
o
f
o
u
r
co
r
p
u
s
—
is
ca
teg
o
r
ized
in
to
o
n
e
o
f
f
o
u
r
class
if
icatio
n
s
:
tr
u
e
p
o
s
itiv
e,
f
alse
p
o
s
itiv
e,
tr
u
e
n
e
g
ativ
e,
o
r
f
alse
n
e
g
ativ
e.
A
to
k
en
is
d
esig
n
ated
as
a
tr
u
e
p
o
s
itiv
e
wh
en
it is
b
o
th
p
r
ed
ic
ted
an
d
tag
g
ed
as a
k
e
y
wo
r
d
.
T
ab
le
4
p
r
esen
ts
th
e
weig
h
ted
av
er
ag
e
m
etr
ics
f
o
r
SKET
,
in
clu
d
in
g
Pre
cisi
o
n
,
R
ec
all,
an
d
F1
-
s
co
r
e.
Sin
ce
F1
-
s
co
r
e
ex
ce
ed
s
9
1
%
f
o
r
all
d
o
m
ai
n
s
,
th
is
m
etr
ics
ev
alu
atio
n
p
r
o
v
id
es
a
co
m
p
r
eh
en
s
iv
e
o
v
er
v
iew
o
f
th
e
SKET
's
ef
f
ec
ti
v
en
ess
in
a
cc
u
r
ately
id
en
tify
in
g
k
ey
wo
r
d
s
.
Ad
d
itio
n
ally
,
T
ab
le
4
in
clu
d
es
two
im
p
o
r
tan
t
tim
e
m
etr
ics:
Tb
,
wh
ich
in
d
i
ca
tes
th
e
tim
e
tak
en
t
o
b
u
ild
th
e
m
o
d
el
(
m
ea
s
u
r
e
d
in
h
o
u
r
s
)
,
an
d
Tp
,
w
h
ich
r
ep
r
esen
ts
th
e
tim
e
tak
en
t
o
p
r
ed
ict
a
to
k
en
(
m
ea
s
u
r
ed
i
n
m
il
lis
ec
o
n
d
s
)
.
T
ab
le
4
.
T
h
e
o
b
tain
e
d
m
etr
ics'
o
u
tco
m
es
D
o
ma
i
n
P
r
e
c
i
s
i
o
n
R
e
c
a
l
l
F
-
sco
r
e
Tb
(
h
r
)
Tp
(
ms)
A
r
t
s
0
.
9
4
5
0
.
9
4
1
0
.
9
3
8
1
.
6
1
7
.
0
6
6
Ec
o
n
o
my
0
.
9
3
0
0
.
9
2
0
0
.
9
1
8
1
.
7
7
7
.
0
4
2
P
o
l
i
t
i
c
s
0
.
9
5
1
0
.
9
4
8
0
.
9
4
6
1
.
7
6
7
.
0
9
1
S
p
o
r
t
0
.
9
8
4
0
.
9
8
3
0
.
9
8
3
1
.
6
5
7
.
0
0
6
3
.
3
.
Co
m
pa
ra
t
iv
e
a
na
ly
s
is
T
h
e
s
ec
o
n
d
ex
p
e
r
im
en
t
aim
e
d
to
ev
alu
ate
th
e
p
er
f
o
r
m
an
ce
o
f
SKET
th
r
o
u
g
h
a
c
o
m
p
a
r
ativ
e
an
aly
s
is
with
p
r
io
r
s
tu
d
ies.
R
ec
en
t
r
esear
ch
[
2
5
]
-
[
2
9
]
h
as
in
d
icate
d
th
at
tr
a
n
s
f
o
r
m
er
-
b
ased
m
o
d
els,
o
u
tp
er
f
o
r
m
tr
ad
itio
n
al
s
tatis
tical,
m
ac
h
in
e
lear
n
in
g
,
a
n
d
d
ee
p
lear
n
in
g
tech
n
iq
u
es
in
v
a
r
io
u
s
task
s
.
T
o
f
ac
ilit
ate
th
is
co
m
p
ar
is
o
n
,
we
d
o
wn
lo
ad
e
d
an
d
im
p
lem
en
te
d
th
e
L
lam
a
-
2
-
7
b
,
L
lam
a
-
2
-
1
3
b
,
L
lam
a
-
2
-
7
0
b
,
an
d
Mistra
l
-
7B
-
v
0
.
1
m
o
d
els.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
A
th
r
ee
-
p
h
a
s
e
mo
d
el
t
o
ke
ywo
r
d
d
etec
tio
n
in
A
r
a
b
ic
c
o
r
p
o
r
a
(
Dri
s
s
N
a
mly
)
211
Ho
wev
er
,
o
u
r
attem
p
ts
to
u
tili
ze
th
ese
L
L
Ms
f
o
r
k
ey
wo
r
d
id
en
tific
atio
n
f
r
o
m
t
h
e
co
r
p
u
s
en
co
u
n
ter
e
d
ch
allen
g
es
d
u
e
to
lim
itatio
n
s
in
th
eir
co
n
tex
t
s
ize
p
ar
am
eter
s
.
Sp
ec
if
ically
,
L
lam
a
-
2
m
o
d
els
ar
e
co
n
s
tr
ain
ed
to
a
co
n
tex
t
s
ize
o
f
4
,
0
0
0
to
k
en
s
,
wh
ile
th
e
Mistra
l
m
o
d
el
ca
n
h
an
d
le
u
p
to
8
,
0
0
0
to
k
en
s
.
T
h
is
co
n
tex
t
s
ize
d
ef
in
es
th
e
m
ax
i
m
u
m
n
u
m
b
er
o
f
to
k
en
s
th
at
ca
n
b
e
p
r
o
c
ess
ed
in
a
s
in
g
le
in
p
u
t,
in
clu
d
in
g
b
o
th
th
e
p
r
o
m
p
t
an
d
th
e
r
esp
o
n
s
e.
Giv
en
th
at
th
e
C
AKE
co
r
p
u
s
is
r
elativ
ely
lar
g
e,
th
is
lim
itatio
n
h
in
d
er
e
d
th
e
ef
f
ec
tiv
en
ess
o
f
th
e
L
L
Ms
in
o
u
r
c
o
m
p
a
r
ativ
e
s
tu
d
y
,
u
ltima
tely
m
ak
in
g
th
e
ev
al
u
atio
n
o
f
SKET
ag
ain
s
t
th
ese
mod
els less
r
elev
an
t.
Nev
er
th
eless
,
we
co
m
p
ar
e
SK
E
T
with
s
o
m
e
o
n
lin
e
L
L
Ms
u
s
in
g
th
r
ee
r
an
d
o
m
ly
s
elec
ted
d
o
cu
m
e
n
ts
f
r
o
m
C
AKE
co
n
tain
in
g
f
ewe
r
th
an
4
0
0
0
to
k
e
n
s
.
