I
nte
rna
t
io
na
l J
o
urna
l o
f
E
lect
rica
l a
nd
Co
m
pu
t
er
E
ng
ineering
(
I
J
E
CE
)
Vo
l.
14
,
No
.
6
,
Dec
em
b
er
20
24
,
p
p
.
7
0
3
6
~
7
0
4
5
I
SS
N:
2088
-
8
7
0
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijece.
v
14
i
6
.
pp
7
0
3
6
-
7
0
4
5
7036
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ec
e.
ia
esco
r
e.
co
m
H
o
mo
ny
m a
nd po
ly
sem
y
appro
a
ches with
mo
rpho
lo
g
y
ex
trac
tion in
weig
hting te
rms
f
o
r I
n
do
nesia
n t
o
Eng
li
sh ma
chine
trans
la
tion
B
ud
i H
a
rj
o
1
,
M
uljo
no
1
,
Ra
chm
a
d Abdu
lla
h
2,
3
1
F
a
c
u
l
t
y
o
f
C
o
mp
u
t
e
r
S
c
i
e
n
c
e
,
D
i
a
n
N
u
sw
a
n
t
o
r
o
U
n
i
v
e
r
s
i
t
y
,
S
e
m
a
r
a
n
g
,
I
n
d
o
n
e
s
i
a
2
D
e
p
a
r
t
me
n
t
o
f
I
n
f
o
r
mat
i
c
s
,
I
n
st
i
t
u
t
T
e
k
n
o
l
o
g
i
S
e
p
u
l
u
h
N
o
p
e
mb
e
r
,
S
u
r
a
b
a
y
a
,
I
n
d
o
n
e
si
a
3
D
e
p
a
r
m
e
n
t
o
f
M
a
n
a
g
e
me
n
t
,
S
e
k
o
l
a
h
Ti
n
g
g
i
I
l
mu
E
k
o
n
o
m
i
I
n
d
o
n
e
si
a
,
S
u
r
a
b
a
y
a
,
I
n
d
o
n
e
si
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Ma
y
6
,
2
0
2
4
R
ev
is
ed
J
u
l 1
2
,
2
0
2
4
Acc
ep
ted
Au
g
6
,
2
0
2
4
Ho
m
o
n
y
m
a
n
d
p
o
ly
se
m
y
fe
a
tu
re
s
c
a
n
in
fl
u
e
n
c
e
so
m
e
e
rro
rs
in
t
ra
n
sla
ti
o
n
fro
m
a
so
u
rc
e
lan
g
u
a
g
e
t
o
a
n
o
th
e
r
targ
e
t
lan
g
u
a
g
e
,
fo
r
e
x
a
m
p
le,
fro
m
In
d
o
n
e
sia
n
to
En
g
li
s
h
.
A
lem
m
a
o
r
a
m
o
rp
h
o
l
o
g
y
fa
c
to
r
c
a
n
c
a
u
se
th
e
c
o
n
fig
u
ra
ti
o
n
o
f
I
n
d
o
n
e
sia
n
h
o
m
o
n
y
m
fe
a
tu
re
s.
F
o
r
e
x
a
m
p
le,
th
e
wo
rd
b
e
ru
a
n
g
c
a
n
m
e
a
n
a
n
a
n
ima
l
b
e
ru
a
n
g
(b
e
a
r)
a
n
d
c
a
n
m
e
a
n
a
v
e
rb
a
lt
e
rn
a
ti
o
n
b
e
r+u
a
n
g
(h
a
s/h
a
v
e
m
o
n
e
y
)
.
T
h
e
In
d
o
n
e
sia
n
p
o
ly
se
m
y
fe
a
tu
re
c
a
n
a
lso
imp
a
c
t
a
n
e
rro
r
in
th
e
tran
sla
ti
o
n
p
r
o
c
e
ss
b
e
c
a
u
se
it
c
a
n
h
a
v
e
a
li
tera
l
m
e
a
n
in
g
a
n
d
a
sy
m
b
o
li
c
m
e
a
n
in
g
.
F
o
r
e
x
a
m
p
le,
t
h
e
term
s
b
u
n
g
a
me
la
ti
(jas
m
in
e
flo
we
r)
a
n
d
b
u
n
g
a
h
a
ti
(lo
v
e
r),
w
h
e
re
b
u
n
g
a
d
o
e
s
n
o
t
o
n
l
y
m
e
a
n
flo
we
r.
T
h
e
re
fo
re
,
t
h
e
d
e
v
e
lo
p
m
e
n
t
m
a
c
h
in
e
tran
sl
a
ti
o
n
(M
T)
m
e
th
o
d
n
e
e
d
s
to
c
a
p
tu
re
h
o
m
o
n
y
m
a
n
d
p
o
ly
s
e
m
y
fe
a
tu
re
s
in
th
e
fo
rm
o
f
a
wo
rd
o
r
a
p
h
ra
se
.
T
h
is
re
se
a
rc
h
p
r
o
p
o
se
s
h
o
m
o
n
y
m
a
n
d
p
o
l
y
se
m
y
a
p
p
ro
a
c
h
e
s
with
m
o
rp
h
o
lo
g
y
e
x
trac
ti
o
n
i
n
we
ig
h
ti
n
g
term
s
fo
r
In
d
o
n
e
sia
n
to
E
n
g
li
sh
M
T
.
F
irst,
th
is
re
se
a
rc
h
u
se
s
m
o
rp
h
o
lo
g
y
e
x
trac
ti
o
n
to
d
e
tec
t
se
n
ten
c
e
s
th
a
t
c
o
n
tain
p
re
fix
e
s,
lem
m
a
,
a
n
d
su
ffix
e
s.
T
h
e
n
,
t
h
e
wo
rd
sim
il
a
rit
y
m
e
a
su
re
m
e
n
t
fu
n
c
ti
o
n
s
to
e
x
trac
t
h
o
m
o
n
y
m
a
n
d
p
o
l
y
se
m
y
in
th
e
fo
rm
o
f
uni
-
g
ra
m
a
n
d
b
i
-
g
ra
m
u
sin
g
b
i
d
irec
ti
o
n
a
l
e
n
c
o
d
e
r
re
p
re
se
n
tati
o
n
s
fro
m
tran
sfo
rm
e
rs
(BERT
)
e
m
b
e
d
d
i
n
g
,
n
ame
d
e
n
ti
ty
re
c
o
g
n
i
ti
o
n
(NER)
,
sy
n
o
n
y
m
-
b
a
se
d
term
e
x
p
a
n
sio
n
,
a
n
d
se
m
a
n
ti
c
sim
il
a
rit
y
.
T
h
is
re
se
a
rc
h
u
se
s
n
e
u
ra
l
m
a
c
h
in
e
tran
sla
ti
o
n
fo
r
th
e
tran
sla
ti
o
n
p
r
o
c
e
ss
.
K
ey
w
o
r
d
s
:
B
id
ir
ec
tio
n
al
en
co
d
er
r
ep
r
esen
tatio
n
s
f
r
o
m
tr
an
s
f
o
r
m
er
s
em
b
ed
d
in
g
Mo
r
p
h
o
l
o
g
y
e
x
tr
ac
tio
n
Neu
r
al
m
ac
h
in
e
tr
a
n
s
latio
n
Sem
an
tic
s
im
ilar
ity
Sy
n
o
n
y
m
-
b
ased
ter
m
ex
p
a
n
s
io
n
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
:
Mu
ljo
n
o
Facu
lty
o
f
C
o
m
p
u
ter
Scien
ce
,
Dian
Nu
s
wan
to
r
o
Un
iv
e
r
s
ity
2
0
7
I
m
am
B
o
n
jo
l Ro
ad
,
Sem
ar
an
g
,
C
en
tr
al
J
av
a
5
0
1
3
1
,
I
n
d
o
n
esia
E
m
ail: m
u
ljo
n
o
@
d
s
n
.
d
in
u
s
.
ac
.
id
1.
I
NT
RO
D
UCT
I
O
N
T
h
e
m
ac
h
i
n
e
tr
a
n
s
latio
n
(
MT
)
d
ev
el
o
p
m
en
ts
[
1
]
,
[
2
]
in
te
n
d
to
s
o
lv
e
s
en
ten
ce
tr
an
s
latio
n
p
r
o
b
lem
s
f
r
o
m
s
o
u
r
ce
to
tar
g
et
la
n
g
u
a
g
e
.
Ho
m
o
n
y
m
s
an
d
p
o
ly
s
em
y
ar
e
wo
r
d
f
ea
tu
r
es
th
at
ca
n
in
f
lu
e
n
ce
s
o
m
e
er
r
o
r
s
in
tr
an
s
latio
n
f
r
o
m
a
s
o
u
r
ce
lan
g
u
ag
e
t
o
an
o
th
er
ta
r
g
et
lan
g
u
ag
e,
f
o
r
e
x
am
p
le,
f
r
o
m
I
n
d
o
n
esian
to
E
n
g
lis
h
.
A
lem
m
a
with
m
u
ltip
le
m
ea
n
in
g
s
ca
n
ca
u
s
e
th
e
co
n
f
ig
u
r
atio
n
o
f
th
e
I
n
d
o
n
esian
h
o
m
o
n
y
m
f
ea
tu
r
e.
Fo
r
in
s
tan
ce
,
p
a
lu
ca
n
m
ea
n
a
city
n
am
e
P
a
lu
(
Palu
)
an
d
a
to
o
l
p
a
lu
(
h
am
m
er
)
.
T
h
e
h
y
b
r
i
d
MT
m
eth
o
d
d
e
v
el
o
p
m
en
t
u
s
in
g
s
tatis
tical
MT
a
n
d
r
u
le
-
b
ased
MT
[
3
]
d
is
cu
s
s
es
h
o
w
to
s
o
lv
e
tr
an
s
latio
n
task
s
f
r
o
m
I
n
d
o
n
esian
to
E
n
g
lis
h
s
en
ten
c
es
b
u
t
n
o
t
h
o
w
to
tr
an
s
late
th
e
h
o
m
o
n
y
m
f
ea
tu
r
e.
Neu
r
al
m
ac
h
i
n
e
tr
a
n
s
latio
n
(
NM
T
)
[
4
]
,
[
5
]
h
as
ac
h
iev
ed
a
s
ig
n
if
ican
t
b
r
ea
k
th
r
o
u
g
h
in
tr
an
s
latio
n
p
er
f
o
r
m
an
ce
.
B
u
t
h
o
w
to
s
o
lv
e
th
e
s
en
ten
ce
tr
a
n
s
latio
n
th
at
co
n
tain
s
th
e
I
n
d
o
n
esian
h
o
m
o
n
y
m
f
ea
t
u
r
e
is
s
till
n
o
t d
is
cu
s
s
ed
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
Ho
mo
n
ym
a
n
d
p
o
lysemy
a
p
p
r
o
a
ch
es w
ith
mo
r
p
h
o
lo
g
y
ex
tr
a
ctio
n
in
…
(
B
u
d
i H
a
r
jo
)
7037
A
web
-
b
ased
tr
a
n
s
latio
n
en
g
in
e,
e.
g
.
,
[
6
]
–
[
8
]
,
ca
n
f
in
d
v
o
ca
b
u
lar
y
item
s
an
d
en
h
an
ce
th
e
c
o
m
p
letio
n
o
f
I
n
d
o
n
esian
-
E
n
g
lis
h
tr
an
s
latin
g
b
u
t
is
n
o
t
ac
c
u
r
ate
en
o
u
g
h
f
o
r
tr
an
s
latin
g
h
o
m
o
n
y
m
f
ea
t
u
r
es.
Fo
r
ex
am
p
le,
Go
o
g
le
T
r
a
n
s
lato
r
s
till
tr
an
s
lates
th
e
s
en
ten
ce
A
ya
h
p
erg
i
k
e
P
a
lu
(
Fath
e
r
g
o
es
to
Palu
)
i
n
to
F
a
th
er
w
en
t
to
th
e
h
a
mme
r
,
wh
er
e
P
a
lu
s
till
t
r
an
s
lates a
s
th
e
h
am
m
er
an
d
h
as b
ee
n
u
n
ab
le
to
tr
an
s
late
P
a
lu
as a
city
n
am
e
o
f
P
a
lu
.
T
h
is
tr
an
s
latio
n
e
r
r
o
r
o
c
cu
r
s
b
ec
au
s
e
th
e
MT
m
et
h
o
d
c
an
n
o
t c
ap
t
u
r
e
th
e
wo
r
d
'
s
co
n
tex
t in
th
e
s
en
ten
ce
.
Mo
r
p
h
o
l
o
g
ical
f
ac
to
r
s
ca
n
also
ca
u
s
e
th
e
h
o
m
o
n
y
m
f
ea
tu
r
e
in
I
n
d
o
n
esian
.
Fo
r
ex
am
p
le,
b
eru
a
n
g
h
as
m
u
ltip
le
m
ea
n
in
g
s
:
an
a
n
im
al
n
am
e
b
eru
a
n
g
(
b
ea
r
)
an
d
a
v
e
r
b
with
b
er
+
u
a
n
g
(
h
as/h
av
e
m
o
n
ey
)
.
Ap
ar
t
f
r
o
m
th
e
h
o
m
o
n
y
m
f
ac
to
r
,
th
e
I
n
d
o
n
esian
p
o
ly
s
em
y
f
ac
to
r
ca
n
also
ca
u
s
e
er
r
o
r
s
in
tr
an
s
lati
n
g
s
en
ten
ce
s
f
r
o
m
I
n
d
o
n
esian
to
E
n
g
lis
h
.
I
n
d
o
n
e
s
ian
p
o
ly
s
em
y
p
h
r
ases
m
ay
h
av
e
a
liter
al
m
ea
n
in
g
b
u
t c
an
also
h
av
e
a
s
y
m
b
o
lic
m
ea
n
in
g
.
Fo
r
ex
am
p
le,
b
u
n
g
a
h
as th
e
p
h
r
ase
b
u
n
g
a
mela
ti
(
j
asm
in
e
f
lo
wer
)
an
d
b
u
n
g
a
h
a
ti
(
lo
v
er
)
.
Ma
n
y
MT
m
eth
o
d
d
e
v
elo
p
m
en
t
f
o
r
th
e
I
n
d
o
n
esian
la
n
g
u
ag
e
s
till
f
o
c
u
s
o
n
s
p
o
k
e
n
lan
g
u
a
g
e
tr
an
s
latio
n
[
9
]
an
d
b
u
ild
s
o
m
e
p
ar
allel
co
r
p
u
s
to
tr
an
s
late
b
r
o
ad
e
r
wo
r
d
s
an
d
p
h
r
ases
[
1
0
]
,
[
1
1
]
,
b
u
t
s
till
d
o
n
o
t
wo
r
k
o
n
h
o
w
to
tr
an
s
late
h
o
m
o
n
y
m
a
n
d
p
o
ly
s
em
y
ter
m
s
in
th
e
s
en
ten
ce
.
I
n
d
o
n
esian
MT
[
1
2
]
wo
r
k
s
o
n
tr
an
s
latio
n
s
f
o
r
ca
s
es
o
f
h
o
m
o
n
y
m
an
d
p
o
ly
s
em
y
.
Ho
wev
e
r
,
th
e
d
ev
elo
p
ed
m
eth
o
d
ca
n
n
o
t
d
etec
t
h
o
m
o
n
y
m
ter
m
s
in
th
e
f
o
r
m
o
f
p
r
e
f
ix
es.
B
esid
es
th
at,
th
e
im
p
lem
en
tati
o
n
ca
n
s
till
s
o
lv
e
p
o
ly
s
em
y
te
r
m
s
th
at
in
d
icate
a
d
en
o
tatio
n
an
d
n
o
t
co
n
n
o
tatio
n
.
L
ex
ico
n
an
d
co
r
p
u
s
d
ata
[
1
3
]
,
[
1
4
]
an
d
s
y
llab
le
an
d
p
h
o
n
em
ic
len
g
th
s
[
1
5
]
f
o
r
p
o
ly
s
em
y
f
ea
t
u
r
e
ex
tr
ac
ti
o
n
ac
h
iev
e
h
ig
h
e
r
p
r
ec
is
io
n
a
n
d
F1
-
m
ea
s
u
r
e
but
h
a
v
e
n
o
t
ex
p
lo
r
ed
co
n
tex
tu
al
d
iv
er
s
ity
.
T
h
e
MT
d
ev
elo
p
m
e
n
t
s
h
o
u
ld
b
e
ab
le
t
o
ca
p
t
u
r
e
h
o
m
o
n
y
m
a
n
d
p
o
ly
s
em
y
f
ea
tu
r
es
in
th
e
f
o
r
m
o
f
a
wo
r
d
o
r
p
h
r
ase
.
B
ased
o
n
th
e
p
r
o
b
lem
s
in
p
r
ev
io
u
s
I
n
d
o
n
esian
MT
s
tu
d
ie
s
,
th
is
r
esear
ch
p
r
o
p
o
s
es
h
o
m
o
n
y
m
a
n
d
p
o
ly
s
em
y
ap
p
r
o
ac
h
es
with
m
o
r
p
h
o
lo
g
y
ex
tr
ac
tio
n
i
n
weig
h
tin
g
ter
m
s
f
o
r
I
n
d
o
n
esian
to
E
n
g
lis
h
MT
.
T
h
is
r
esear
ch
aim
s
to
tr
a
n
s
late
I
n
d
o
n
esian
s
en
te
n
ce
s
with
h
o
m
o
n
y
m
s
an
d
p
o
ly
s
em
y
f
ea
tu
r
es
in
to
E
n
g
lis
h
s
en
ten
ce
s
,
wh
eth
er
th
e
y
co
n
tain
m
o
r
p
h
o
lo
g
ical
f
ea
tu
r
es
o
r
n
o
t.
First,
th
is
r
esear
ch
u
s
es
m
o
r
p
h
o
lo
g
y
ex
tr
ac
tio
n
t
o
d
etec
t
s
en
ten
ce
s
th
at
co
n
tai
n
p
r
ef
ix
es
a
n
d
s
u
f
f
ix
es.
T
h
en
,
th
e
wo
r
d
s
im
ilar
ity
m
ea
s
u
r
em
e
n
t
ex
tr
ac
ts
h
o
m
o
n
y
m
an
d
p
o
ly
s
em
y
f
ea
t
u
r
es
u
s
in
g
b
i
d
ir
ec
tio
n
al
e
n
co
d
er
r
e
p
r
esen
tatio
n
s
f
r
o
m
tr
a
n
s
f
o
r
m
e
r
s
(
B
E
R
T
)
em
b
ed
d
in
g
,
n
am
e
en
tity
r
ec
o
g
n
itio
n
(
NE
R
)
,
s
y
n
o
n
y
m
-
b
ased
te
r
m
ex
p
an
s
io
n
,
an
d
s
em
an
tic
s
im
ilar
ity
.
T
h
is
r
esear
ch
u
s
es
NM
T
f
o
r
th
e
tr
an
s
latio
n
p
r
o
c
ess
.
Fin
ally
,
th
is
r
esear
ch
ev
al
u
ates
th
e
p
r
o
p
o
s
ed
MT
p
er
f
o
r
m
an
ce
.
2.
RE
L
AT
E
D
WO
RK
2
.
1
.
Da
t
a
s
et
Data
s
et
[
1
2
]
is
an
I
n
d
o
n
esian
an
d
E
n
g
lis
h
d
ataset
f
o
r
m
ac
h
in
e
tr
an
s
latio
n
test
in
g
.
T
h
is
d
ataset
o
f
1
,
2
0
0
s
en
ten
ce
s
co
n
s
is
ts
o
f
f
o
u
r
ty
p
es
o
f
s
en
ten
ce
s
:
s
im
p
le,
co
m
p
o
u
n
d
,
co
m
p
lex
,
an
d
c
o
m
p
o
u
n
d
-
c
o
m
p
lex
.
T
h
ese
s
en
ten
ce
s
ar
e
g
e
n
er
al
s
en
ten
ce
s
th
at
ca
n
c
o
n
tain
n
eu
t
r
al,
h
o
m
o
n
y
m
,
an
d
p
o
ly
s
em
y
wo
r
d
s
.
T
h
is
d
ataset
h
as
b
ee
n
p
r
e
-
p
r
o
ce
s
s
ed
an
d
well
-
an
n
o
tated
.
T
h
e
I
n
d
o
n
esian
s
y
n
tax
is
an
d
s
em
an
tic
p
r
o
b
lem
s
co
n
tain
ed
in
th
is
d
ataset
ar
e
q
u
ite
co
m
p
lex
,
an
d
s
o
m
e
h
av
e
n
o
t
y
et
b
ee
n
d
is
cu
s
s
ed
.
Fo
r
ex
am
p
le,
h
o
w
ca
n
w
e
tr
an
s
late
a
wo
r
d
in
to
a
s
en
ten
ce
wh
er
e
th
e
wo
r
d
ca
n
b
e
an
a
f
f
ix
wo
r
d
an
d
ca
n
also
b
e
a
b
asic
wo
r
d
,
wh
er
e
ea
ch
o
n
e
h
as
a
d
if
f
er
en
t
m
ea
n
in
g
b
ased
o
n
th
e
co
n
tex
t
o
f
t
h
e
s
en
ten
ce
.
T
h
e
r
ef
o
r
e,
th
is
d
ataset
ca
n
b
e
u
s
ed
as
in
p
u
t
to
test
th
e
p
er
f
o
r
m
an
ce
o
f
th
e
I
n
d
o
n
esian
m
ac
h
in
e
tr
an
s
latio
n
m
eth
o
d
.
2
.
2
.
M
o
rpho
lo
g
y
ex
t
ra
c
t
io
n
I
n
d
o
n
esian
m
o
r
p
h
o
l
o
g
y
ex
tr
ac
tio
n
[
1
6
]
id
e
n
tifie
s
a
wo
r
d
'
s
p
r
ef
ix
es
an
d
s
u
f
f
ix
es
b
a
s
ed
o
n
t
h
e
alter
n
atio
n
s
ch
em
e
o
f
n
o
u
n
s
,
ad
jectiv
es,
v
er
b
s
,
a
n
d
n
u
m
b
er
s
.
T
h
is
id
en
tific
atio
n
is
u
s
ed
t
o
an
aly
ze
th
e
f
o
r
m
o
f
wo
r
d
s
ac
cu
r
ately
an
d
in
ac
c
o
r
d
an
ce
with
th
e
co
n
tex
t
o
f
a
s
en
ten
ce
,
wh
eth
er
th
e
wo
r
d
is
a
co
m
p
lete
wo
r
d
o
r
a
wo
r
d
with
a
p
r
ef
ix
o
r
s
u
f
f
ix
.
T
h
e
alter
n
atio
n
s
ch
em
e
f
o
r
I
n
d
o
n
esian
n
o
u
n
s
,
ad
jectiv
es,
v
e
r
b
s
,
an
d
n
u
m
er
als
is
s
h
o
wn
in
T
ab
le
1
.
2
.
3
.
M
et
a
ph
o
r
co
rpus
T
h
e
m
etap
h
o
r
co
r
p
u
s
,
wh
ic
h
co
n
s
is
ts
o
f
2
5
0
8
I
n
d
o
n
esian
p
h
r
ases
,
is
ex
tr
ac
ted
f
r
o
m
th
e
I
n
d
o
n
esian
th
esau
r
u
s
d
ictio
n
ar
y
[
1
7
]
.
T
a
b
le
2
s
h
o
ws
th
e
m
etap
h
o
r
c
o
r
p
u
s
r
ep
r
esen
tatio
n
.
T
ab
le
2
s
h
o
ws
th
at
th
e
th
r
ee
ter
m
s
lis
ted
ca
n
h
av
e
s
y
n
o
n
y
m
s
,
wh
ich
ca
n
b
e
d
en
o
tatio
n
s
o
r
co
n
n
o
tatio
n
s
.
2
.
4
.
Wo
rd
f
ea
t
ure
ex
t
r
a
ct
io
n
Gen
er
ally
,
wo
r
d
f
ea
tu
r
e
e
x
tr
a
ctio
n
aim
s
to
ca
p
tu
r
e
t
h
e
m
ea
n
in
g
f
u
l
c
h
ar
ac
ter
is
tics
o
f
wo
r
d
s
,
p
h
r
ases
,
o
r
d
o
cu
m
e
n
ts
in
a
way
th
at
alg
o
r
ith
m
s
ca
n
i
n
ter
p
r
et
an
d
p
r
o
ce
s
s
.
T
h
e
d
ee
p
c
o
n
tex
tu
alize
d
wo
r
d
r
ep
r
esen
tatio
n
s
ar
e
in
tr
o
d
u
ce
d
to
ef
f
ec
tiv
ely
m
o
d
el
co
m
p
l
ex
ch
ar
ac
ter
is
tics
o
f
wo
r
d
u
s
e
(
e.
g
.
,
s
y
n
ta
x
a
n
d
s
em
an
tics
)
an
d
th
e
v
ar
iatio
n
s
o
f
th
ese
wo
r
d
s
in
th
e
co
n
te
x
t
(
i.e
.
,
to
m
o
d
el
p
o
ly
s
em
y
)
,
th
er
eb
y
g
en
er
atin
g
co
n
tex
t
in
f
o
r
m
atio
n
[
1
8
]
.
I
n
th
is
r
esear
ch
,
th
e
wo
r
d
f
ea
tu
r
e
ex
tr
ac
tio
n
f
u
n
ctio
n
s
to
id
en
tify
co
n
tex
tu
al
wo
r
d
s
in
s
en
ten
ce
s
an
d
ex
tr
ac
t
ter
m
s
m
o
r
e
ac
cu
r
ately
b
ased
o
n
s
y
n
o
n
y
m
s
.
Fo
r
th
is
r
ea
s
o
n
,
th
is
r
esear
ch
u
s
es
a
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
14
,
No
.
6
,
Dec
em
b
e
r
20
24
:
7
0
3
6
-
7
0
4
5
7038
co
m
b
in
atio
n
o
f
B
E
R
T
em
b
ed
d
in
g
m
eth
o
d
s
,
n
am
e
en
tity
r
e
co
g
n
itio
n
,
s
y
n
o
n
y
m
-
b
ased
ter
m
ex
p
an
s
io
n
,
a
n
d
s
em
an
tic
s
im
ilar
ity
.
T
ab
le
1
.
Alter
n
atio
n
s
ch
em
e
f
o
r
m
o
r
p
h
o
l
o
g
y
e
x
tr
ac
tio
n
A
l
t
e
r
n
a
t
i
o
n
Pre
-
p
r
e
f
i
x
P
r
e
f
i
x
Le
mm
a
S
u
f
f
i
x
N
o
u
n
ε+
ε+
+ε
p
e
n
+
ke+
p
e
r+
Le
mm
a
k
e
+
t
i
d
a
k
+
A
d
j
e
c
t
i
v
e
ε+
ε+
+ε
n
o
n
+
t
e
r+
+
a
n
ke+
Le
mm
a
+
n
y
a
se+
V
e
r
b
ε+
ε+
+ε
m
e
n
+
p
e
r+
+
k
a
n
d
i
+
Le
mm
a
+i
b
e
r+
N
u
mera
l
ε+
+ε
ke+
+
n
y
a
b
e
r+
Le
mm
a
+
b
e
l
a
s
T
ab
le
2
.
Me
tap
h
o
r
c
o
r
p
u
s
r
ep
r
esen
tatio
n
Te
r
ms
S
y
n
o
n
y
ms
Bu
n
g
a
K
e
m
b
a
n
g
(
f
l
o
w
e
r
)
,
o
rn
a
m
e
n
t
(
o
r
n
a
m
e
n
t
)
,
p
e
rem
p
u
a
n
c
a
n
t
i
c
(
b
e
a
u
t
i
f
u
l
w
o
m
e
n
)
,
e
m
b
e
l
-
e
m
b
e
l
(
f
r
i
l
l
)
Bu
n
g
a
a
p
i
C
e
t
u
s
a
n
(
sp
a
r
k
)
,
k
i
l
a
t
a
n
a
p
i
(
f
i
r
e
f
l
a
s
h
)
,
l
e
l
a
t
u
(
f
l
a
s
h
)
Bu
n
g
a
h
a
t
i
b
e
l
a
h
a
n
j
i
w
a
(
s
o
u
l
-
mat
e
)
,
k
e
k
a
s
i
h
(
l
o
v
e
r
)
,
k
e
s
a
y
a
n
g
a
n
(
b
e
l
o
v
e
d
)
2
.
4
.
1
.
B
E
RT
em
bed
din
g
B
id
ir
ec
tio
n
al
en
co
d
er
r
ep
r
ese
n
tatio
n
s
f
r
o
m
t
r
an
s
f
o
r
m
e
r
s
(
B
E
R
T
)
[
1
9
]
,
[
2
0
]
f
u
n
ctio
n
s
to
tr
ain
d
ee
p
two
-
way
r
ep
r
esen
tatio
n
o
f
u
n
lab
eled
tex
t
b
y
c
o
-
co
n
d
itio
n
i
n
g
th
e
lef
t
an
d
r
ig
h
t
c
o
n
tex
t
s
ac
r
o
s
s
all
lay
er
s
.
B
E
R
T
u
s
es
a
co
r
p
u
s
o
f
3
,
3
0
0
m
illi
o
n
wo
r
d
s
f
o
r
th
e
p
r
e
-
tr
ain
in
g
p
r
o
ce
s
s
.
T
h
en
,
t
h
e
f
in
e
-
tu
n
in
g
p
r
o
ce
s
s
f
u
n
ctio
n
s
to
m
o
d
el
s
in
g
le
tex
t e
x
tr
ac
tio
n
task
s
o
r
tex
t
p
air
s
b
y
s
wap
p
in
g
th
e
a
p
p
r
o
p
r
iate
in
p
u
t
an
d
o
u
tp
u
t.
Fo
r
ap
p
licatio
n
s
in
v
o
lv
in
g
tex
t
p
ai
r
s
,
B
E
R
T
u
s
e
s
th
e
s
elf
-
atten
ti
o
n
m
ec
h
a
n
is
m
to
en
co
d
e
th
e
c
o
m
b
in
ed
te
x
t
p
air
s
b
y
ef
f
ec
tiv
ely
im
p
lem
en
tin
g
th
e
s
elf
-
atten
tio
n
m
ec
h
an
is
m
th
at
s
im
u
ltan
eo
u
s
ly
in
clu
d
es
two
-
way
cr
o
s
s
-
atten
tio
n
b
etwe
en
two
s
en
ten
c
es
.
2
.
4
.
2
.