As
illu
s
tr
ated
in
T
ab
le
5
,
SKET
d
is
p
lay
s
r
o
b
u
s
t
p
r
ec
is
io
n
an
d
a
h
ig
h
F1
-
s
co
r
e,
p
o
s
itio
n
i
n
g
it
as
an
ex
ce
p
tio
n
al
m
o
d
el
in
ter
m
s
o
f
r
eliab
ilit
y
f
o
r
p
o
s
itiv
e
p
r
ed
ictio
n
s
.
On
th
e
o
th
er
h
an
d
,
m
o
d
els
lik
e
GPT
-
3
.
5
an
d
Mix
tr
al
o
f
f
e
r
a
m
o
r
e
b
alan
ce
d
p
er
f
o
r
m
a
n
ce
,
alb
eit
with
lo
wer
p
r
ec
is
io
n
an
d
F1
-
s
co
r
es.
T
ab
le
5
.
T
h
e
co
m
p
ar
is
o
n
r
esu
l
ts
M
o
d
e
l
P
r
e
c
i
s
i
o
n
R
e
c
a
l
l
F1
-
sc
o
r
e
G
P
T
-
3
.
5
0
.
6
4
8
1
0
.
2
7
3
4
0
.
3
8
4
6
G
e
mi
n
i
0
.
5
0
6
8
0
.
2
8
9
1
0
.
3
6
8
2
Ll
a
m
a
2
-
7
0
b
0
.
2
0
0
0
0
.
0
7
8
1
0
.
1
1
2
4
M
i
x
t
r
a
l
0
.
3
9
5
8
0
.
2
9
6
9
0
.
3
3
9
3
S
K
ET
0
.
8
8
8
9
0
.
7
5
0
0
0
.
8
1
5
6
3
.
4
.
Dis
cus
s
io
n
T
h
is
s
tu
d
y
in
v
esti
g
ated
th
e
c
r
itical
n
ee
d
f
o
r
e
f
f
icien
t
to
o
ls
ca
p
ab
le
o
f
s
wif
tly
,
a
u
to
m
ati
ca
lly
,
an
d
ac
cu
r
ately
id
en
tify
in
g
k
ey
wo
r
d
s
with
in
a
co
llectio
n
o
f
Ar
ab
ic
d
o
cu
m
en
ts
.
W
h
ile
ea
r
lier
s
tu
d
ies h
av
e
ex
p
lo
r
ed
au
to
m
atic
k
ey
w
o
r
d
id
en
tific
atio
n
,
th
ey
h
a
v
e
n
o
t
ad
d
r
ess
ed
th
e
s
in
g
le
d
o
c
u
m
en
t
lim
i
tatio
n
.
SK
E
T
,
th
e
p
r
o
p
o
s
ed
to
o
l,
co
n
s
is
ts
o
f
s
ev
e
r
al
co
m
p
o
n
en
ts
in
clu
d
in
g
p
r
ep
r
o
ce
s
s
in
g
s
tep
s
,
f
r
eq
u
en
cy
a
n
a
ly
s
is
,
v
ec
to
r
s
p
ac
e
m
o
d
elin
g
,
an
d
lo
g
is
tic
r
eg
r
ess
io
n
,
wh
ich
co
llectiv
ely
g
en
er
ate
th
r
ee
lis
t
s
o
f
k
ey
wo
r
d
ca
n
d
id
ates.
T
h
ese
lis
t
s
ar
e
s
u
b
s
eq
u
en
tly
i
n
teg
r
ated
t
o
f
o
r
m
th
e
f
in
al
co
m
p
ilatio
n
o
f
k
ey
wo
r
d
s
.
T
h
e
ev
alu
atio
n
r
esu
lts
f
o
r
k
e
y
wo
r
d
d
etec
tio
n
o
n
th
e
C
AKE
co
r
p
u
s
u
tili
zin
g
th
e
p
r
o
p
o
s
ed
SKET
to
o
l
in
d
icate
th
at
t
h
e
F1
-
s
co
r
e
c
o
n
s
is
ten
tly
ex
ce
ed
s
9
1
%
ac
r
o
s
s
all
d
o
m
ain
s
,
r
ea
ch
in
g
a
m
ax
im
u
m
o
f
9
8
.
3
%
with
in
th
e
s
p
o
r
t
s
d
o
m
ain
,
th
er
eb
y
u
n
d
er
s
co
r
in
g
th
e
s
ig
n
if
ican
t
ef
f
ec
tiv
en
ess
o
f
o
u
r
m
eth
o
d
o
lo
g
y
.
Ad
d
itio
n
ally
,
SKET
d
em
o
n
s
tr
ates
r
em
ar
k
ab
le
ef
f
icien
cy
,
wi
th
m
o
d
el
co
n
s
tr
u
ctio
n
tak
i
n
g
l
ess
th
an
1
.
7
7
h
o
u
r
s
an
d
to
k
en
p
r
e
d
ictio
n
o
cc
u
r
r
in
g
in
ap
p
r
o
x
im
ately
7
m
il
lis
ec
o
n
d
s
.
T
h
is
ass
ess
m
en
t
co
n
f
ir
m
s
b
o
th
th
e
ef
f
ec
tiv
en
ess
an
d
co
m
p
u
tatio
n
al
ef
f
icien
cy
o
f
SKET
.
C
o
m
p
ar
ativ
e
an
aly
s
is
with
ex
is
tin
g
L
L
Ms
r
ev
ea
ls
th
at
SKE
T
o
u
tp
er
f
o
r
m
s
th
ese
m
o
d
els
in
ter
m
s
o
f
Pre
cisi
o
n
an
d
F1
-
s
co
r
e.
W
h
ile
tr
an
s
f
o
r
m
er
-
b
ased
m
o
d
els
d
em
o
n
s
tr
ate
p
o
ten
tial
ac
r
o
s
s
v
ar
io
u
s
ap
p
licatio
n
s
,
th
eir
co
n
tex
t
s
ize
co
n
s
tr
ain
ts
p
r
esen
t
s
ig
n
if
ican
t
ch
allen
g
es
wh
en
ap
p
lied
to
lar
g
er
d
atas
ets.
T
h
is
co
n
s
tr
ain
t
h
ig
h
lig
h
ts
th
e
im
p
o
r
tan
ce
o
f
u
tili
zin
g
a
s
p
ec
ialized
to
o
l
s
u
ch
as
SKET
,
wh
ich
is
s
p
ec
if
i
ca
lly
d
esig
n
ed
f
o
r
ef
f
icien
t
k
e
y
wo
r
d
id
en
tific
ati
o
n
with
in
lar
g
e
Ar
ab
ic
tex
t
c
o
llectio
n
s
.