Na
m
ed
ent
it
y
re
co
g
niti
o
n
T
h
e
n
am
ed
en
tity
r
ec
o
g
n
itio
n
(
NE
R
)
ap
p
r
o
ac
h
f
o
r
th
e
I
n
d
o
n
esian
lan
g
u
ag
e
[
2
1
]
is
b
ased
o
n
a
s
et
o
f
r
u
les
ca
p
tu
r
in
g
th
e
co
n
tex
tu
al
,
m
o
r
p
h
o
lo
g
ical,
an
d
p
ar
t
-
of
-
s
p
ee
ch
k
n
o
wled
g
e
n
ec
ess
ar
y
to
r
ec
o
g
n
ize
n
am
e
d
en
titi
es
in
I
n
d
o
n
esian
tex
ts
.
T
h
e
Sin
g
g
alan
g
d
ataset
[
2
2
]
is
a
NE
R
d
ataset
co
m
p
r
is
in
g
4
8
,
9
5
7
s
en
ten
ce
s
.
T
h
e
d
ataset
is
d
iv
id
ed
in
to
f
o
u
r
n
a
m
ed
en
tity
class
es: p
er
s
o
n
n
a
m
es,
p
lace
n
am
es,
o
r
g
an
izatio
n
n
am
es,
an
d
o
th
e
r
s
.
2
.
4
.
3
.
Sy
no
ny
m
-
ba
s
ed
t
er
m
e
x
pa
ns
io
n
T
h
e
s
y
n
o
n
y
m
-
b
ased
ter
m
ex
p
an
s
io
n
[
2
3
]
ca
p
tu
r
es
th
e
ex
is
tin
g
ter
m
s
y
n
o
n
y
m
to
g
e
t
th
e
b
est
ac
cu
r
atio
n
o
f
t
h
e
ter
m
ac
co
r
d
i
n
g
to
th
e
s
en
ten
ce
co
n
tex
t.
T
h
e
s
y
n
o
n
y
m
-
b
ased
ter
m
ex
p
an
s
io
n
id
en
tifie
s
ea
ch
ter
m
th
at
ca
n
in
d
icate
h
o
m
o
n
y
m
an
d
p
o
ly
s
em
y
f
ea
tu
r
es
b
ased
o
n
th
e
ex
t
r
ac
ted
s
y
n
o
n
y
m
ter
m
with
th
e
h
ig
h
est
s
im
ilar
ity
v
alu
e
to
th
e
ter
m
v
ec
to
r
s
.
Fo
r
ex
am
p
le,
s
y
n
o
n
y
m
-
b
ased
ter
m
e
x
p
an
s
io
n
[
1
2
]
e
x
p
an
d
s
th
e
ter
m
ma
la
n
g
,
to
in
clu
d
e
s
y
n
o
n
y
m
s
lik
e
Ma
la
n
g
(
city
n
am
e
)
,
an
d
s
ia
l
(
u
n
l
u
ck
y
)
.
2
.
4
.
4
.
Sem
a
ntic
s
im
ila
rit
y
Sem
an
tic
s
im
ilar
ity
u
s
in
g
C
o
s
in
e
[
2
4
]
p
r
e
d
icts
wo
r
d
s
im
ilar
i
ty
b
etwe
en
th
e
two
in
p
u
t
wo
r
d
s
.
C
o
s
in
e
ca
lcu
lates
th
e
s
im
ilar
ity
o
f
t
wo
wo
r
d
s
b
ased
o
n
th
e
m
ea
n
in
g
u
s
in
g
(
1
)
,
wh
er
e
w
a
d
en
o
tes
th
e
w
o
r
d
1
,
w
b
d
en
o
tes th
e
wo
r
d
2
,
w
ai
d
en
o
tes th
e
v
ec
to
r
m
em
b
er
f
r
o
m
w
a
,
an
d
w
bi
d
en
o
tes th
e
v
ec
to
r
m
em
b
er
f
r
o
m
w
b
.
(
,
)
=
∑
ai
=
1
bi
√
∑
(
ai
)
2
=
1
√
∑
(
bi
)
2
=
1
(
1
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
Ho
mo
n
ym
a
n
d
p
o
lysemy
a
p
p
r
o
a
ch
es w
ith
mo
r
p
h
o
lo
g
y
ex
tr
a
ctio
n
in
…
(
B
u
d
i H
a
r
jo
)
7039
2
.
5
.
Neura
l m
a
chine t
ra
ns
la
t
io
n
T
h
e
NM
T
[
4
]
tr
ain
s
d
ata
o
n
a
lar
g
e
s
ca
le
th
r
o
u
g
h
a
n
ar
tific
ial
n
eu
r
al
n
etwo
r
k
to
b
u
ild
a
m
o
d
el
f
o
r
th
e
tr
an
s
latio
n
p
r
o
ce
s
s
.
T
h
e
N
MT
s
tag
es
co
n
s
is
t
o
f
em
b
ed
d
in
g
,
en
co
d
in
g
,
atten
d
in
g
,
a
n
d
d
ec
o
d
in
g
.
T
h
e
NM
T
s
o
f
tm
ax
lay
er
f
o
r
ca
lcu
latin
g
th
e
s
co
r
e
to
g
en
e
r
ate
th
e
tar
g
et
wo
r
d
as
o
u
t
p
u
t
P
is
s
h
o
wn
in
(
2
)
,
wh
er
e
=
[
1
,
…
,
]
d
en
o
tes
th
e
in
p
u
t
s
o
u
r
ce
s
en
ten
ce
,
d
en
o
tes
th
e
cu
r
r
en
t
g
e
n
er
ated
wo
r
d
,
<
d
en
o
tes
th
e
p
r
ev
io
u
s
ly
g
en
er
ated
wo
r
d
s
,
d
en
o
tes
th
e
d
ec
o
d
er
h
id
d
e
n
s
tate
f
o
r
th
e
cu
r
r
en
t
wo
r
d
,
−
1
d
en
o
tes
th
e
em
b
ed
d
in
g
o
f
th
e
p
r
ev
io
u
s
wo
r
d
,
d
en
o
tes th
e
co
n
tex
t v
ec
to
r
an
d
d
en
o
tes th
e
f
ee
d
f
o
r
war
d
lay
er
.
P
(
|
<
,
)
=
S
o
ftM
a
x
(
(
,
−
1
,
)
)
(
2
)
T
h
e
NM
T
ap
p
r
o
ac
h
h
as
b
ee
n
wid
ely
u
s
ed
in
v
ar
io
u
s
lan
g
u
a
g
e
tr
an
s
latio
n
s
,
in
clu
d
in
g
th
e
I
n
d
o
n
esian
lan
g
u
ag
e
[
9
]
.
Ho
wev
e
r
,
NM
T
[
4
]
,
[
9
]
n
ee
d
s
to
b
e
d
ev
elo
p
ed
in
th
e
em
b
ed
d
i
n
g
task
to
ca
p
t
u
r
e
th
e
tar
g
et
wo
r
d
tr
an
s
latio
n
co
n
tain
in
g
ce
r
tain
I
n
d
o
n
esian
lan
g
u
a
g
e
f
ea
tu
r
es,
s
u
ch
as
m
o
r
p
h
o
lo
g
y
,
h
o
m
o
n
y
m
s
,
an
d
p
o
l
y
s
em
y
.
T
h
e
lead
in
g
tr
an
s
latio
n
task
is
tr
an
s
latin
g
wo
r
d
s
b
ased
o
n
le
x
ical
an
d
p
h
r
ase
s
em
an
tic
m
ea
n
in
g
.
T
h
e
s
em
an
tic
d
is
tan
ce
m
ea
s
u
r
em
en
t
b
etwe
e
n
th
e
ter
m
s
o
u
r
ce
an
d
tr
an
s
lat
ed
ter
m
tar
g
et
is
n
ee
d
e
d
t
o
ca
p
tu
r
e
t
h
e
c
o
n
tex
t
o
f
th
e
wo
r
d
o
r
p
h
r
ase
tr
an
s
latio
n
m
o
r
e
ac
cu
r
ately
.
3.
M
E
T
H
O
D
T
h
is
r
esear
ch
d
e
v
elo
p
s
a
wo
r
d
f
ea
tu
r
e
ap
p
r
o
ac
h
o
f
h
o
m
o
n
y
m
an
d
p
o
ly
s
em
y
with
m
o
r
p
h
o
lo
g
y
ex
tr
ac
tio
n
i
n
ter
m
weig
h
ti
n
g
.
T
h
e
p
u
r
p
o
s
e
is
to
en
h
a
n
ce
t
h
e
p
er
f
o
r
m
a
n
ce
o
f
I
n
d
o
n
esian
to
E
n
g
lis
h
m
ac
h
in
e
tr
an
s
la
tio
n
.
T
h
is
s
ec
tio
n
ex
p
l
ain
s
th
e
p
r
o
p
o
s
ed
d
ataset,
p
r
o
p
o
s
ed
m
o
r
p
h
o
lo
g
y
e
x
tr
ac
tio
n
,
p
r
o
p
o
s
ed
wo
r
d
f
ea
tu
r
e
ex
tr
ac
tio
n
,
p
r
o
p
o
s
ed
m
ac
h
in
e
tr
an
s
latio
n
,
a
n
d
ev
al
u
atio
n
.
3
.
1
.
P
ro
po
s
ed
da
t
a
s
et
As th
e
p
r
o
p
o
s
ed
d
ataset,
th
e
I
n
d
o
n
esian
d
ataset
[
3
]
co
n
s
is
ts
o
f
1
,
0
0
0
tr
ai
n
d
ata
an
d
2
0
0
test
d
ata.
T
h
e
d
ataset
h
ad
b
ee
n
p
r
e
-
p
r
o
ce
s
s
ed
an
d
p
r
o
p
er
ly
a
n
n
o
tated
m
an
u
ally
b
y
I
n
d
o
n
esian
lan
g
u
ag
e
ex
p
er
ts
.
T
h
is
r
esear
ch
u
s
es
th
is
d
ataset
to
test
th
e
p
r
o
p
o
s
ed
MT
p
er
f
o
r
m
an
ce
.
T
h
e
d
ataset
r
ep
r
esen
tatio
n
is
s
h
o
wn
i
n
T
ab
le
3
.
T
ab
le
3
.
Pro
p
o
s
ed
d
ataset
r
ep
r
esen
tatio
n
ID
S
e
n
t
e
n
c
e
s
0
Ay
a
h
p
e
r
g
i
k
e
P
a
l
u
(
F
a
t
h
e
r
g
o
e
s t
o
P
a
l
u
)
1
Ay
a
h
m
e
m
b
e
l
i
p
a
l
u
(
F
a
t
h
e
r
b
u
y
s
a
h
a
mm
e
r
)
2
An
d
a
p
e
rl
u
b
e
r
u
a
n
g
b
a
n
y
a
k
u
n
t
u
k
m
e
m
b
e
l
i
m
o
b
i
l
i
n
i
(
Y
o
u
n
e
e
d
t
o
h
a
v
e
a
l
o
t
o
f
m
o
n
e
y
t
o
b
u
y
t
h
i
s
c
a
r
)
3
K
a
m
i
m
e
n
i
k
m
a
t
i
p
e
rt
u
n
j
u
k
a
n
b
e
ru
a
n
g
y
a
n
g
l
u
a
r
b
i
a
s
a
(
w
e
e
n
j
o
y
a
g
r
e
a
t
b
e
a
r
s
h
o
w
)
4
Aro
m
a
t
e
h
b
u
n
g
a
m
e
l
a
t
i
i
n
i
s
u
n
g
g
u
h
n
i
k
m
a
t
(
Th
e
a
r
o
m
a
o
f
t
h
i
s j
a
sm
i
n
e
f
l
o
w
e
r
t
e
a
i
s rea
l
l
y
d
e
l
i
c
i
o
u
s)
5
S
a
y
a
m
e
n
i
k
m
a
t
i
s
u
a
sa
n
a
o
u
t
d
o
o
r
y
a
n
g
i
n
d
a
h
d
e
n
g
a
n
b
u
n
g
a
h
a
t
i
k
u
(
I
e
n
j
o
y
t
h
e
b
e
a
u
t
i
f
u
l
o
u
t
d
o
o
r
a
t
m
o
s
p
h
e
r
e
w
i
t
h
my
l
o
v
e
r
)
3
.
2
.
P
ro
po
s
ed
wo
rd
f
ea
t
ure
ex
t
ra
ct
io
n wit
h m
o
rpho
lo
g
y
ex
t
ra
ct
io
n
First,
th
e
p
r
o
p
o
s
ed
m
o
r
p
h
o
lo
g
y
ex
tr
ac
tio
n
u
s
es
th
e
co
n
ce
p
t
o
f
m
o
r
p
h
o
lo
g
y
with
f
o
u
r
alter
n
atio
n
s
ch
em
es:
n
o
u
n
alter
n
atio
n
,
a
d
jectiv
e
alter
n
atio
n
,
v
er
b
alter
n
atio
n
,
a
n
d
n
u
m
er
al
alter
n
at
io
n
[
1
6
]
.
Fig
u
r
e
1
s
h
o
ws
th
e
p
r
o
p
o
s
ed
m
o
r
p
h
o
lo
g
y
e
x
tr
ac
tio
n
f
l
o
w
ch
ar
t
to
ex
tr
ac
t
lem
m
a
f
ea
tu
r
es
an
d
d
er
iv
ativ
es
b
ased
o
n
p
r
ef
ix
es,
lem
m
as,
an
d
s
u
f
f
ix
e
s
.
T
h
e
to
k
en
s
f
r
o
m
th
e
in
p
u
t
s
en
ten
ce
s
ar
e
g
en
er
ated
u
s
in
g
th
e
to
k
en
izatio
n
p
r
o
ce
s
s
.
T
h
e
to
k
en
r
esu
lts
ar
e
p
r
o
ce
s
s
ed
th
r
o
u
g
h
th
e
alter
n
atio
n
s
ch
em
e:
s
u
f
f
i
x
es
ex
tr
a
ctio
n
an
d
p
r
ef
ix
es
ex
tr
ac
tio
n
.
T
h
e
r
esu
lts
o
f
s
u
f
f
ix
an
d
p
r
ef
ix
ex
tr
ac
tio
n
ar
e
p
r
o
ce
s
s
ed
in
th
e
lem
m
a
u
p
d
ate
p
r
o
ce
s
s
to
o
b
tain
m
o
r
p
h
o
lo
g
ical
ter
m
id
en
tific
atio
n
r
esu
lts
.
T
h
en
,
lem
m
atiza
tio
n
is
ca
r
r
ied
o
u
t
to
ex
tr
ac
t
m
o
d
if
ied
to
k
en
s
.
Fin
ally
,
we
s
av
e
th
e
m
o
d
i
f
ied
to
k
en
r
esu
lts
.
T
ab
le
4
illu
s
tr
ates
s
en
ten
ce
s
3
an
d
5
m
o
r
p
h
o
lo
g
y
ex
tr
ac
tio
n
.
Seco
n
d
,
th
e
p
r
o
p
o
s
ed
wo
r
d
f
ea
tu
r
e
ex
tr
ac
tio
n
u
s
es
B
E
R
T
em
b
ed
d
i
n
g
[
1
9
]
,
s
y
n
o
n
y
m
-
b
ased
ter
m
ex
p
an
s
io
n
[
2
3
]
,
an
d
Sem
an
tic
s
im
ilar
ity
[
2
5
]
t
o
o
b
tain
h
o
m
o
n
y
m
a
n
d
p
o
ly
s
em
y
ter
m
s
.