B
y
ad
d
r
ess
in
g
th
es
e
ch
allen
g
es,
SKET
p
r
o
v
id
es
a
m
o
r
e
r
eliab
le
s
o
lu
t
io
n
f
o
r
r
esear
ch
e
r
s
an
d
p
r
ac
tit
io
n
er
s
wo
r
k
in
g
o
n
k
ey
wo
r
d
d
etec
tio
n
with
lar
g
e
v
o
lu
m
es o
f
A
r
ab
ic
tex
t d
ata.
Ou
r
s
tu
d
y
d
em
o
n
s
tr
ates
th
e
ef
f
icac
y
o
f
SKET
f
o
r
k
e
y
wo
r
d
d
etec
tio
n
in
th
e
Ar
ab
ic
lan
g
u
a
g
e.
Fu
tu
r
e
s
tu
d
ies
m
ay
ex
p
lo
r
e
its
ap
p
l
icatio
n
in
v
ar
io
u
s
lin
g
u
is
tic
en
v
ir
o
n
m
en
ts
.
B
y
le
v
er
ag
in
g
th
e
f
o
u
n
d
atio
n
al
p
r
in
cip
les
o
f
o
u
r
m
o
d
el,
r
esear
ch
er
s
an
d
p
r
ac
titi
o
n
er
s
ca
n
ef
f
ec
tiv
ely
tailo
r
th
e
s
y
s
tem
t
o
m
ee
t
th
e
s
p
ec
if
ic
n
ee
d
s
o
f
d
i
f
f
er
en
t la
n
g
u
a
g
es,
e
n
h
an
cin
g
its
u
tili
ty
in
o
th
er
a
p
p
licatio
n
s
.
4.
CO
NCLU
SI
O
N
T
h
e
SKET
em
p
lo
y
s
a
s
y
s
tem
atic
ap
p
r
o
ac
h
to
k
ey
wo
r
d
ex
tr
ac
tio
n
th
r
o
u
g
h
d
is
tin
ct
p
h
ases
.
I
t
b
eg
in
s
with
a
p
r
ep
r
o
ce
s
s
in
g
s
tag
e
to
ef
f
ec
tiv
ely
ad
d
r
ess
lin
g
u
is
tic
ch
allen
g
es.
Fo
llo
win
g
th
is
,
t
h
e
f
r
e
q
u
en
c
y
-
b
ase
d
m
eth
o
d
id
en
tifie
s
p
o
ten
tial
k
ey
wo
r
d
s
b
ased
o
n
th
eir
o
cc
u
r
r
e
n
ce
with
in
th
e
co
r
p
u
s
,
u
s
in
g
T
F
as
a
g
u
id
in
g
m
etr
ic.
T
o
f
u
r
th
er
e
n
h
an
ce
k
e
y
wo
r
d
r
ele
v
an
ce
,
SKET
in
co
r
p
o
r
ates
a
v
ec
to
r
s
p
ac
e
a
p
p
r
o
ac
h
th
at
co
n
s
id
er
s
th
e
d
is
tr
ib
u
tio
n
o
f
to
k
e
n
s
ac
r
o
s
s
th
e
en
tire
co
r
p
u
s
,
th
e
r
eb
y
f
ilter
in
g
o
u
t
is
o
lated
ter
m
s
.
T
h
e
m
ac
h
in
e
lear
n
in
g
p
h
ase
in
tr
o
d
u
ce
s
a
class
if
icati
o
n
alg
o
r
ith
m
,
s
p
ec
if
ically
lo
g
is
tic
r
eg
r
ess
io
n
,
wh
ich
ca
p
tu
r
e
s
less
co
m
m
o
n
b
u
t
s
ig
n
if
ican
t
k
ey
wo
r
d
s
wh
ile
in
teg
r
atin
g
d
o
m
ain
-
s
p
ec
if
ic
k
n
o
wled
g
e
to
im
p
r
o
v
e
ac
cu
r
a
cy
.
Fin
ally
,
SKET
m
er
g
es
th
e
th
r
ee
k
e
y
wo
r
d
lis
ts
u
s
in
g
a
lo
g
ical
“
a
n
d
”
o
p
er
a
tio
n
.
T
h
e
ev
alu
atio
n
o
f
SKET
r
ev
ea
ls
its
r
o
b
u
s
t
p
er
f
o
r
m
an
ce
an
d
ef
f
icien
cy
i
n
k
ey
wo
r
d
d
etec
tio
n
with
in
t
h
e
C
AKE
co
r
p
u
s
.
W
ith
an
im
p
r
ess
iv
e
F1
-
s
co
r
e
co
n
s
is
ten
tly
ex
ce
ed
in
g
9
1
%,
an
d
p
ea
k
in
g
at
9
8
.
3
%
in
th
e
s
p
o
r
ts
d
o
m
ain
,
SKET
d
em
o
n
s
tr
ates
s
ig
n
if
ican
t
ef
f
ec
tiv
en
ess
in
ac
cu
r
ately
id
en
tify
in
g
k
e
y
wo
r
d
s
ac
r
o
s
s
v
ar
io
u
s
co
n
tex
ts
.
T
h
e
co
m
p
u
tatio
n
al
ef
f
icien
cy
o
f
th
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
5
0
2
-
4
7
52
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
,
Vo
l.
37
,
No
.
1
,
J
an
u
ar
y
20
25
:
206
-
2
1
3
212
to
o
l
is
f
u
r
th
er
u
n
d
e
r
s
co
r
ed
b
y
its
m
o
d
el
co
n
s
tr
u
ctio
n
tim
e
o
f
less
th
an
1
.
7
7
h
o
u
r
s
an
d
r
a
p
id
to
k
en
p
r
e
d
ictio
n
at
ap
p
r
o
x
im
ately
7
m
illi
s
ec
o
n
d
s
.
I
n
c
o
m
p
ar
ativ
e
an
aly
s
es,
SKET
o
u
tp
er
f
o
r
m
e
d
s
ev
er
al
tr
an
s
f
o
r
m
er
-
b
ased
m
o
d
els,
s
u
ch
as L
lam
a
-
2
an
d
Mistra
l,
p
ar
ticu
lar
ly
in
ter
m
s
o
f
p
r
ec
is
io
n
an
d
F1
-
s
co
r
e.
T
h
e
lim
itatio
n
s
f
ac
ed
b
y
tr
a
n
s
f
o
r
m
er
m
o
d
els,
p
ar
ticu
lar
ly
r
eg
ar
d
in
g
co
n
te
x
t
s
ize
co
n
s
tr
ain
ts
wi
th
lar
g
er
d
atasets
,
f
u
r
th
e
r
em
p
h
a
s
ize
th
e
n
ec
ess
ity
f
o
r
s
p
ec
ialized
to
o
ls
lik
e
SKET
.
I
ts
d
esig
n
s
p
ec
if
ically
ca
ter
s
to
th
e
ch
allen
g
es
o
f
p
r
o
ce
s
s
in
g
ex
ten
s
iv
e
Ar
ab
ic
tex
t
c
o
r
p
o
r
a,
m
a
k
in
g
it
a
v
alu
ab
le
ass
et
f
o
r
r
esear
ch
er
s
a
n
d
p
r
ac
titi
o
n
er
s
in
th
e
f
ield
.
M
o
r
eo
v
er
,
th
e
m
o
d
u
lar
n
atu
r
e
o
f
SKET
,
en
co
m
p
ass
in
g
p
r
ep
r
o
ce
s
s
in
g
,
f
r
eq
u
e
n
cy
an
aly
s
is
,
v
ec
to
r
s
p
ac
e
m
o
d
elin
g
,
a
n
d
m
ac
h
in
e
lear
n
in
g
tec
h
n
iq
u
es,
la
y
s
a
s
tr
o
n
g
f
o
u
n
d
atio
n
f
o
r
p
o
ten
tial
ad
ap
tatio
n
s
b
ey
o
n
d
Ar
ab
ic.
T
h
is
ad
ap
tab
ilit
y
o
p
en
s
av
en
u
es
f
o
r
e
x
ten
d
in
g
th
e
to
o
l'
s
ca
p
ab
ilit
ies
to
o
th
e
r
lan
g
u
ag
es,
th
e
r
eb
y
e
n
h
an
ci
n
g
its
ap
p
licab
ilit
y
in
d
iv
er
s
e
lin
g
u
is
tic
en
v
ir
o
n
m
e
n
ts
.
RE
F
E
R
E
NC
E
S
[
1
]
Ö
.
A
y
d
ı
n
,
F
.
B
.
S
a
k
a
l
l
ı
,
a
n
d
A
.
Ş
.
M
e
su
t
,
“
A
r
e
v
i
e
w
o
f
a
p
p
r
o
a
c
h
e
s
f
o
r
k
e
y
p
h
r
a
se
e
x
t
r
a
c
t
i
o
n
,
”
J
o
u
rn
a
l
F
u
n
d
a
m
e
n
t
a
l
S
c
i
e
n
c
e
s
a
n
d
Ap
p
l
i
c
a
t
i
o
n
s,
v
o
l
.
2
6
,
n
o
.
1
,
p
p
.
1
-
6
,
2
0
2
0
.
[
2
]
S
.
La
z
e
mi
,
H
.
E
b
r
a
h
i
m
p
o
u
r
-
K
o
ml
e
h
,
a
n
d
N
.
N
o
r
o
o
z
i
,
“
P
A
K
E
:
a
s
u
p
e
r
v
i
s
e
d
a
p
p
r
o
a
c
h
f
o
r
P
e
r
s
i
a
n
a
u
t
o
m
a
t
i
c
k
e
y
w
o
r
d
e
x
t
r
a
c
t
i
o
n
u
si
n
g
st
a
t
i
st
i
c
a
l
f
e
a
t
u
r
e
s
,
”
S
N
A
p
p
l
i
e
d
S
c
i
e
n
c
e
s
,
v
o
l
.
1
,
p
p
.
1
-
4
,
2
0
1
9
,
d
o
i
:
1
0
.
1
0
0
7
/
s
4
2
4
5
2
-
0
1
9
-
1
6
2
7
-
5.
[
3
]
M
.
M
.
A
.
H
a
d
i
d
i
,
M
.
A
l
z
g
h
o
o
l
,
a
n
d
H
.
M
u
a
i
d
i
,
“
K
e
y
w
o
r
d
e
x
t
r
a
c
t
i
o
n
f
r
o
m
a
r
a
b
i
c
t
e
x
t
u
s
i
n
g
t
h
e
p
a
g
e
r
a
n
k
a
l
g
o
r
i
t
h
m,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
I
n
n
o
v
a
t
i
v
e
T
e
c
h
n
o
l
o
g
y
a
n
d
Ex
p
l
o
r
i
n
g
En
g
i
n
e
e
ri
n
g
,
v
o
l
.
8
,
n
o
.
1
2
,
p
p
.
3
4
9
5
–
3
5
0
4
,
2
0
1
9
,
d
o
i
:
1
0
.
3
5
9
4
0
/
i
j
i
t
e
e
.
L2
6
1
4
.
1
0
8
1
2
1
9
.
[
4
]
P
.
S
h
a
r
ma
a
n
d
M
.
C
h
e
n
,
“
Te
x
t
s
u
m
mariz
a
t
i
o
n
a
n
d
k
e
y
w
o
r
d
e
x
t
r
a
c
t
i
o
n
,
”
i
n
2
0
2
3
1
4
t
h
I
I
AI
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
g
ress
o
n
Ad
v
a
n
c
e
d
Ap
p
l
i
e
d
I
n
f
o
rm
a
t
i
c
s (I
I
AI
-
AAI)
,
K
o
r
i
y
a
ma,
Ja
p
a
n
,
2
0
2
3
,
p
p
.
3
6
9
-
3
7
2
,
d
o
i
:
1
0
.
1
1
0
9
/
I
I
A
I
-
A
A
I
5
9
0
6
0
.
2
0
2
3
.
0
0
0
7
8
.
[
5
]
F
.
H
o
r
a
sa
n
,
“
K
e
y
w
o
r
d
e
x
t
r
a
c
t
i
o
n
f
o
r
sea
r
c
h
e
n
g
i
n
e
o
p
t
i
m
i
z
a
t
i
o
n
u
si
n
g
l
a
t
e
n
t
s
e
ma
n
t
i
c
a
n
a
l
y
si
s
,
”
P
o
l
i
t
e
k
n
i
k
D
e
r
g
i
s
i
,
v
o
l
.
2
4
,
n
o
.
2
,
p
p
.
4
7
3
-
4
7
9
,
2
0
2
1
,
d
o
i
:
1
0
.
2
3
3
9
/
p
o
l
i
t
e
k
n
i
k
.
6
8
4
3
7
7
.
[
6
]
Z.
Y
a
n
g
,
H
.
Y
u
,
J
.
Ta
n
g
,
a
n
d
H
.
Li
u
,
“
To
w
a
r
d
k
e
y
w
o
r
d
e
x
t
r
a
c
t
i
o
n
i
n
c
o
n
st
r
a
i
n
e
d
i
n
f
o
r
m
a
t
i
o
n
r
e
t
r
i
e
v
a
l
i
n
v
e
h
i
c
l
e
so
c
i
a
l
n
e
t
w
o
r
k
,
”
I
EEE
T
r
a
n
s
a
c
t
i
o
n
s
o
n
Ve
h
i
c
u
l
a
r Te
c
h
n
o
l
o
g
y
,
v
o
l
.