T
h
e
f
lo
wch
ar
t
o
f
th
e
p
r
o
p
o
s
ed
wo
r
d
f
ea
t
u
r
e
ex
tr
ac
t
io
n
is
s
h
o
wn
in
Fig
u
r
e
2
.
W
e
u
s
e
s
en
ten
ce
s
,
id
en
tifie
d
m
o
r
p
h
o
lo
g
y
te
r
m
s
,
an
d
m
o
d
if
ied
to
k
en
r
esu
lts
as
th
e
in
p
u
t.
W
e
ex
tr
ac
t
th
e
s
y
n
o
n
y
m
ter
m
s
u
s
in
g
Sem
an
tic
s
im
ilar
ity
an
d
B
E
R
T
b
ased
o
n
th
e
ter
m
with
th
e
h
ig
h
est
s
im
ilar
ity
v
alu
e
th
r
o
u
g
h
th
e
Sin
g
g
alan
g
en
tity
co
r
p
u
s
an
d
th
e
th
esau
r
u
s
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
14
,
No
.
6
,
Dec
em
b
e
r
20
24
:
7
0
3
6
-
7
0
4
5
7040
s
y
n
o
n
y
m
co
r
p
u
s
.
Mo
r
eo
v
er
,
i
n
th
e
s
y
n
o
n
y
m
ex
tr
ac
tio
n
p
r
o
ce
s
s
,
if
th
er
e
is
an
e
x
tr
ac
ted
p
r
ef
ix
b
er
-
,
th
e
ter
m
b
er
-
is
m
o
d
if
ied
to
b
e
th
e
ter
m
mem
p
u
n
ya
i
(
h
as/h
av
e
)
.
T
h
e
n
,
if
th
er
e
ar
e
b
i
-
g
r
am
ter
m
ex
tr
ac
tio
n
r
esu
lts
an
d
th
e
b
i
-
g
r
a
m
ter
m
e
x
is
ts
in
th
e
m
etap
h
o
r
co
r
p
u
s
,
tak
e
th
e
s
y
n
o
n
y
m
ter
m
f
r
o
m
t
h
e
m
etap
h
o
r
co
r
p
u
s
with
th
e
h
ig
h
est
s
im
ilar
ity
v
alu
e
to
b
e
th
e
ex
tr
ac
ted
s
y
n
o
n
y
m
ter
m
.
Fu
r
th
er
m
o
r
e,
B
E
R
T
an
d
Sem
an
tic
s
im
ilar
ity
m
ea
s
u
r
e
th
e
s
im
ilar
ity
b
etwe
e
n
ex
is
tin
g
ter
m
s
,
m
o
d
if
ied
to
k
en
s
,
an
d
ex
tr
ac
ted
s
y
n
o
n
y
m
ter
m
s
.
Fin
ally
,
th
e
ex
tr
ac
ted
ter
m
r
esu
lt
with
th
e
h
ig
h
est
s
im
ilar
ity
is
u
s
ed
to
s
u
b
s
titu
te
th
e
ex
is
tin
g
ter
m
s
in
th
e
in
p
u
t
s
en
ten
ce
.
T
ab
le
5
illu
s
tr
ates
s
en
ten
ce
s
3
an
d
5
wo
r
d
f
ea
t
u
r
e
ex
t
r
ac
tio
n
.
Fig
u
r
e
1
.
Pro
p
o
s
ed
m
o
r
p
h
o
lo
g
y
ex
tr
ac
tio
n
T
ab
le
4
.
I
llu
s
tr
atio
n
o
f
m
o
r
p
h
o
lo
g
y
e
x
tr
ac
tio
n
ID
S
e
n
t
e
n
c
e
s
To
k
e
n
s
I
d
e
n
t
i
f
i
e
d
m
o
r
p
h
o
l
o
g
y
t
e
r
ms
M
o
d
i
f
i
e
d
t
o
k
e
n
s
3
K
a
m
i
m
e
n
i
k
m
a
t
i
p
e
rt
u
n
j
u
k
a
n
b
e
r
u
a
n
g
y
a
n
g
l
u
a
r
b
i
a
s
a
m
e
n
i
k
m
a
t
i
,
p
e
r
t
u
n
j
u
k
a
n
,
b
e
ru
a
n
g
m
e
+
n
i
k
m
a
t
+
i
,
p
e
r+
t
u
n
j
u
k
+
a
n
,
b
e
r+
u
a
n
g
m
e
n
i
k
m
a
t
i
,
p
e
r
t
u
n
j
u
k
a
n
,
b
e
r
u
a
n
g
5
S
a
y
a
m
e
n
i
k
m
a
t
i
s
u
a
sa
n
a
o
u
t
d
o
o
r
y
a
n
g
i
n
d
a
h
d
e
n
g
a
n
b
u
n
g
a
h
a
t
i
k
u
m
e
n
i
k
m
a
t
i
,
s
u
a
s
a
n
a
,
o
u
t
d
o
o
r,
b
u
n
g
a
,
h
a
t
i
k
u
m
e
+
n
i
k
m
a
t
+
i
,
h
a
t
i
+
k
u
m
e
n
i
k
m
a
t
i
,
s
u
a
s
a
n
a
,
o
u
t
d
o
o
r,
b
u
n
g
a
,
h
a
t
i
Fig
u
r
e
2
.
Pro
p
o
s
ed
wo
r
d
f
ea
t
u
r
e
ex
tr
ac
tio
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
Ho
mo
n
ym
a
n
d
p
o
lysemy
a
p
p
r
o
a
ch
es w
ith
mo
r
p
h
o
lo
g
y
ex
tr
a
ctio
n
in
…
(
B
u
d
i H
a
r
jo
)
7041
T
ab
le
5
.
I
llu
s
tr
atio
n
o
f
wo
r
d
f
ea
tu
r
e
ex
tr
ac
tio
n
3
.
3
.
P
ro
po
s
ed
m
a
chine t
ra
ns
la
t
io
n
T
h
e
alg
o
r
ith
m
o
f
th
e
p
r
o
p
o
s
ed
MT
m
eth
o
d
u
s
in
g
NM
T
[
4
]
is
s
h
o
wn
in
T
a
b
le
6
.
First,
th
e
wo
r
d
ex
tr
ac
tio
n
r
esu
lt
is
u
s
ed
as
th
e
in
p
u
t.
I
n
th
e
en
co
d
in
g
s
tep
s
,
t
h
e
in
p
u
t
s
eq
u
e
n
ce
will
b
e
co
n
v
er
ted
in
t
o
a
f
ix
ed
-
len
g
th
r
e
p
r
esen
tatio
n
o
r
a
s
e
r
ies
o
f
v
ec
to
r
s
th
at
ca
p
tu
r
e
th
e
m
ea
n
in
g
o
f
th
e
in
p
u
t.
T
h
en
,
th
e
atten
tio
n
m
ec
h
an
is
m
co
m
p
u
tes
a
co
n
tex
t
v
ec
to
r
as
a
weig
h
ted
s
u
m
o
f
all
e
n
co
d
e
r
h
i
d
d
en
s
tates.
T
h
e
weig
h
ts
ar
e
d
eter
m
in
ed
b
y
alig
n
m
en
t
s
co
r
es,
wh
ich
m
ea
s
u
r
e
th
e
r
elev
an
ce
o
f
ea
ch
en
co
d
e
r
'
s
h
id
d
en
s
tate
to
th
e
cu
r
r
en
t
d
ec
o
d
in
g
s
tep
.
T
h
e
alig
n
m
en
t
s
co
r
es
ar
e
n
o
r
m
alize
d
u
s
in
g
a
So
f
tMa
x
f
u
n
ctio
n
to
p
r
o
d
u
ce
a
p
r
o
b
ab
ilit
y
d
is
tr
ib
u
tio
n
o
v
er
th
e
en
co
d
er
'
s
h
id
d
e
n
s
tates.
T
h
e
d
ec
o
d
in
g
g
en
er
ates
th
e
o
u
tp
u
t
s
eq
u
e
n
ce
o
n
e
to
k
e
n
at
a
tim
e
,
u
s
in
g
th
e
co
n
tex
t
v
ec
to
r
s
f
r
o
m
th
e
atten
tio
n
m
ec
h
an
is
m
an
d
th
e
p
r
ev
io
u
s
d
ec
o
d
er
’
s
h
id
d
e
n
s
tates.
Fin
ally
,
th
e
tr
an
s
latio
n
r
esu
lt is
s
av
ed
.
T
ab
le
6
.
T
h
e
alg
o
r
ith
m
o
f
th
e
p
r
o
p
o
s
ed
m
ac
h
in
e
tr
an
s
latio
n
I
n
p
u
t
:
W
o
rd
f
e
a
t
u
r
e
e
x
t
r
a
c
t
i
o
n
r
e
su
l
t
1.
Ta
k
i
n
g
t
h
e
w
o
r
d
f
e
a
t
u
r
e
e
x
t
r
a
c
t
i
o
n
r
e
s
u
l
t
s a
s
t
h
e
i
n
p
u
t
.
2.
En
c
o
d
i
n
g
3.
A
t
t
e
n
d
i
n
g
.
4.
D
e
c
o
d
i
n
g
.
5.
S
a
v
e
t
h
e
t
r
a
n
sl
a
t
i
o
n
r
e
su
l
t
.
3
.
4
.
E
v
a
lua
t
io
n
T
h
e
ev
alu
atio
n
p
r
o
ce
s
s
aim
s
to
m
ea
s
u
r
e
th
e
p
er
f
o
r
m
an
ce
o
f
th
e
p
r
o
p
o
s
ed
m
eth
o
d
.
T
h
e
ev
alu
atio
n
u
s
es
a
co
n
f
u
s
io
n
m
atr
ix
t
o
ca
lcu
late
s
co
r
es
o
f
p
r
ec
is
io
n
(
P
)
,
r
ec
all
(
R
)
,
F
1
-
m
e
asu
r
e
(
F)
,
an
d
ac
cu
r
ac
y
(
A)
[
2
5
]
.
T
h
e
p
r
ec
is
io
n
,
r
ec
all,
F
1
-
m
ea
s
u
r
e,
an
d
ac
cu
r
ac
y
ar
e
ca
l
cu
lated
u
s
in
g
(
3
)
,
(
4
)
,
(
5
)
,
an
d
(
6
)
,
r
esp
ec
tiv
el
y
.
=
+
(
3
)
=
+
(
4
)
=
2
×
×
+
(
5
)
=
+
+
+
+
(
6
)
4.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
I
n
th
is
s
ec
tio
n
,
th
e
r
esu
lts
o
f
th
e
p
r
o
p
o
s
ed
m
o
r
p
h
o
lo
g
y
ex
tr
ac
tio
n
an
d
p
r
o
p
o
s
ed
wo
r
d
f
ea
tu
r
e
ex
tr
ac
tio
n
ar
e
ex
p
lain
ed
f
ir
s
t.
T
h
en
,
th
e
p
r
o
p
o
s
ed
MT
an
d
Go
o
g
le
T
r
an
s
lato
r
r
esu
lts
ar
e
also
co
m
p
ar
ed
.
Fin
ally
,
th
e
p
er
f
o
r
m
an
ce
r
esu
l
ts
ar
e
co
m
p
ar
ed
with
o
th
er
p
er
f
o
r
m
an
ce
m
eth
o
d
s
.
4
.
1
.
Wo
rd
f
ea
t
ure
ex
t
ra
c
t
io
n r
esu
lt
T
h
e
h
o
m
o
n
y
m
an
d
p
o
ly
s
em
y
f
ea
tu
r
es
ca
n
b
e
a
d
eq
u
ately
e
x
tr
ac
ted
.
T
ab
le
7
s
h
o
ws
th
e
illu
s
tr
atio
n
r
esu
lt
o
f
th
e
wo
r
d
f
ea
tu
r
e
ex
tr
ac
tio
n
f
o
r
s
ix
s
en
ten
ce
s
.
T
h
e
h
ig
h
est
s
im
ilar
ity
s
co
r
e
o
f
s
en
ten
ce
0
was
0
.
7
4
4
6
f
o
r
p
a
l
u
,
an
d
p
a
lu
is
u
s
ed
to
u
p
d
ate
th
e
r
esu
lt
o
f
t
h
e
m
o
d
if
ied
s
en
ten
ce
.
T
h
e
h
ig
h
est
s
im
ilar
ity
s
co
r
e
o
f
ID
S
e
n
t
e
n
c
e
s
I
d
e
n
t
i
f
i
e
d
mo
r
p
h
o
l
o
g
y
t
e
r
ms
M
o
d
i
f
i
e
d
t
o
k
e
n
s
I
d
e
n
t
i
f
i
e
d
t
e
r
ms
o
f
h
o
m
o
n
y
m
a
n
d
p
o
l
y
sem
y
M
o
d
i
f
i
e
d
t
e
r
ms
S
i
mi
l
a
r
i
t
y
sc
o
r
e
b
e
t
w
e
e
n
i
d
e
n
t
i
f
i
e
d
t
e
r
ms
a
n
d
m
o
d
i
f
i
e
d
t
o
k
e
n
s
S
i
mi
l
a
r
i
t
y
sc
o
r
e
b
e
t
w
e
e
n
m
o
d
i
f
i
e
d
t
e
r
ms
a
n
d
mo
d
i
f
i
e
d
t
o
k
e
n
s
R
e
s
u
l
t
s
3
K
a
m
i
m
e
n
i
k
m
a
t
i
p
e
r
t
u
n
j
u
k
a
n
b
e
r
u
a
n
g
y
a
n
g
l
u
a
r
b
i
a
s
a
m
e
+
n
i
k
m
a
t
+
i
,
p
e
r+
t
u
n
j
u
k
+
a
n
,
b
e
r+
u
a
n
g
m
e
n
i
k
m
a
t
i
,
p
e
r
t
u
n
j
u
k
a
n
,
b
e
r
u
a
n
g
b
e
r
u
a
n
g
m
e
m
p
u
n
y
a
i
,
u
a
n
g
0
.
7
3
6
3
0
.
7
2
5
9
K
a
m
i
m
e
n
i
k
m
a
t
i
p
e
r
t
u
n
j
u
k
a
n
b
e
r
u
a
n
g
y
a
n
g
l
u
a
r
b
i
a
s
a
5
S
a
y
a
m
e
n
i
k
m
a
t
i
su
a
s
a
n
a
o
u
t
d
o
o
r
y
a
n
g
i
n
d
a
h
d
e
n
g
a
n
b
u
n
g
a
h
a
t
i
k
u
m
e
+
n
i
k
m
a
t
+
i
,
h
a
t
i
+
k
u
m
e
n
i
k
m
a
t
i
,
su
a
s
a
n
a
,
o
u
t
d
o
o
r,
b
u
n
g
a
,
h
a
t
i
b
u
n
g
a
h
a
t
i
k
e
k
a
si
h
0
.
6
5
7
1
0
.
7
5
5
7
S
a
y
a
m
e
n
i
k
m
a
t
i
su
a
s
a
n
a
o
u
t
d
o
o
r
y
a
n
g
i
n
d
a
h
d
e
n
g
a
n
k
e
k
a
si
h
k
u
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
14
,
No
.
6
,
Dec
em
b
e
r
20
24
:
7
0
3
6
-
7
0
4
5
7042
Sen
ten
ce
1
was
0
.
7
2
8
3
f
o
r
ma
r
til,
an
d
ma
r
til
is
u
s
ed
to
u
p
d
ate
th
e
r
esu
lt
o
f
t
h
e
m
o
d
if
ied
s
en
ten
ce
.