6
8
,
n
o
.
5
,
p
p
.
4
2
8
5
-
4
2
9
4
,
2
0
1
9
,
d
o
i
:
1
0
.
1
1
0
9
/
TV
T.
2
0
1
9
.
2
9
0
6
7
9
9
.
[
7
]
R
.
C
a
m
p
o
s
,
V
.
M
a
n
g
a
r
a
v
i
t
e
,
A
.
P
a
sq
u
a
l
i
,
A
.
J
o
r
g
e
,
C
.
N
u
n
e
s,
a
n
d
A
.
Ja
t
o
w
t
,
“
Y
A
K
E!
K
e
y
w
o
r
d
e
x
t
r
a
c
t
i
o
n
f
r
o
m si
n
g
l
e
d
o
c
u
m
e
n
t
s
u
si
n
g
m
u
l
t
i
p
l
e
l
o
c
a
l
f
e
a
t
u
r
e
s,
”
I
n
f
o
rm
a
t
i
o
n
S
c
i
e
n
c
e
s,
v
o
l
.
5
0
9
,
p
p
.
2
5
7
-
2
8
9
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
n
s.
2
0
1
9
.
0
9
.
0
1
3
.
[
8
]
W
.
A
.
E
t
a
i
w
i
,
A
.
A
.
A
w
a
j
a
n
,
a
n
d
D
.
S
u
l
e
i
ma
n
,
“
K
e
y
w
o
r
d
s e
x
t
r
a
c
t
i
o
n
f
r
o
m
A
r
a
b
i
c
d
o
c
u
me
n
t
s u
s
i
n
g
c
e
n
t
r
a
l
i
t
y
m
e
a
s
u
r
e
s,
”
i
n
2
0
1
9
S
i
x
t
h
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
S
o
c
i
a
l
N
e
t
w
o
r
k
s
An
a
l
y
si
s,
M
a
n
a
g
e
m
e
n
t
a
n
d
S
e
c
u
ri
t
y
(
S
N
A
MS
)
,
2
0
1
9
:
I
EEE,
p
p
.
2
3
7
-
2
4
1
,
d
o
i
:
1
0
.
1
1
0
9
/
S
N
A
M
S
.
2
0
1
9
.
8
9
3
1
8
0
8
.
[
9
]
Y
.
W
.
Y
u
a
n
d
H
.
G
.
K
i
m
,
“
I
n
t
e
r
a
c
t
i
v
e
mo
r
p
h
o
l
o
g
i
c
a
l
a
n
a
l
y
s
i
s
t
o
i
mp
r
o
v
e
a
c
c
u
r
a
c
y
o
f
k
e
y
w
o
r
d
e
x
t
r
a
c
t
i
o
n
b
a
sed
o
n
c
o
h
e
si
o
n
sco
r
i
n
g
,
”
J
o
u
rn
a
l
o
f
t
h
e
K
o
re
a
S
o
c
i
e
t
y
o
f
C
o
m
p
u
t
e
r
a
n
d
I
n
f
o
rm
a
t
i
o
n
,
v
o
l
.
2
5
,
n
o
.
1
2
,
p
p
.
1
4
5
-
1
5
3
,
2
0
2
0
,
d
o
i
:
1
0
.
9
7
0
8
/
J
K
S
C
I
.
2
0
2
0
.
2
5
.
1
2
.
1
4
5
.
[
1
0
]
X
.
Li
u
,
J
.
T
a
n
,
J.
F
a
n
,
K
.
Ta
n
,
J
.
H
u
,
a
n
d
S
.
D
o
n
g
,
“
A
S
y
n
t
a
x
-
e
n
h
a
n
c
e
d
m
o
d
e
l
b
a
se
d
o
n
c
a
t
e
g
o
r
y
k
e
y
w
o
r
d
s
f
o
r
b
i
o
me
d
i
c
a
l
r
e
l
a
t
i
o
n
e
x
t
r
a
c
t
i
o
n
,
”
J
o
u
r
n
a
l
o
f
Bi
o
m
e
d
i
c
a
l
I
n
f
o
rm
a
t
i
c
s,
v
o
l
.
1
3
2
,
p
.
1
0
4
1
3
5
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
b
i
.
2
0
2
2
.
1
0
4
1
3
5
.
[
1
1
]
B
.
A
r
mo
u
t
y
a
n
d
S
.
T
e
d
m
o
r
i
,
“
A
u
t
o
mat
e
d
k
e
y
w
o
r
d
e
x
t
r
a
c
t
i
o
n
u
s
i
n
g
su
p
p
o
r
t
v
e
c
t
o
r
mac
h
i
n
e
f
r
o
m
A
r
a
b
i
c
n
e
w
s
d
o
c
u
m
e
n
t
s,
”
i
n
2
0
1
9
I
EEE
J
o
r
d
a
n
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
i
n
t
C
o
n
f
e
re
n
c
e
o
n
E
l
e
c
t
ri
c
a
l
E
n
g
i
n
e
e
ri
n
g
a
n
d
I
n
f
o
rm
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
(
J
EEIT
)
,
2
0
1
9
,
d
o
i
:
1
0
.
1
1
0
9
/
JEEI
T.
2
0
1
9
.
8
7
1
7
4
2
0
.
[
1
2
]
H
.
H
a
sh
i
m,
E.
-
S
.
A
t
l
a
m,
A
.
R
.
A
l
z
i
g
h
a
i
b
i
,
a
n
d
M
.
A
l
m
a
l
i
k
i
,
“
A
n
i
m
p
l
e
men
t
a
t
i
o
n
me
t
h
o
d
f
o
r
A
r
a
b
i
c
k
e
y
w
o
r
d
t
e
n
d
e
n
c
y
u
si
n
g
d
e
c
i
si
o
n
t
r
e
e
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
C
o
m
p
u
t
e
r
A
p
p
l
i
c
a
t
i
o
n
s
i
n
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
6
3
,
n
o
.
1
-
2
,
p
p
.
5
5
-
6
3
,
2
0
2
0
,
d
o
i
:
1
0
.
1
5
0
4
/
I
JC
A
T.
2
0
2
0
.
1
0
7
9
1
1
.
[
1
3
]
N
.
A
.
A
b
d
u
l
l
a
h
a
n
d
N
.
T.
J
a
b
o
o
r
y
,
“
A
r
a
b
i
c
k
e
y
w
o
r
d
s
e
x
t
r
a
c
t
i
o
n
u
s
i
n
g
c
o
n
v
e
n
t
i
o
n
a
l
n
e
u
r
a
l
n
e
t
w
o
r
k
,
”
I
ra
q
i
J
o
u
r
n
a
l
o
f
S
c
i
e
n
c
e
,
p
p
.
2
8
3
-
2
9
3
,
2
0
2
2
,
d
o
i
:
1
0
.
2
4
9
9
6
/
i
j
s.
2
0
2
2
.
6
3
.
1
.
2
8
.
[
1
4
]
D
.
S
u
l
e
i
ma
n
,
A
.
A
.
A
w
a
j
a
n
,
a
n
d
W
.
A
.
Et
a
i
w
i
,
“
A
r
a
b
i
c
t
e
x
t
k
e
y
w
o
r
d
s
e
x
t
r
a
c
t
i
o
n
u
s
i
n
g
w
o
r
d
2
v
e
c
,
”
i
n
2
0
1
9
2
n
d
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
n
e
w
T
re
n
d
s
i
n
C
o
m
p
u
t
i
n
g
S
c
i
e
n
c
e
s (I
C
T
C
S
)
,
2
0
1
9
:
I
EEE,
p
p
.
1
-
7
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
TC
S
.
2
0
1
9
.
8
9
2
3
0
3
4
.
[
1
5
]
R
.
A
l
h
a
r
b
i
a
n
d
H
.
A
l
-
M
u
h
t
a
sa
b
,
“
A
r
a
b
i
c
k
e
y
p
h
r
a
se
e
x
t
r
a
c
t
i
o
n
:
e
n
h
a
n
c
i
n
g
d
e
e
p
l
e
a
r
n
i
n
g
mo
d
e
l
s
w
i
t
h
p
r
e
-
t
r
a
i
n
e
d
c
o
n
t
e
x
t
u
a
l
e
mb
e
d
d
i
n
g
a
n
d
e
x
t
e
r
n
a
l
f
e
a
t
u
r
e
s
,
”
i
n
Pro
c
e
e
d
i
n
g
s
o
f
t
h
e
T
h
e
S
e
v
e
n
t
h
Ar
a
b
i
c
N
a
t
u
r
a
l
L
a
n
g
u
a
g
e
Pr
o
c
e
ssi
n
g
W
o
r
k
sh
o
p
(
WA
N
L
P)
,
2
0
2
2
,
d
o
i
:
1
0
.
1
8
6
5
3
/
v
1
/
2
0
2
2
.
w
a
n
l
p
-
1
.
3
0
.
[
1
6
]
P
.
C
.
C
h
a
t
t
e
r
j
e
e
,
M
.
B
o
r
d
o
l
o
i
,
a
n
d
S
.
K
.
B
i
sw
a
s,
“
K
e
y
w
o
r
d
e
x
t
r
a
c
t
i
o
n
u
si
n
g
G
r
a
p
h
b
a
se
d
s
u
p
e
r
v
i
se
d
t
e
r
m
w
e
i
g
h
t
i
n
g
,
”
i
n
2
0
1
9
2
n
d
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
I
n
n
o
v
a
t
i
o
n
s
i
n
E
l
e
c
t
r
o
n
i
c
s
,
S
i
g
n
a
l
Pro
c
e
ssi
n
g
a
n
d
C
o
m
m
u
n
i
c
a
t
i
o
n
(
I
ES
C
)
,
2
0
1
9
,
d
o
i
:
1
0
.
1
1
0
9
/
I
ESP
C
.
2
0
1
9
.
8
9
0
2
4
3
1
.
[
1
7
]
S
.
D
u
a
r
i
a
n
d
V
.
B
h
a
t
n
a
g
a
r
,
“
s
C
A
K
E
:
sem
a
n
t
i
c
c
o
n
n
e
c
t
i
v
i
t
y
a
w
a
r
e
k
e
y
w
o
r
d
e
x
t
r
a
c
t
i
o
n
,
”
I
n
f
o
rm
a
t
i
o
n
S
c
i
e
n
c
e
s
,
v
o
l
.
4
7
7
,
p
p
.
1
0
0
-
1
1
7
,
2
0
1
9
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
n
s
.
2
0
1
8
.
1
0
.
0
3
4
.
[
1
8
]
N
.
Zh
o
u
,
W
.
S
h
i
,
R
.
L
i
a
n
g
,
a
n
d
N
.
Z
h
o
n
g
,
“
Te
x
t
r
a
n
k
k
e
y
w
o
r
d
e
x
t
r
a
c
t
i
o
n
a
l
g
o
r
i
t
h
m
u
si
n
g
w
o
r
d
v
e
c
t
o
r
c
l
u
st
e
r
i
n
g
b
a
se
d
o
n
r
o
u
g
h
d
a
t
a
-
d
e
d
u
c
t
i
o
n
,
”
C
o
m
p
u
t
a
t
i
o
n
a
l
I
n
t
e
l
l
i
g
e
n
c
e
a
n
d
N
e
u
r
o
sc
i
e
n
c
e
,
v
o
l
.
2
0
2
2
,
2
0
2
2
,
d
o
i
:
1
0
.
1
1
5
5
/
2
0
2
2
/
5
6
4
9
9
9
4
.
[
1
9
]
X
.
M
a
o
,
S
.
H
u
a
n
g
,
R
.
Li
,
a
n
d
L
.
S
h
e
n
,
“
A
u
t
o
ma
t
i
c
k
e
y
w
o
r
d
s
e
x
t
r
a
c
t
i
o
n
b
a
s
e
d
o
n
c
o
-
o
c
c
u
r
r
e
n
c
e
a
n
d
sem
a
n
t
i
c
r
e
l
a
t
i
o
n
s
h
i
p
s
b
e
t
w
e
e
n
w
o
r
d
s
,
”
I
e
e
e
Ac
c
e
ss
,
v
o
l
.
8
,
p
p
.
1
1
7
5
2
8
-
1
1
7
5
3
8
,
2
0
2
0
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
0
.
3
0
0
4
6
2
8
.
[
2
0
]
W
.
X
.
Zh
a
o
e
t
a
l
.
,
“
A
s
u
r
v
e
y
o
f
l
a
r
g
e
l
a
n
g
u
a
g
e
m
o
d
e
l
s,
”
a
rXi
v
p
r
e
p
r
i
n
t
a
rXi
v
:
2
3
0
3
.
1
8
2
2
3
,
2
0
2
3
,
d
o
i
:
1
0
.
4
8
5
5
0
/
a
r
X
i
v
.
2
3
0
3
.
1
8
2
2
3
.
[
2
1
]
K
.
S
h
a
a
l
a
n
,
S
.
S
i
d
d
i
q
u
i
,
M
.
A
l
k
h
a
t
i
b
,
a
n
d
A
.
A
.