T
h
e
h
ig
h
est
s
im
ilar
ity
s
co
r
e
o
f
s
en
ten
ce
2
was
0
.
7
7
1
1
f
o
r
me
mp
u
n
ya
i
u
a
n
g
,
an
d
mem
p
u
n
y
a
i
u
a
n
g
is
u
s
ed
to
u
p
d
ate
th
e
r
esu
lt o
f
th
e
m
o
d
if
i
ed
s
en
ten
ce
.
T
h
e
h
ig
h
est s
im
ilar
ity
s
co
r
e
o
f
s
en
ten
ce
3
was 0
.
7
3
6
3
f
o
r
b
eru
a
n
g
,
an
d
b
eru
a
n
g
is
u
s
ed
to
u
p
d
ate
th
e
r
esu
lt
o
f
th
e
m
o
d
if
ied
s
en
ten
ce
.
T
h
e
h
i
g
h
est
s
im
ilar
ity
s
co
r
e
o
f
s
en
te
n
ce
4
was
n
u
ll
b
ec
au
s
e
th
er
e
was
n
o
id
en
tifie
d
ter
m
,
a
n
d
th
e
r
es
u
lt
o
f
th
e
m
o
d
if
ied
s
en
ten
ce
was
th
e
s
am
e
as
th
e
in
p
u
t
s
en
ten
ce
.
T
h
e
h
ig
h
est
s
im
ilar
ity
s
co
r
e
o
f
Sen
ten
ce
5
was
0
.
7
5
5
7
f
o
r
ke
ka
s
ih
,
an
d
ke
ka
s
ih
is
u
s
ed
to
u
p
d
ate
th
e
r
esu
lt o
f
th
e
m
o
d
if
i
ed
s
en
ten
ce
.
T
ab
le
7
.
I
llu
s
tr
atio
n
r
esu
lts
o
f
wo
r
d
f
ea
tu
r
e
ex
tr
ac
tio
n
ID
To
k
e
n
s
I
d
e
n
t
i
f
i
e
d
t
e
r
ms
C
o
m
p
a
r
i
so
n
s
i
m
i
l
a
r
i
t
y
b
e
t
w
e
e
n
t
e
r
ms
a
n
d
t
o
k
e
n
s
M
o
d
i
f
i
e
d
s
e
n
t
e
n
c
e
r
e
s
u
l
t
s
I
d
e
n
t
i
f
i
e
d
M
o
d
i
f
i
e
d
Te
r
ms
S
c
o
r
e
Te
r
ms
S
c
o
r
e
0
p
e
r
g
i
,
p
a
l
u
p
a
l
u
p
a
l
u
0
.
7
4
4
6
m
a
rt
i
l
0
.
7
2
8
3
Ay
a
h
p
e
r
g
i
k
e
P
a
l
u
1
m
e
m
b
e
l
i
,
p
a
l
u
p
a
l
u
p
a
l
u
0
.
6
6
9
4
m
a
rt
i
l
0
.
7
2
8
3
Ay
a
h
m
e
m
b
e
l
i
m
a
r
t
i
l
2
p
e
r
l
u
,
b
e
r
u
a
n
g
,
m
e
m
b
e
l
i
,
m
o
b
i
l
b
e
r
u
a
n
g
b
e
r
u
a
n
g
0
.
7
5
4
8
m
e
m
p
u
n
y
a
i
,
u
a
n
g
0
.
7
7
1
1
An
d
a
p
e
rl
u
m
e
m
p
u
n
y
a
i
u
a
n
g
b
a
n
y
a
k
u
n
t
u
k
m
e
m
b
e
l
i
m
o
b
i
l
i
n
i
3
m
e
n
i
k
m
a
t
i
,
p
e
r
t
u
n
j
u
k
a
n
,
b
e
r
u
a
n
g
b
e
r
u
a
n
g
b
e
r
u
a
n
g
0
.
7
3
6
3
m
e
m
p
u
n
y
a
i
,
u
a
n
g
0
.
7
2
5
9
K
a
m
i
m
e
n
i
k
m
a
t
i
p
e
rt
u
n
j
u
k
a
n
b
e
r
u
a
n
g
y
a
n
g
l
u
a
r
b
i
a
s
a
4
a
ro
m
a
,
t
e
h
,
b
u
n
g
a
,
m
e
l
a
t
i
,
n
i
k
m
a
t
n
u
l
l
n
u
l
l
n
u
l
l
n
u
l
l
n
u
l
l
Aro
m
a
t
e
h
b
u
n
g
a
m
e
l
a
t
i
i
n
i
su
n
g
g
u
h
n
i
k
m
a
t
5
m
e
n
i
k
m
a
t
i
,
s
u
a
s
a
n
a
,
o
u
t
d
o
o
r,
b
u
n
g
a
,
h
a
t
i
b
u
n
g
a
h
a
t
i
b
u
n
g
a
h
a
t
i
0
.
6
5
7
1
k
e
k
a
si
h
0
.
7
5
5
7
S
a
y
a
m
e
n
i
k
m
a
t
i
s
u
a
sa
n
a
o
u
t
d
o
o
r
y
a
n
g
i
n
d
a
h
d
e
n
g
a
n
k
e
k
a
si
h
k
u
T
h
e
u
s
e
o
f
th
e
m
o
r
p
h
o
lo
g
y
alter
n
atio
n
co
n
ce
p
t
in
wo
r
d
f
ea
tu
r
e
ex
tr
ac
tio
n
ca
n
well
ca
p
tu
r
e
th
e
m
o
r
p
h
o
lo
g
ical
f
ea
t
u
r
es
o
f
h
o
m
o
n
y
m
ter
m
s
(
e.
g
.
,
b
eru
a
n
g
t
o
b
e
b
er+u
a
n
g
)
an
d
p
o
ly
s
em
y
ter
m
s
(
e.
g
.
,
b
u
n
g
a
h
a
tiku
to
b
e
b
u
n
g
a
h
a
ti+ku
)
.
T
h
e
n
,
B
E
R
T
em
b
e
d
d
in
g
an
d
Sem
an
tic
s
im
ilar
ity
ex
p
an
d
ter
m
s
th
r
o
u
g
h
s
y
n
o
n
y
m
s
b
ased
o
n
ter
m
s
i
n
t
h
e
en
tity
co
r
p
u
s
(
e.
g
.
,
p
a
lu
h
a
s
s
y
n
o
n
y
m
ma
r
til
)
a
n
d
th
esau
r
u
s
(
e.
g
.
,
b
u
n
g
a
h
a
ti
h
as
s
y
n
o
n
y
m
ke
ka
s
ih
)
.
T
h
e
r
etr
iev
al
o
f
m
o
d
if
ied
ter
m
r
esu
lts
f
o
r
m
o
d
i
f
ied
s
en
ten
ce
s
is
d
o
n
e
b
y
m
ea
s
u
r
in
g
th
e
s
im
ilar
ity
v
alu
e
b
etwe
en
t
h
e
id
en
tifie
d
ter
m
a
n
d
th
e
ex
t
r
ac
ted
to
k
e
n
.
T
h
e
r
esu
ltin
g
ter
m
with
th
e
h
ig
h
est
s
im
ilar
ity
v
alu
e
is
u
s
ed
as
a
m
o
d
if
ier
f
o
r
th
e
in
p
u
t
s
en
ten
c
e.
T
h
is
m
o
d
if
ied
s
en
ten
ce
is
th
en
u
s
ed
as
in
p
u
t
f
o
r
th
e
p
r
o
p
o
s
ed
m
ac
h
in
e
tr
an
s
latio
n
.
T
h
e
m
o
d
e
l
p
e
r
f
o
r
m
a
n
c
e
m
e
a
s
u
r
e
m
e
n
t
r
e
s
u
l
ts
a
r
e
s
h
o
w
n
i
n
T
a
b
l
e
8
.
T
a
b
l
e
8
c
o
m
p
a
r
e
s
t
h
e
a
v
e
r
a
g
e
a
c
c
u
r
a
c
y
r
e
s
u
lt
s
o
f
t
h
e
t
h
r
ee
m
o
d
e
l
s
:
s
e
m
a
n
t
i
c
s
i
m
il
a
r
i
ty
,
B
E
R
T
e
m
b
e
d
d
i
n
g
+
s
e
m
a
n
ti
c
s
i
m
i
l
a
r
i
t
y
,
a
n
d
m
o
r
p
h
o
l
o
g
y
e
x
t
r
a
c
t
i
o
n
+
s
y
n
o
n
y
m
-
b
a
s
e
d
t
e
r
m
e
x
p
a
n
s
i
o
n
+B
E
R
T
e
m
b
e
d
d
i
n
g
+
s
e
m
a
n
t
i
c
s
i
m
il
a
r
i
t
y
.
Pe
r
f
o
r
m
a
n
c
e
t
e
s
ti
n
g
o
f
2
0
0
t
e
s
t
d
a
t
a
w
a
s
ca
r
r
i
e
d
o
u
t
u
s
i
n
g
5
0
e
p
o
c
h
s
.
T
h
e
b
e
s
t
m
o
d
e
l
r
e
s
u
l
ts
o
b
t
a
i
n
e
d
w
e
r
e
t
h
e
p
r
o
p
o
s
e
d
m
e
t
h
o
d
m
o
d
e
l
u
s
i
n
g
m
o
r
p
h
o
l
o
g
y
e
x
t
r
a
c
t
i
o
n
,
s
y
n
o
n
y
m
-
b
a
s
e
d
t
e
r
m
e
x
p
a
n
s
i
o
n
,
B
E
R
T
e
m
b
e
d
d
i
n
g
,
a
n
d
S
e
m
a
n
t
ic
s
i
m
il
a
r
i
t
y
wi
t
h
a
n
a
v
e
r
a
g
e
a
cc
u
r
a
c
y
v
a
l
u
e
o
f
0
.
8
1
.
T
ab
le
8
.
Mo
d
el
av
er
a
g
e
ac
cu
r
ac
y
o
f
wo
r
d
ex
t
r
ac
tio
n
M
e
t
h
o
d
A
v
e
r
a
g
e
a
c
c
u
r
a
c
y
S
e
ma
n
t
i
c
s
i
mi
l
a
r
i
t
y
0
.
7
3
B
ER
T
e
m
b
e
d
d
i
n
g
+
S
e
ma
n
t
i
c
s
i
mi
l
a
r
i
t
y
0
.
7
8
M
o
r
p
h
o
l
o
g
y
e
x
t
r
a
c
t
i
o
n
+
S
y
n
o
n
y
m
-
b
a
s
e
d
t
e
r
m
e
x
p
a
n
s
i
o
n
+
B
E
R
T
e
mb
e
d
d
i
n
g
+
S
e
ma
n
t
i
c
s
i
m
i
l
a
r
i
t
y
0
.
8
1
4
.
2
.
Co
m
pa
riso
n
re
s
ults
o
f
m
a
ch
ine t
ra
ns
la
t
io
ns
T
h
e
p
r
ev
io
u
s
m
eth
o
d
u
s
in
g
NM
T
,
Go
o
g
le
T
r
a
n
s
lato
r
,
ca
n
ad
eq
u
ately
tr
a
n
s
late
th
e
s
en
t
en
ce
s
1
,
3
,
an
d
4
b
u
t
ca
n
n
o
t
co
r
r
ec
tly
tr
a
n
s
late
th
e
s
en
ten
ce
s
0
,
2
,
a
n
d
5
.
I
n
Sen
ten
ce
0
,
Go
o
g
le
T
r
an
s
lato
r
s
till
tr
an
s
lates
p
a
lu
as
th
e
h
a
mme
r
,
wh
ich
m
ea
n
s
a
to
o
l,
an
d
it
ca
n
n
o
t
tr
an
s
late
th
e
co
r
r
ec
t
ter
m
p
a
lu
as
th
e
city
n
am
e
P
a
lu
.
In
Sen
ten
ce
2
,
Go
o
g
le
T
r
an
s
l
ato
r
s
till
tr
an
s
lates
b
eru
a
n
g
as
th
e
b
ea
r
,
wh
ich
m
ea
n
s
an
an
im
al,
an
d
ca
n
n
o
t
tr
an
s
late
th
e
co
r
r
ec
t te
r
m
b
eru
a
n
g
as th
e
alter
n
atio
n
v
er
b
b
er
+u
a
n
g
,
wh
ich
m
ea
n
s
h
a
ve
mo
n
ey
.
I
n
Sen
ten
ce
5
,
Go
o
g
le
T
r
an
s
lato
r
s
till
tr
an
s
lates
b
u
n
g
a
h
a
tiku
as
th
e
flo
w
ers
o
f
my
h
ea
r
t,
wh
ich
m
ea
n
s
a
d
en
o
tatio
n
ter
m
,
an
d
ca
n
n
o
t
tr
an
s
late
th
e
co
r
r
ec
t te
r
m
b
u
n
g
a
h
a
tiku
as
my
lo
ve
r
,
wh
ich
m
ea
n
s
a
co
n
n
o
tatio
n
ter
m
.
W
e
co
m
p
ar
e
o
u
r
p
r
o
p
o
s
ed
MT
with
Go
o
g
le
T
r
an
s
lat
o
r
.
T
h
e
wo
r
d
f
ea
tu
r
e
ex
tr
a
ctio
n
with
m
o
r
p
h
o
lo
g
y
e
x
tr
ac
tio
n
ca
n
s
i
g
n
if
ican
tly
en
h
a
n
ce
NM
T
p
er
f
o
r
m
an
ce
.
T
h
e
p
r
o
p
o
s
ed
MT
m
eth
o
d
ca
n
tr
an
s
late
co
r
r
ec
tly
f
o
r
s
ix
s
en
ten
ce
s
0
,
1
,
2
,
3
,
4
,
an
d
5
.
T
h
e
p
r
o
b
lem
s
o
f
t
r
an
s
latio
n
task
s
f
r
o
m
I
n
d
o
n
esian
to
E
n
g
lis
h
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
Ho
mo
n
ym
a
n
d
p
o
lysemy
a
p
p
r
o
a
ch
es w
ith
mo
r
p
h
o
lo
g
y
ex
tr
a
ctio
n
in
…
(
B
u
d
i H
a
r
jo
)
7043
f
o
r
in
p
u
t
s
en
ten
ce
s
co
n
tain
i
n
g
h
o
m
o
n
y
m
an
d
p
o
ly
s
em
y
f
e
atu
r
es
with
m
o
r
p
h
o
lo
g
ical
f
ea
tu
r
es
ca
n
b
e
s
o
lv
ed
b
y
th
e
p
r
o
p
o
s
ed
m
eth
o
d
.
Ho
w
ev
er
,
th
e
p
r
o
p
o
s
ed
wo
r
d
f
ea
tu
r
e
ex
tr
ac
tio
n
m
eth
o
d
s
till
m
ea
s
u
r
es
th
e
s
im
ilar
ity
o
f
an
id
en
tifie
d
ter
m
to
th
e
to
k
en
o
f
a
s
en
ten
ce
.
W
e
h
av
e
n
o
t
test
ed
th
is
ap
p
r
o
ac
h
f
o
r
m
u
ltip
le
h
o
m
o
n
y
m
an
d
p
o
ly
s
em
y
ter
m
s
in
a
s
en
ten
ce
.
T
h
en
,
t
h
e
MT
r
esu
lts
in
d
eter
m
in
in
g
th
e
v
er
b
f
o
r
m
s
o
f
t
h
e
t
ar
g
et
s
en
ten
ce
ar
e
s
till
d
if
f
er
en
t
f
r
o
m
th
e
ac
tu
al
r
esu
lt
th
at
th
e
ex
p
e
r
t
d
eter
m
in
es.