M
o
n
e
m
,
“
C
h
a
l
l
e
n
g
e
s
i
n
A
r
a
b
i
c
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
,
”
i
n
C
o
m
p
u
t
a
t
i
o
n
a
l
L
i
n
g
u
i
s
t
i
c
s
,
S
p
e
e
c
h
a
n
d
I
m
a
g
e
P
r
o
c
e
s
s
i
n
g
f
o
r
A
r
a
b
i
c
L
a
n
g
u
a
g
e
:
W
o
r
l
d
S
c
i
e
n
t
i
f
i
c
,
2
0
1
9
,
p
p
.
5
9
-
8
3
,
d
o
i
:
1
0
.
1
1
4
2
/
9
7
8
9
8
1
3
2
2
9
3
9
6
_
0
0
0
3
.
[
2
2
]
J.
R
o
ss
i
a
n
d
E.
K
a
n
o
u
l
a
s
,
“
Q
u
e
r
y
g
e
n
e
r
a
t
i
o
n
f
o
r
p
a
t
e
n
t
r
e
t
r
i
e
v
a
l
w
i
t
h
k
e
y
w
o
r
d
e
x
t
r
a
c
t
i
o
n
b
a
se
d
o
n
s
y
n
t
a
c
t
i
c
f
e
a
t
u
r
e
s,
”
Fr
o
n
t
i
e
rs
i
n
Art
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
a
n
d
A
p
p
l
i
c
a
t
i
o
n
s
,
p
.
2
1
0
,
2
0
1
8
,
d
o
i
:
1
0
.
3
2
3
3
/
9
7
8
-
1
-
6
1
4
9
9
-
9
3
5
-
5
-
2
1
0
.
[
2
3
]
K
.
B
o
u
z
o
u
b
a
a
e
t
a
l
.
,
“
A
d
e
scr
i
p
t
i
o
n
a
n
d
d
e
m
o
n
s
t
r
a
t
i
o
n
o
f
S
A
F
A
R
f
r
a
m
e
w
o
r
k
,
”
i
n
Pr
o
c
e
e
d
i
n
g
s
o
f
t
h
e
1
6
t
h
C
o
n
f
e
r
e
n
c
e
o
f
t
h
e
Eu
r
o
p
e
a
n
C
h
a
p
t
e
r
o
f
t
h
e
Asso
c
i
a
t
i
o
n
f
o
r
C
o
m
p
u
t
a
t
i
o
n
a
l
L
i
n
g
u
i
s
t
i
c
s:
S
y
st
e
m
D
e
m
o
n
s
t
r
a
t
i
o
n
s
,
2
0
2
1
,
p
p
.
1
2
7
-
1
3
4
,
d
o
i
:
1
0
.
1
8
6
5
3
/
v
1
/
2
0
2
1
.
e
a
c
l
-
d
e
m
o
s.
1
6
.
[2
4]
D
.
N
a
ml
y
,
K
.
B
o
u
z
o
u
b
a
a
,
A
.
E.
Ji
h
a
d
,
a
n
d
S
.
L
.
A
o
u
r
a
g
h
,
“
I
mp
r
o
v
i
n
g
A
r
a
b
i
c
l
e
mm
a
t
i
z
a
t
i
o
n
t
h
r
o
u
g
h
a
l
e
mm
a
s
d
a
t
a
b
a
se
a
n
d
a
mac
h
i
n
e
-
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
,
”
Re
c
e
n
t
Ad
v
a
n
c
e
s i
n
N
L
P:
T
h
e
C
a
s
e
o
f
Ara
b
i
c
L
a
n
g
u
a
g
e
,
p
p
.
8
1
-
1
0
0
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
3
-
0
3
0
-
3
4
6
1
4
-
0
_
5
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
d
o
n
esian
J
E
lec
E
n
g
&
C
o
m
p
Sci
I
SS
N:
2
5
0
2
-
4
7
52
A
th
r
ee
-
p
h
a
s
e
mo
d
el
t
o
ke
ywo
r
d
d
etec
tio
n
in
A
r
a
b
ic
c
o
r
p
o
r
a
(
Dri
s
s
N
a
mly
)
213
[
2
5
]
E.
C
.
G
a
r
r
i
d
o
-
M
e
r
c
h
a
n
,
R
.
G
o
z
a
l
o
-
B
r
i
z
u
e
l
a
,
a
n
d
S
.
G
o
n
z
a
l
e
z
-
C
a
r
v
a
j
a
l
,
“
C
o
m
p
a
r
i
n
g
B
E
R
T
a
g
a
i
n
st
t
r
a
d
i
t
i
o
n
a
l
mac
h
i
n
e
l
e
a
r
n
i
n
g
mo
d
e
l
s
i
n
t
e
x
t
c
l
a
ssi
f
i
c
a
t
i
o
n
,
”
J
o
u
r
n
a
l
o
f
C
o
m
p
u
t
a
t
i
o
n
a
l
a
n
d
C
o
g
n
i
t
i
v
e
En
g
i
n
e
e
ri
n
g
,
v
o
l
.
2
,
n
o
.
4
,
p
p
.
3
5
2
-
3
5
6
,
2
0
2
3
,
d
o
i
:
1
0
.
4
7
8
5
2
/
b
o
n
v
i
e
w
JC
C
E
3
2
0
2
8
3
8
.
[
2
6
]
N
.
N
a
v
é
r
,
“
T
h
e
p
a
st
,
p
r
e
se
n
t
o
r
f
u
t
u
r
e
?
:
A
c
o
m
p
a
r
a
t
i
v
e
N
LP
s
t
u
d
y
o
f
N
a
i
v
e
B
a
y
e
s,
LSTM
a
n
d
B
ER
T
f
o
r
c
l
a
s
si
f
y
i
n
g
S
w
e
d
i
sh
sen
t
e
n
c
e
s
b
a
se
d
o
n
t
h
e
i
r
t
e
n
se
,
”
2
0
2
1
.
[
2
7
]
Z.
A
.
G
u
v
e
n
,
“
C
o
mp
a
r
i
s
o
n
o
f
B
E
R
T
m
o
d
e
l
s
a
n
d
mac
h
i
n
e
l
e
a
r
n
i
n
g
me
t
h
o
d
s
f
o
r
se
n
t
i
me
n
t
a
n
a
l
y
si
s
o
n
Tu
r
k
i
s
h
t
w
e
e
t
s,
”
i
n
2
0
2
1
6
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
E
n
g
i
n
e
e
ri
n
g
(
U
B
MK
)
,
2
0
2
1
:
I
EEE,
p
p
.
9
8
-
1
0
1
,
d
o
i
:
10
.
1
1
0
9
/
U
B
M
K
5
2
7
0
8
.
2
0
2
1
.
9
5
5
9
0
1
4
.
[
2
8
]
K
.
D
h
o
l
a
a
n
d
M
.