Fo
r
ex
am
p
le,
in
th
e
in
p
u
t
s
en
ten
ce
1
A
y
a
h
mem
b
eli
p
a
lu
,
th
e
ex
p
er
t
d
e
ter
m
in
es
th
e
r
esu
lt
is
F
a
th
er
b
u
ys
a
h
a
mme
r
,
wh
ile
th
e
p
r
o
p
o
s
ed
m
eth
o
d
d
eter
m
in
es
th
e
r
esu
lt
is
F
a
th
e
r
b
o
u
g
h
t
a
h
a
mme
r
.
T
h
e
v
e
r
b
mem
b
eli
as
th
e
in
p
u
t
is
s
till
t
r
an
s
lated
to
b
o
u
g
h
t
b
y
th
e
p
r
o
p
o
s
ed
m
eth
o
d
an
d
is
n
o
t th
e
s
am
e
as th
e
tr
a
n
s
lated
r
esu
lt b
y
th
e
e
x
p
er
t,
n
am
ely
b
u
ys
.
T
h
e
d
if
f
er
e
n
tiatio
n
o
cc
u
r
s
b
ec
au
s
e
th
e
ex
p
er
t
d
ef
in
es
th
e
v
e
r
b
f
o
r
m
b
ased
o
n
th
e
ex
is
tin
g
ad
v
er
b
o
f
tim
e
in
th
e
s
en
ten
ce
.
I
f
th
e
s
e
n
ten
ce
d
o
es
n
o
t
c
o
n
tain
a
n
y
a
d
v
er
b
o
f
tim
e
,
th
en
th
e
e
x
p
er
t
lab
els
th
e
s
en
ten
ce
as
th
e
p
r
esen
t
ten
s
e,
wh
ich
h
as
th
e
v
er
b
i
n
th
e
f
ir
s
t
f
o
r
m
.
Me
an
wh
ile,
th
e
p
r
o
p
o
s
ed
m
eth
o
d
an
d
Go
o
g
le
T
r
an
s
lato
r
d
ef
in
e
th
e
s
en
te
n
ce
with
o
u
t
an
ad
v
e
r
b
o
f
tim
e,
wh
ich
m
i
g
h
t
b
e
p
r
esen
t
te
n
s
e
o
r
p
ast
ten
s
e
b
ec
au
s
e
o
f
th
e
d
ef
a
u
lt
ass
u
m
p
tio
n
s
m
ad
e
b
y
th
e
m
o
d
el.
I
n
t
h
is
r
esear
ch
,
th
e
d
if
f
er
en
tiatio
n
o
f
tr
a
n
s
latio
n
r
esu
lts
b
etwe
en
d
o
in
g
b
y
ex
p
er
t
an
d
d
o
in
g
b
y
th
e
p
r
o
p
o
s
ed
m
eth
o
d
f
o
r
d
eter
m
i
n
in
g
th
e
v
er
b
f
o
r
m
in
t
h
e
tar
g
et
lan
g
u
ag
e
b
ased
o
n
th
e
in
p
u
t sen
ten
ce
with
o
u
t th
e
ad
v
er
b
o
f
tim
e
is
ass
es
s
ed
as r
ea
s
o
n
ab
le
an
d
h
as tr
u
e
v
alu
e.
4
.
3
.
E
v
a
lua
t
io
n r
esu
lt
T
h
e
co
m
p
a
r
is
o
n
o
f
ev
alu
atio
n
r
esu
lts
is
s
h
o
wn
in
T
ab
le
9
.
T
ab
le
9
s
h
o
ws
th
e
p
r
o
p
o
s
ed
MT
m
eth
o
d
ca
n
p
er
f
o
r
m
b
etter
t
h
an
th
e
p
r
ev
io
u
s
m
eth
o
d
s
.
T
h
e
p
r
o
p
o
s
ed
wo
r
d
f
ea
tu
r
e
ex
tr
ac
tio
n
u
s
in
g
h
o
m
o
n
y
m
a
n
d
p
o
ly
s
em
y
a
p
p
r
o
ac
h
with
m
o
r
p
h
o
lo
g
y
ex
tr
ac
tio
n
d
ete
r
m
in
es
g
o
o
d
p
e
r
f
o
r
m
an
ce
to
in
cr
ea
s
e
NM
T
p
er
f
o
r
m
an
ce
.
T
h
e
ev
alu
atio
n
r
esu
lts
ar
e
0
.
8
3
5
7
f
o
r
p
r
ec
is
io
n
,
0
.
7
8
6
2
f
o
r
r
ec
all,
0
.
8
1
0
2
f
o
r
th
e
F
-
1
m
ea
s
u
r
e,
an
d
0
.
8
0
9
8
f
o
r
ac
cu
r
ac
y
.
T
ab
le
9
.
C
o
m
p
a
r
is
o
n
r
esu
lts
o
f
m
ac
h
in
e
tr
a
n
s
latio
n
p
er
f
o
r
m
an
ce
s
M
e
t
h
o
d
La
n
g
u
a
g
e
t
r
a
n
sl
a
t
i
o
n
P
R
F
A
N
M
T
[
9
]
I
n
d
o
n
e
si
a
n
t
o
En
g
l
i
s
h
0
.
7
2
9
2
0
.
6
5
3
9
0
.
6
8
9
5
0
.
7
0
7
5
H
y
b
r
i
d
R
B
M
T
a
n
d
S
M
T
[
3
]
0
.
7
2
3
1
0
.
7
0
0
0
0
.
7
1
1
4
0
.
7
4
1
7
N
M
T
w
i
t
h
h
o
m
o
n
y
m a
n
d
p
o
l
y
sem
y
e
x
t
r
a
c
t
i
o
n
[
1
2
]
0
.
7
7
9
1
0
.
8
4
2
8
0
.
8
0
9
7
0
.
7
9
7
5
P
r
o
p
o
se
d
m
e
t
h
o
d
0
.
8
3
5
7
0
.
7
8
6
2
0
.
8
1
0
2
0
.
8
0
9
8
T
h
e
NM
T
m
eth
o
d
[
9
]
,
with
an
ac
cu
r
ac
y
s
co
r
e
o
f
0
.
7
0
7
5
,
h
as
b
ee
n
d
ev
elo
p
ed
u
s
in
g
th
e
NM
T
m
eth
o
d
with
h
o
m
o
n
y
m
a
n
d
p
o
ly
s
em
y
ex
tr
ac
tio
n
[
1
2
]
.
T
h
e
ac
cu
r
ac
y
s
co
r
e
o
f
th
e
NM
T
m
eth
o
d
with
h
o
m
o
n
y
m
an
d
p
o
ly
s
em
y
ex
tr
ac
tio
n
[
1
2
]
is
0
.
7
9
7
5
an
d
is
b
etter
th
an
th
e
ac
cu
r
ac
y
s
co
r
e
r
esu
lt
o
f
th
e
NM
T
m
eth
o
d
[
9
]
.
Me
a
n
wh
ile,
th
e
r
esu
lts
o
f
o
th
er
m
eth
o
d
s
u
s
in
g
h
y
b
r
i
d
R
B
MT
an
d
SMT
[
3
]
co
u
ld
s
till
g
et
an
ac
cu
r
ac
y
s
co
r
e
o
f
0
.
7
4
1
7
.
T
h
e
ac
cu
r
ac
y
s
co
r
e
r
esu
lt
o
f
t
h
e
p
r
o
p
o
s
ed
m
et
h
o
d
o
f
0
.
8
0
9
8
s
h
o
ws
th
at
th
is
p
r
o
p
o
s
ed
m
eth
o
d
is
b
etter
th
a
n
th
e
p
r
ev
io
u
s
m
eth
o
d
s
[
3
]
,
[
9
]
,
[
1
2
]
in
tr
a
n
s
latin
g
I
n
d
o
n
e
s
ian
s
en
ten
ce
s
th
at
co
n
tain
m
o
r
p
h
o
l
o
g
ical
f
ea
tu
r
e
s
in
th
e
h
o
m
o
n
y
m
an
d
p
o
l
y
s
em
y
f
ea
tu
r
es.
Ho
wev
e
r
,
th
e
p
r
o
p
o
s
ed
MT
m
eth
o
d
s
till
wo
r
k
s
o
n
o
n
e
-
way
tr
a
n
s
latio
n
f
r
o
m
I
n
d
o
n
esian
to
E
n
g
li
s
h
an
d
h
as
n
o
t
wo
r
k
ed
o
n
th
e
r
ev
er
s
e
tr
an
s
latio
n
f
r
o
m
E
n
g
lis
h
to
I
n
d
o
n
esian
f
o
r
a
s
im
ilar
ca
s
e.
Ap
ar
t
f
r
o
m
th
at,
th
er
e
ar
e
s
till
f
alse
p
o
s
itiv
es
f
o
r
tr
an
s
latio
n
r
esu
lts
f
r
o
m
in
p
u
t
s
en
ten
ce
s
co
n
tain
in
g
th
e
s
am
e
ter
m
s
b
u
t
with
d
if
f
er
en
t
co
n
tex
ts
.
Fo
r
ex
am
p
le,
in
t
h
e
s
en
ten
ce
Dia
mem
b
eli
p
a
lu
d
i
p
a
lu
,
wh
er
e
th
e
r
esu
lt
o
f
th
e
p
r
o
p
o
s
ed
m
eth
o
d
is
wr
o
n
g
,
He
w
en
t
to
b
u
y
a
h
a
mme
r
o
n
a
h
a
mme
r
.
Ov
er
all,
th
e
p
er
f
o
r
m
a
n
ce
o
f
th
e
p
r
o
p
o
s
ed
m
eth
o
d
h
as
s
h
o
wn
s
ig
n
if
ican
t
r
esu
lts
in
t
r
an
s
latin
g
I
n
d
o
n
esian
s
en
ten
ce
s
in
t
o
E
n
g
lis
h
.
I
d
en
tif
y
in
g
h
o
m
o
n
y
m
a
n
d
p
o
ly
s
em
y
f
ea
tu
r
es
i
n
I
n
d
o
n
e
s
ian
,
wh
eth
er
th
ey
co
n
tain
m
o
r
p
h
o
lo
g
ical
f
ea
tu
r
e
s
o
r
n
o
t,
is
im
p
o
r
tan
t
in
th
e
wo
r
d
em
b
ed
d
in
g
s
tag
e
in
m
a
ch
in
e
tr
an
s
latio
n
s
o
th
at
it
ca
n
in
cr
ea
s
e
tr
an
s
latio
n
ac
cu
r
ac
y
.
Dev
elo
p
m
en
t
o
f
th
e
MT
m
eth
o
d
is
s
till
n
ee
d
ed
to
tr
an
s
late
s
en
ten
ce
s
th
at
co
n
tain
th
e
s
am
e
two
ter
m
s
b
u
t
h
av
e
d
if
f
e
r
en
t
m
ea
n
in
g
s
.
Mo
r
eo
v
er
,
th
e
s
en
ten
ce
s
s
till
lab
eled
as
f
alse
p
o
s
itiv
e
an
d
f
alse n
e
g
ativ
e
n
ee
d
to
b
e
a
n
aly
ze
d
.
So
,
f
u
r
th
er
MT
m
eth
o
d
d
ev
elo
p
m
en
t c
an
wo
r
k
b
etter
.
5.
CO
NCLU
SI
O
N
W
e
p
r
o
p
o
s
e
h
o
m
o
n
y
m
an
d
p
o
ly
s
em
y
ap
p
r
o
ac
h
es
with
m
o
r
p
h
o
lo
g
y
e
x
tr
ac
tio
n
in
weig
h
tin
g
ter
m
s
f
o
r
I
n
d
o
n
esian
to
E
n
g
lis
h
MT
.
T
h
e
p
r
o
p
o
s
ed
m
o
r
p
h
o
lo
g
y
e
x
tr
ac
tio
n
u
s
es
m
o
r
p
h
o
lo
g
y
alter
n
atio
n
s
ch
em
es
th
at
ca
n
ad
eq
u
ately
d
etec
t
ter
m
s
o
f
p
r
e
f
ix
es
an
d
s
u
f
f
ix
es.
T
h
e
m
o
r
p
h
o
lo
g
y
ex
tr
ac
ti
o
n
r
esu
lt
is
u
s
ed
as
in
p
u
t
f
o
r
wo
r
d
f
ea
tu
r
e
ex
tr
ac
tio
n
u
s
in
g
m
etap
h
o
r
co
r
p
u
s
,
e
n
tity
co
r
p
u
s
,
B
E
R
T
em
b
ed
d
in
g
,
s
y
n
o
n
y
m
-
b
ased
e
x
p
an
s
io
n
,
an
d
Sem
an
tic
s
im
ilar
ity
,
wh
ic
h
ca
n
ex
tr
ac
t
p
r
o
p
er
ter
m
s
an
d
d
if
f
er
en
t
s
y
n
o
n
y
m
s
to
g
et
m
o
r
e
ac
c
u
r
ate
ter
m
s
b
ased
o
n
th
e
co
n
tex
t
o
f
ea
c
h
s
en
ten
ce
.
T
h
e
wo
r
d
f
ea
t
u
r
e
ex
tr
ac
tio
n
r
esu
lt
ca
n
d
etec
t
th
e
h
o
m
o
n
y
m
a
n
d
p
o
ly
s
em
y
ter
m
s
in
th
e
f
o
r
m
o
f
wo
r
d
s
an
d
p
h
r
ases
with
m
o
r
p
h
o
lo
g
y
f
ea
tu
r
es,
wh
ich
ca
n
h
av
e
m
u
ltip
le
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
14
,
No
.
6
,
Dec
em
b
e
r
20
24
:
7
0
3
6
-
7
0
4
5
7044
m
ea
n
in
g
s
,
d
e
n
o
tatio
n
,
an
d
co
n
n
o
tatio
n
m
ea
n
in
g
s
.
T
h
e
w
o
r
d
f
ea
tu
r
e
ex
tr
ac
tio
n
r
esu
lt
is
t
h
en
u
s
ed
as
in
p
u
t
f
o
r
m
ac
h
in
e
tr
a
n
s
latio
n
.
Fin
ally
,
th
e
p
r
o
p
o
s
ed
m
ac
h
i
n
e
tr
an
s
latio
n
u
s
in
g
NM
T
ca
n
co
r
r
ec
tly
tr
an
s
late
th
e
s
en
ten
ce
s
th
at
co
n
tai
n
h
o
m
o
n
y
m
an
d
p
o
ly
s
em
y
f
ea
tu
r
es
u
s
in
g
u
p
d
ated
s
en
ten
ce
s
f
r
o
m
th
e
p
r
o
p
o
s
ed
wo
r
d
ex
tr
ac
tio
n
r
esu
lts
.
T
h
e
ev
alu
a
tio
n
r
esu
lts
wer
e
b
etter
th
an
th
e
p
r
ev
io
u
s
m
eth
o
d
s
,
with
v
a
lu
es
o
f
0
.
8
3
5
7
f
o
r
p
r
ec
is
io
n
,
0
.
7
8
6
2
f
o
r
r
ec
all,
0
.
8
1
0
2
f
o
r
F
1
-
m
ea
s
u
r
e
,
a
n
d
0
.
8
0
9
8
f
o
r
ac
cu
r
ac
y
.
Fo
r
f
u
t
u
r
e
r
esear
c
h
,
t
h
is
p
r
o
p
o
s
ed
m
eth
o
d
n
ee
d
s
to
b
e
d
ev
elo
p
ed
to
s
o
lv
e
th
e
o
th
er
p
r
o
b
lem
s
in
I
n
d
o
n
esian
to
E
n
g
lis
h
tr
an
s
latio
n
,
s
u
ch
as
h
o
w
to
d
eter
m
in
e
th
e
p
r
ec
is
e
tr
an
s
latio
n
o
f
th
e
E
n
g
l
is
h
tar
g
et
v
er
b
b
ased
o
n
th
e
ad
v
er
b
o
f
tim
e
th
at
is
co
n
tain
ed
in
th
e
s
en
ten
ce
,
h
o
w
to
tr
an
s
late
two
s
im
ilar
ter
m
s
in
a
s
en
ten
ce
th
at
h
as
d
if
f
er
en
t
m
ea
n
in
g
s
,
a
n
d
th
e
o
th
er
I
n
d
o
n
esian
s
en
ten
ce
f
ea
tu
r
es.
W
e
also
h
o
p
e
th
ese
r
esear
ch
r
esu
lts
ca
n
s
u
p
p
o
r
t
m
ac
h
in
e
tr
an
s
latio
n
d
ev
elo
p
m
e
n
t f
r
o
m
E
n
g
lis
h
to
I
n
d
o
n
esian
tr
a
n
s
latio
n
o
r
t
h
e
I
n
d
o
n
esian
lan
g
u
ag
e
with
a
n
o
th
er
lan
g
u
a
g
e.
ACK
NO
WL
E
DG
E
M
E
NT
S
T
h
is
r
esear
ch
is
s
u
p
p
o
r
ted
b
y
Un
iv
er
s
itas
Dian
Nu
s
wan
to
r
o
an
d
t
h
e
Dir
ec
to
r
ate
o
f
R
esear
ch
an
d
C
o
m
m
u
n
ity
Ser
v
ice,
Dir
ec
to
r
ate
Gen
er
al
o
f
R
esear
ch
an
d
Dev
elo
p
m
e
n
t
Stre
n
g
th
e
n
in
g
o
f
th
e
Min
is
tr
y
o
f
R
esear
ch
,
T
ec
h
n
o
lo
g
y
an
d
Hi
g
h
er
E
d
u
ca
tio
n
o
f
th
e
R
ep
u
b
li
c
o
f
I
n
d
o
n
esia.
RE
F
E
R
E
NC
E
S
[
1
]
F
.
R
a
h
u
t
o
mo
,
A
.
A
.
S
e
p
t
a
r
i
n
a
,
M
.
S
a
r
o
sa,
A
.
S
e
t
i
a
w
a
n
,
a
n
d
M
.
M
.
H
u
d
a
,
“
A
r
e
v
i
e
w
o
n
I
n
d
o
n
e
si
a
n
ma
c
h
i
n
e
t
r
a
n
sl
a
t
i
o
n
,
”
i
n
4
t
h
An
n
u
a
l
A
p
p
l
i
e
d
S
c
i
e
n
c
e
a
n
d
E
n
g
i
n
e
e
r
i
n
g
C
o
n
f
e
re
n
c
e
,
2
0
1
9
,
p
p
.
1
–
6
,
d
o
i
:
1
0
.
1
0
8
8
/
1
7
4
2
-
6
5
9
6
/
1
4
0
2
/
7
/
0
7
7
0
4
0
.
[
2
]
I
.
R
i
v
e
r
a
-
t
r
i
g
u
e
r
o
s,
“
M
a
c
h
i
n
e
t
r
a
n
sl
a
t
i
o
n
s
y
st
e
ms
a
n
d
q
u
a
l
i
t
y
a
ssessm
e
n
t
:
a
s
y
st
e
ma
t
i
c
r
e
v
i
e
w
,
”
L
a
n
g
u
a
g
e
Re
s
o
u
rce
s
a
n
d
Ev
a
l
u
a
t
i
o
n
,
v
o
l
.
5
6
,
n
o
.
2
,
p
p
.
5
9
3
–
6
1
9
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
0
5
7
9
-
0
2
1
-
0
9
5
3
7
-
5.
[
3
]
M
.
Y
a
m
i
n
,
“
S
y
n
t
a
x
i
s
-
b
a
se
d
e
x
t
r
a
c
t
i
o
n
m
e
t
h
o
d
w
i
t
h
t
y
p
e
a
n
d
f
u
n
c
t
i
o
n
o
f
w
o
r
d
d
e
t
e
c
t
i
o
n
a
p
p
r
o
a
c
h
f
o
r
m
a
c
h
i
n
e
t
r
a
n
s
l
a
t
i
o
n
o
f
I
n
d
o
n
e
si
a
n
-
To
l
a
k
i
a
n
d
E
n
g
l
i
s
h
se
n
t
e
n
c
e
s,”
i
n
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
I
n
f
o
rm
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
Re
se
a
r
c
h
a
n
d
I
n
n
o
v
a
t
i
o
n
(
I
C
I
T
RI
)
,
2
0
2
2
,
p
p
.
1
0
1
–
1
0
6
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
I
TR
I
5
6
4
2
3
.
2
0
2
2
.
9
9
7
0
2
2
5
.
[
4
]
W
.
Jo
o
st
e
,
R
.
H
a
q
u
e
,
a
n
d
A
.
W
a
y
,
“
P
h
i
l
i
p
p
K
o
e
h
n
:
n
e
u
r
a
l
mac
h
i
n
e
t
r
a
n
s
l
a
t
i
o
n
,
”
Ma
c
h
i
n
e
T
ra
n
s
l
a
t
i
o
n
,
v
o
l
.
3
5
,
n
o
.
2
,
p
p
.
2
8
9
–
2
9
9
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
0
5
9
0
-
0
2
1
-
0
9
2
7
7
-
x.
[
5
]
F
.
S
t
a
h
l
b
e
r
g
,
“
N
e
u
r
a
l
m
a
c
h
i
n
e
t
r
a
n
s
l
a
t
i
o
n
:
A
r
e
v
i
e
w
,
”
J
o
u
rn
a
l
o
f
Ar
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
R
e
se
a
rc
h
,
v
o
l
.
6
9
,
p
p
.
3
4
3
–
4
1
8
,
2
0
2
0
,
d
o
i
:
1
0
.
1
6
1
3
/
JA
I
R
.
1
.
1
2
0
0
7
.
[
6
]
M
.
G
r
o
v
e
s
a
n
d
K
.
M
u
n
d
t
,
“
F
r
i
e
n
d
o
r
f
o
e
?
G
o
o
g
l
e
t
r
a
n
s
l
a
t
e
i
n
l
a
n
g
u
a
g
e
f
o
r
a
c
a
d
e
mi
c
p
u
r
p
o
ses
,
”
E
n
g
l
i
s
h
f
o
r
S
p
e
c
i
f
i
c
Pu
r
p
o
ses
,
v
o
l
.
3
7
,
p
p
.
1
1
2
–
1
2
1
,
2
0
1
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
s
p
.
2
0
1
4
.
0
9
.
0
0
1
.
[
7
]
S
.
C
.
Tsa
i
,
“
U
s
i
n
g
g
o
o
g
l
e
t
r
a
n
s
l
a
t
e
i
n
EFL
d
r
a
f
t
s:
a
p
r
e
l
i
mi
n
a
r
y
i
n
v
e
s
t
i
g
a
t
i
o
n
,
”
C
o
m
p
u
t
e
r
Assi
st
e
d
L
a
n
g
u
a
g
e
L
e
a
r
n
i
n
g
,
v
o
l
.
3
2
,
n
o
.
5
–
6
,
p
p
.
5
1
0
–
5
2
6
,
J
u
l
.
2
0
1
9
,
d
o
i
:
1
0
.
1
0
8
0
/
0
9
5
8
8
2
2
1
.
2
0
1
8
.
1
5
2
7
3
6
1
.
[
8
]
S
.
M
a
l
l
a
n
d
U
.
C
.
Ja
i
sw
a
l
,
“
S
h
a
l
l
o
w
p
a
r
si
n
g
a
n
d
w
o
r
d
se
n
se
d
i
sam
b
i
g
u
a
t
i
o
n
u
s
e
d
f
o
r
mac
h
i
n
e
t
r
a
n
s
l
a
t
i
o
n
f
r
o
m
H
i
n
d
i
t
o
En
g
l
i
s
h
l
a
n
g
u
a
g
e
s
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
I
n
t
e
l
l
i
g
e
n
t
E
n
g
i
n
e
e
r
i
n
g
a
n
d
S
y
st
e
m
s
,
v
o
l
.
1
0
,
n
o
.
3
,
p
p
.
3
8
1
–
3
9
0
,
2
0
1
7
,
d
o
i
:
1
0
.
2
2
2
6
6
/
i
j
i
e
s
2
0
1
7
.
0
6
3
0
.
4
3
.
[
9
]
M
.
D
w
i
a
st
u
t
i
,
“
En
g
l
i
s
h
-
I
n
d
o
n
e
s
i
a
n
n
e
u
r
a
l
m
a
c
h
i
n
e
t
r
a
n
sl
a
t
i
o
n
f
o
r
s
p
o
k
e
n
l
a
n
g
u
a
g
e
d
o
m
a
i
n
s,
”
i
n
Pro
c
e
e
d
i
n
g
s
o
f
t
h
e
5
7
t
h
A
n
n
u
a
l
Me
e
t
i
n
g
o
f
t
h
e
A
sso
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
t
u
d
e
n
t
R
e
se
a
rc
h
W
o
rks
h
o
p
,
2
0
1
9
,
p
p
.
3
0
9
–
3
1
4
,
d
o
i
:
1
0
.
1
8
6
5
3
/
v
1
/
P
1
9
-
2
0
4
3
.
[
1
0
]
A
.
E
k
a
,
P
.
L
e
st
a
r
i
,
A
.
A
r
d
i
y
a
n
t
i
,
a
n
d
I
.
A
sr
o
r
,
“
P
h
r
a
se
b
a
se
d
s
t
a
t
i
s
t
i
c
a
l
m
a
c
h
i
n
e
t
r
a
n
sl
a
t
i
o
n
Ja
v
a
n
e
s
e
-
I
n
d
o
n
e
si
a
n
,
”
J
u
r
n
a
l
Me
d
i
a
I
n
f
o
rm
a
t
i
k
a
Bu
d
i
d
a
rm
a
,
v
o
l
.
5
,
n
o
.
2
,
p
p
.
3
7
8
–
3
8
6
,
2
0
2
1
,
d
o
i
:
1
0
.
3
0
8
6
5
/
mi
b
.
v
5
i
2
.
2
8
1
2
.
[
1
1
]
Z.
A
b
i
d
i
n
,
P
e
r
m
a
t
a
,
a
n
d
F
.
A
r
i
y
a
n
i
,
“
Tr
a
n
s
l
a
t
i
o
n
o
f
t
h
e
L
a
m
p
u
n
g
l
a
n
g
u
a
g
e
t
e
x
t
d
i
a
l
e
c
t
o
f
N
y
o
i
n
t
o
t
h
e
I
n
d
o
n
e
si
a
n
l
a
n
g
u
a
g
e
w
i
t
h
D
M
T
a
n
d
S
M
T
a
p
p
r
o
a
c
h
,
”
I
N
T
EN
S
I
F
,
v
o
l
.
5
,
n
o
.
1
,
p
p
.
5
8
–
7
1
,
2
0
2
1
,
d
o
i
:
1
0
.
2
9
4
0
7
/
i
n
t
e
n
s
i
f
.
v
5
i
1
.
1
4
6
7
0
.
[
1
2
]
R
.
A
b
d
u
l
l
a
h
,
R
.
S
a
r
n
o
,
D
.
P
u
r
w
i
t
a
s
a
r
i
,
A
.
I
.
A
k
h
s
a
n
i
,
a
n
d
S
u
h
a
r
i
y
a
n
t
o
,
“
H
o
mo
n
y
m
a
n
d
p
o
l
y
sem
y
a
p
p
r
o
a
c
h
e
s
i
n
t
e
r
m
w
e
i
g
h
t
i
n
g
f
o
r
I
n
d
o
n
e
si
a
n
-
E
n
g
l
i
sh
m
a
c
h
i
n
e
t
r
a
n
sl
a
t
i
o
n
,
”
i
n
2
0
2
3
1
4
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
I
n
f
o
rm
a
t
i
o
n
a
n
d
C
o
m
m
u
n
i
c
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
a
n
d
S
y
st
e
m
,
I
C
T
S
2
0
2
3
,
2
0
2
3
,
p
p
.
2
3
2
–
2
3
7
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
TS
5
8
7
7
0
.
2
0
2
3
.
1
0
3
3
0
8
7
5
.
[
1
3
]
S
.
S
k
o
u
f
a
k
i
a
n
d
B
.
P
e
t
r
i
ć
,
“
Ex
p
l
o
r
i
n
g
p
o
l
y
se
my
i
n
t
h
e
a
c
a
d
e
mi
c
v
o
c
a
b
u
l
a
r
y
l
i
st
:
a
l
e
x
i
c
o
g
r
a
p
h
i
c
a
p
p
r
o
a
c
h
,
”
J
o
u
r
n
a
l
o
f
E
n
g
l
i
sh
f
o
r
Ac
a
d
e
m
i
c
P
u
r
p
o
s
e
s
,
v
o
l
.
5
4
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
e
a
p
.
2
0
2
1
.
1
0
1
0
3
8
.
[
1
4
]
S
.
Li
,
R
.
P
a
n
,
H
.
L
u
o
,
X
.
Li
u
,
a
n
d
G
.
Z
h
a
o
,
“
A
d
a
p
t
i
v
e
c
r
o
ss
-
c
o
n
t
e
x
t
u
a
l
w
o
r
d
e
m
b
e
d
d
i
n
g
f
o
r
w
o
r
d
p
o
l
y
s
e
my
w
i
t
h
u
n
s
u
p
e
r
v
i
s
e
d
t
o
p
i
c
m
o
d
e
l
i
n
g
,
”
K
n
o
w
l
e
d
g
e
-
B
a
se
d
S
y
st
e
m
s
,
v
o
l
.
2
1
8
,
2
0
2
1
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
k
n
o
s
y
s.
2
0
2
1
.
1
0
6
8
2
7
.
[
1
5
]
B
.
C
a
sa
s,
A
.
H
e
r
n
á
n
d
e
z
-
F
e
r
n
á
n
d
e
z
,
N
.
C
a
t
a
l
à
,
R
.
F
e
r
r
e
r
-
i
-
C
a
n
c
h
o
,
a
n
d
J.
B
a
i
x
e
r
i
e
s
,
“
P
o
l
y
s
e
my
a
n
d
b
r
e
v
i
t
y
v
e
r
su
s
f
r
e
q
u
e
n
c
y
i
n
l
a
n
g
u
a
g
e
,
”
C
o
m
p
u
t
e
r
S
p
e
e
c
h
a
n
d
L
a
n
g
u
a
g
e
,
v
o
l
.
5
8
,
p
p
.
1
9
–
5
0
,
2
0
1
9
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
s
l
.
2
0
1
9
.
0
3
.
0
0
7
.
[
1
6
]
S
.
D
.
L
a
r
a
sa
t
i
,
V
.
K
u
b
o
ň
,
a
n
d
D
.