S
a
r
a
d
v
a
,
“
A
c
o
m
p
a
r
a
t
i
v
e
e
v
a
l
u
a
t
i
o
n
o
f
t
r
a
d
i
t
i
o
n
a
l
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
a
n
d
d
e
e
p
l
e
a
r
n
i
n
g
c
l
a
ss
i
f
i
c
a
t
i
o
n
t
e
c
h
n
i
q
u
e
s
f
o
r
se
n
t
i
me
n
t
a
n
a
l
y
s
i
s,
”
i
n
2
0
2
1
1
1
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
O
n
C
l
o
u
d
C
o
m
p
u
t
i
n
g
,
D
a
t
a
S
c
i
e
n
c
e
a
n
d
En
g
i
n
e
e
ri
n
g
(
C
o
n
f
l
u
e
n
c
e
)
,
2
0
2
1
:
I
EEE,
p
p
.
9
3
2
-
9
3
6
,
d
o
i
:
1
0
.
1
1
0
9
/
C
o
n
f
l
u
e
n
c
e
5
1
6
4
8
.
2
0
2
1
.
9
3
7
7
0
7
0
.
[
2
9
]
G
.
B
o
u
r
a
h
o
u
a
t
,
M
.
A
b
o
u
r
e
z
q
,
a
n
d
N
.
D
a
o
u
d
i
,
“
L
e
v
e
r
a
g
i
n
g
m
o
r
o
c
c
a
n
a
r
a
b
i
c
s
e
n
t
i
m
e
n
t
a
n
a
l
y
si
s
u
si
n
g
a
r
a
b
e
r
t
a
n
d
q
a
r
i
b
,
”
i
n
T
h
e
Pro
c
e
e
d
i
n
g
s
o
f
t
h
e
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
S
m
a
r
t
C
i
t
y
A
p
p
l
i
c
a
t
i
o
n
s
,
2
0
2
2
:
S
p
r
i
n
g
e
r
,
p
p
.
2
9
9
-
3
1
0
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
3
-
0
3
1
-
2
6
8
5
2
-
6
_
2
9
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Dr
iss
Na
m
ly
is
As
sista
n
t
P
ro
fe
ss
o
r
o
f
Co
m
p
u
ter
S
c
ien
c
e
a
t
M
o
h
a
m
m
e
d
V
Un
iv
e
rsity
in
Ra
b
a
t,
M
o
ro
c
c
o
.
P
ro
f
NA
M
LY
re
c
e
iv
e
d
h
is
P
h
D
d
e
g
re
e
in
C
o
m
p
u
ter
S
c
ien
c
e
fro
m
M
o
h
a
m
m
e
d
V
Un
i
v
e
rsity
i
n
2
0
2
0
.
His
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
a
rti
ficia
l
i
n
telli
g
e
n
c
e
,
e
sp
e
c
ially
n
a
tu
ra
l
la
n
g
u
a
g
e
p
r
o
c
e
ss
in
g
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
d
.
n
a
m
ly
@u
m
5
r.
a
c
.
m
a
.
K
a
r
im
Bo
u
z
o
u
b
a
a
is
a
F
u
ll
P
ro
fe
ss
o
r
o
f
c
o
m
p
u
ter
sc
ien
c
e
in
th
e
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter
S
c
ien
c
e
,
M
o
h
a
m
m
a
d
ia
S
c
h
o
o
l
o
f
E
n
g
i
n
e
e
rs,
M
o
h
a
m
m
e
d
V
Un
i
v
e
rsity
i
n
Ra
b
a
t
.
P
ro
f/Dr.
Ka
rim
Bo
u
z
o
u
b
a
a
re
c
e
iv
e
d
h
is
P
h
D
d
e
g
re
e
in
1
9
9
8
f
ro
m
Lav
a
l
Un
i
v
e
rsity
.
His
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
a
rti
ficia
l
in
telli
g
e
n
c
e
,
d
a
ta
sc
ien
c
e
,
n
a
tu
r
a
l
lan
g
u
a
g
e
p
r
o
c
e
ss
in
g
a
n
d
c
o
m
p
u
tati
o
n
a
l
li
n
g
u
isti
c
s
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
k
a
rim.b
o
u
z
o
u
b
a
a
@e
m
i.
a
c
.
m
a
.
Rid
o
u
a
n
e
T
a
c
h
ica
r
t
P
ro
f.
Tac
h
ica
rt
Rid
o
u
a
n
e
h
a
s b
e
e
n
a
n
As
si
sta
n
t
P
r
o
fe
ss
o
r
o
f
Co
m
p
u
ter
S
c
ie
n
c
e
a
t
Ch
o
u
a
ib
D
o
u
k
k
a
li
Un
iv
e
rsit
y
sin
c
e
No
v
e
m
b
e
r
2
0
2
1
,
wh
e
re
h
e
tea
c
h
e
s
b
o
t
h
Ba
c
h
e
l
o
r'
s
a
n
d
M
a
ste
r'
s
p
ro
g
ra
m
s.
He
c
o
o
r
d
in
a
tes
c
o
u
rs
e
m
a
teria
ls,
sy
ll
a
b
u
s,
a
n
d
c
u
rricu
lu
m
wit
h
th
e
d
e
p
a
rtme
n
t
c
h
a
ir,
a
n
d
c
re
a
tes
les
so
n
p
lan
s
t
h
a
t
a
li
g
n
wi
th
e
sta
b
li
s
h
e
d
c
u
rricu
lu
m
a
n
d
u
n
iv
e
rsity
p
o
li
c
ie
s.
P
ro
f
.
Ri
d
o
u
a
n
e
e
v
a
lu
a
tes
st
u
d
e
n
ts
t
h
ro
u
g
h
writt
e
n
a
n
d
o
ra
l
e
x
a
m
in
a
ti
o
n
m
e
th
o
d
s.
He
e
a
rn
e
d
h
is
P
h
D
in
C
o
m
p
u
ter
S
c
ien
c
e
fro
m
M
o
h
a
m
m
e
d
V
Un
iv
e
rsity
in
Ra
b
a
t
in
2
0
2
1
.
His
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
n
a
tu
ra
l
lan
g
u
a
g
e
p
r
o
c
e
ss
in
g
,
m
a
c
h
in
e
tran
sla
ti
o
n
,
m
o
r
p
h
o
lo
g
ica
l
a
n
a
ly
sis,
tex
t
p
re
p
ro
c
e
ss
in
g
,
a
n
d
lan
g
u
a
g
e
re
so
u
rc
e
s
d
e
sig
n
a
n
d
b
u
il
d
i
n
g
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
tac
h
ica
rt.
r@u
c
d
.
a
c
.
m
a
.
Evaluation Warning : The document was created with Spire.PDF for Python.