Z
e
ma
n
,
“
I
n
d
o
n
e
s
i
a
n
m
o
r
p
h
o
l
o
g
y
t
o
o
l
(
M
o
r
p
h
I
n
d
)
:
t
o
w
a
r
d
s
a
n
I
n
d
o
n
e
si
a
n
c
o
r
p
u
s
,
”
C
o
m
m
u
n
i
c
a
t
i
o
n
s
i
n
C
o
m
p
u
t
e
r
a
n
d
I
n
f
o
rm
a
t
i
o
n
S
c
i
e
n
c
e
,
2
0
1
1
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
3
-
6
4
2
-
2
3
1
3
8
-
4
_
8
.
[
1
7
]
F
.
R
a
h
u
t
o
m
o
,
R
.
A
.
A
sm
a
r
a
,
a
n
d
D
.
K
.
P
.
A
j
i
,
“
C
o
m
p
u
t
a
t
i
o
n
a
l
a
n
a
l
y
si
s
o
n
r
i
se
a
n
d
f
a
l
l
o
f
I
n
d
o
n
e
s
i
a
n
v
o
c
a
b
u
l
a
r
y
d
u
r
i
n
g
a
p
e
r
i
o
d
o
f
t
i
me
,
”
i
n
2
0
1
8
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
I
n
f
o
rm
a
t
i
o
n
a
n
d
C
o
m
m
u
n
i
c
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
,
N
o
v
.
2
0
1
8
,
p
p
.
7
5
–
8
0
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
O
I
C
T.
2
0
1
8
.
8
5
2
8
8
1
2
.
[
1
8
]
C
.
S
u
n
e
t
a
l
.
,
“
A
d
e
e
p
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
w
i
t
h
d
e
e
p
c
o
n
t
e
x
t
u
a
l
i
z
e
d
w
o
r
d
r
e
p
r
e
se
n
t
a
t
i
o
n
s
f
o
r
c
h
e
mi
c
a
l
-
p
r
o
t
e
i
n
i
n
t
e
r
a
c
t
i
o
n
e
x
t
r
a
c
t
i
o
n
f
r
o
m
b
i
o
m
e
d
i
c
a
l
l
i
t
e
r
a
t
u
r
e
,
”
I
EEE
Ac
c
e
ss
,
v
o
l
.
7
,
p
p
.
1
5
1
0
3
4
–
1
5
1
0
4
6
,
2
0
1
9
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
1
9
.
2
9
4
8
1
5
5
.
[
1
9
]
J.
D
e
v
l
i
n
,
M
.
W
.
C
h
a
n
g
,
K
.
Le
e
,
a
n
d
K
.
To
u
t
a
n
o
v
a
,
“
B
ER
T
:
p
r
e
-
t
r
a
i
n
i
n
g
o
f
d
e
e
p
b
i
d
i
r
e
c
t
i
o
n
a
l
t
r
a
n
sf
o
r
me
r
s
f
o
r
l
a
n
g
u
a
g
e
u
n
d
e
r
s
t
a
n
d
i
n
g
,
”
N
AA
C
L
H
L
T
2
0
1
9
-
2
0
1
9
C
o
n
f
e
re
n
c
e
o
f
t
h
e
N
o
r
t
h
Am
e
ri
c
a
n
C
h
a
p
t
e
r
o
f
t
h
e
Ass
o
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
st
i
c
s:
H
u
m
a
n
L
a
n
g
u
a
g
e
T
e
c
h
n
o
l
o
g
i
e
s
-
Pr
o
c
e
e
d
i
n
g
s
o
f
t
h
e
C
o
n
f
e
re
n
c
e
,
v
o
l
.
1
,
p
p
.
4
1
7
1
–
4
1
8
6
,
O
c
t
.
2
0
1
9
.
[
2
0
]
N
.
R
e
d
d
y
,
P
.
S
i
n
g
h
,
a
n
d
M
.
M
.
S
r
i
v
a
st
a
v
a
,
“
D
o
e
s
B
ER
T
u
n
d
e
r
s
t
a
n
d
se
n
t
i
men
t
?
l
e
v
e
r
a
g
i
n
g
c
o
m
p
a
r
i
s
o
n
s
b
e
t
w
e
e
n
c
o
n
t
e
x
t
u
a
l
a
n
d
n
o
n
-
c
o
n
t
e
x
t
u
a
l
e
m
b
e
d
d
i
n
g
s
t
o
i
mp
r
o
v
e
a
s
p
e
c
t
-
b
a
se
d
se
n
t
i
me
n
t
mo
d
e
l
s,
”
a
r
Xi
v
p
r
e
p
r
i
n
t
a
rX
i
v
:
2
0
1
1
.
1
1
6
7
3
,
2
0
2
0
.
[
2
1
]
M
.
O
.
I
b
r
o
h
i
m
a
n
d
I
.
B
u
d
i
,
“
M
u
l
t
i
-
l
a
b
e
l
h
a
t
e
s
p
e
e
c
h
a
n
d
a
b
u
s
i
v
e
l
a
n
g
u
a
g
e
d
e
t
e
c
t
i
o
n
i
n
I
n
d
o
n
e
s
i
a
n
Tw
i
t
t
e
r
,
”
i
n
P
ro
c
e
e
d
i
n
g
s
o
f
t
h
e
t
h
i
rd
w
o
rks
h
o
p
o
n
a
b
u
s
i
v
e
l
a
n
g
u
a
g
e
o
n
l
i
n
e
,
2
0
1
9
,
p
p
.
4
6
–
5
7
,
d
o
i
:
1
0
.
1
8
6
5
3
/
v
1
/
w
1
9
-
3
5
0
6
.
[
2
2
]
I
.
A
l
f
i
n
a
,
R
.
M
u
l
i
a
,
M
.
I
.
F
a
n
a
n
y
,
a
n
d
Y
.
Ek
a
n
a
t
a
,
“
H
a
t
e
s
p
e
e
c
h
d
e
t
e
c
t
i
o
n
i
n
t
h
e
I
n
d
o
n
e
s
i
a
n
l
a
n
g
u
a
g
e
:
A
d
a
t
a
s
e
t
a
n
d
p
r
e
l
i
mi
n
a
r
y
st
u
d
y
,
”
2
0
1
7
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
A
d
v
a
n
c
e
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
I
n
f
o
rm
a
t
i
o
n
S
y
st
e
m
s,
I
C
AC
S
I
S
2
0
1
7
,
p
p
.
2
3
3
–
2
3
8
,
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
Ho
mo
n
ym
a
n
d
p
o
lysemy
a
p
p
r
o
a
ch
es w
ith
mo
r
p
h
o
lo
g
y
ex
tr
a
ctio
n
in
…
(
B
u
d
i H
a
r
jo
)
7045
2
0
1
7
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
A
C
S
I
S
.
2
0
1
7
.
8
3
5
5
0
3
9
.
[
2
3
]
I
.
G
h
o
z
a
l
i
,
K
.
R
.
S
u
n
g
k
o
n
o
,
R
.
S
a
r
n
o
,
a
n
d
R
.
A
b
d
u
l
l
a
h
,
“
S
y
n
o
n
y
m
b
a
s
e
d
f
e
a
t
u
r
e
e
x
p
a
n
si
o
n
f
o
r
I
n
d
o
n
e
si
a
n
h
a
t
e
s
p
e
e
c
h
d
e
t
e
c
t
i
o
n
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
E
l
e
c
t
r
i
c
a
l
a
n
d
C
o
m
p
u
t
e
r
E
n
g
i
n
e
e
ri
n
g
,
v
o
l
.
1
3
,
n
o
.
1
,
p
p
.
1
1
0
5
–
1
1
1
2
,
F
e
b
.
2
0
2
3
,
d
o
i
:
1
0
.
1
1
5
9
1
/
i
j
e
c
e
.
v
1
3
i
1
.
p
p
1
1
0
5
-
1
1
1
2
.
[
2
4
]
P
.
X
i
a
,
L.
Zh
a
n
g
,
a
n
d
F
.
L
i
,
“
Le
a
r
n
i
n
g
si
m
i
l
a
r
i
t
y
w
i
t
h
c
o
si
n
e
si
m
i
l
a
r
i
t
y
e
n
sem
b
l
e
,
”
I
n
f
o
rm
a
t
i
o
n
S
c
i
e
n
c
e
s
,
v
o
l
.
3
0
7
,
p
p
.
3
9
–
5
2
,
2
0
1
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
n
s.
2
0
1
5
.
0
2
.
0
2
4
.
[
2
5
]
B
.
H
a
r
j
o
,
M
u
l
j
o
n
o
,
a
n
d
R
.
A
b
d
u
l
l
a
h
,
“
A
t
t
e
n
t
i
o
n
-
b
a
se
d
s
e
n
t
e
n
c
e
e
x
t
r
a
c
t
i
o
n
f
o
r
a
s
p
e
c
t
-
b
a
se
d
s
e
n
t
i
m
e
n
t
a
n
a
l
y
si
s
w
i
t
h
i
m
p
l
i
c
i
t
a
sp
e
c
t
c
a
s
e
s
i
n
h
o
t
e
l
r
e
v
i
e
w
u
si
n
g
mac
h
i
n
e
l
e
a
r
n
i
n
g
a
l
g
o
r
i
t
h
m,
s
e
ma
n
t
i
c
si
m
i
l
a
r
i
t
y
,
a
n
d
B
ER
T
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
I
n
t
e
l
l
i
g
e
n
t
En
g
i
n
e
e
ri
n
g
a
n
d
S
y
st
e
m
s
,
v
o
l
.
1
6
,
n
o
.
3
,
p
p
.
1
8
9
–
2
0
0
,
2
0
2
3
,
d
o
i
:
1
0
.
2
2
2
6
6
/
i
j
i
e
s2
0
2
3
.
0
6
3
0
.
1
5
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Bu
d
i
H
a
r
jo
re
c
e
iv
e
d
th
e
Do
c
to
r
(P
h
.
D.)
d
e
g
re
e
in
in
f
o
rm
a
ti
c
s
e
n
g
in
e
e
rin
g
fro
m
th
e
De
p
a
rtme
n
t
o
f
In
f
o
rm
a
ti
c
s,
F
a
c
u
lt
y
o
f
I
n
telli
g
e
n
t
E
lec
tri
c
a
l
a
n
d
I
n
fo
rm
a
ti
c
s
Tec
h
n
o
lo
g
y
,
In
stit
u
t
Tek
n
o
l
o
g
i
S
e
p
u
lu
h
No
p
e
m
b
e
r
(IT
S
)
.
He
is
a
lec
tu
re
r
a
t
th
e
F
a
c
u
lt
y
o
f
Co
m
p
u
ter
S
c
ien
c
e
,
Dia
n
Nu
sw
a
n
t
o
ro
Un
i
v
e
rsity
,
S
e
m
a
ra
n
g
.
His
re
se
a
rc
h
i
n
c
lu
d
e
s
a
rti
f
icia
l
i
n
telli
g
e
n
c
e
,
m
a
c
h
in
e
lea
rn
in
g
,
d
a
ta
m
in
in
g
,
d
a
ta
sc
ien
c
e
,
c
o
m
p
u
tatio
n
a
l
l
in
g
u
isti
c
s,
a
n
d
n
a
tu
ra
l
lan
g
u
a
g
e
p
ro
c
e
ss
in
g
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
b
u
d
i.
h
a
rjo
@d
s
n
.
d
in
u
s.a
c
.
id
.
Mu
ljo
n
o
h
o
ld
s
a
Do
c
to
r
o
f
E
l
e
c
tri
c
a
l
En
g
in
e
e
rin
g
d
e
g
re
e
fro
m
In
stit
u
t
Te
k
n
o
lo
g
i
S
e
p
u
l
u
h
No
p
e
m
b
e
r
(IT
S
),
S
u
ra
b
a
y
a
,
In
d
o
n
e
sia
in
2
0
1
6
.
He
jo
i
n
e
d
a
n
In
tern
sh
i
p
P
r
o
g
ra
m
a
t
th
e
S
c
h
o
o
l
o
f
M
e
d
ia
S
c
ien
c
e
,
T
o
k
y
o
Un
i
v
e
rsity
o
f
Tec
h
n
o
lo
g
y
Ja
p
a
n
in
2
0
1
4
.
He
re
c
e
iv
e
d
h
is
M
a
g
ister
o
f
Co
m
p
u
ter
(In
f
o
rm
a
ti
c
s)
fro
m
S
TT
IBI
Ja
k
a
rta,
In
d
o
n
e
sia
in
2
0
0
1
,
a
n
d
h
e
re
c
e
iv
e
d
h
is
B.
S
c
(M
a
t
h
e
m
a
ti
c
s)
fro
m
U
n
iv
e
rsitas
Di
p
o
n
e
g
o
r
o
(UN
DIP)
in
1
9
9
6
.
He
is
c
u
rre
n
tl
y
a
n
a
ss
o
c
iate
p
ro
fe
ss
o
r
a
t
th
e
F
a
c
u
lt
y
o
f
C
o
m
p
u
ter
S
c
ien
c
e
a
t
Di
a
n
Nu
sw
a
n
t
o
ro
Un
i
v
e
rsity
,
S
e
m
a
ra
n
g
,
In
d
o
n
e
sia
.
His
re
se
a
rc
h
in
c
l
u
d
e
s
a
rti
f
icia
l
in
telli
g
e
n
c
e
,
m
a
c
h
in
e
lea
rn
in
g
,
d
a
t
a
m
in
in
g
,
d
a
ta
sc
ien
c
e
,
c
o
m
p
u
tati
o
n
a
l
li
n
g
u
isti
c
s,
a
n
d
n
a
t
u
ra
l
lan
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
:
m
u
lj
o
n
o
@d
s
n
.
d
in
u
s.a
c
.
id
.
Ra
c
h
m
a
d
Abd
u
ll
a
h
re
c
e
iv
e
d
th
e
M
.
M
T.
d
e
g
re
e
in
i
n
fo
r
m
a
ti
o
n
tec
h
n
o
l
o
g
y
m
a
n
a
g
e
m
e
n
t
fro
m
I
n
stit
u
t
Tek
n
o
lo
g
i
S
e
p
u
lu
h
N
o
p
e
m
b
e
r
(IT
S
).
He
is
c
u
rre
n
tl
y
p
u
rsu
i
n
g
a
P
h
.
D.
d
e
g
re
e
in
in
fo
rm
a
ti
c
s
e
n
g
in
e
e
rin
g
fr
o
m
t
h
e
De
p
a
rtme
n
t
o
f
In
f
o
rm
a
ti
c
s,
F
a
c
u
lt
y
o
f
In
telli
g
e
n
t
El
e
c
tri
c
a
l
a
n
d
In
f
o
rm
a
ti
c
s T
e
c
h
n
o
lo
g
y
,
In
stit
u
t
Tek
n
o
l
o
g
i
S
e
p
u
lu
h
No
p
e
m
b
e
r
(IT
S
)
.
His
re
se
a
rc
h
in
tere
sts
i
n
c
lu
d
e
d
a
t
a
sc
ien
c
e
,
a
rti
ficia
l
i
n
telli
g
e
n
c
e
,
n
a
tu
ra
l
lan
g
u
a
g
e
p
ro
c
e
ss
in
g
,
fo
c
u
sin
g
te
x
t
m
in
in
g
,
se
n
ti
m
e
n
t
a
n
a
ly
sis,
m
a
c
h
in
e
lea
rn
i
n
g
,
a
n
d
th
e
in
ter
n
e
t
o
f
th
i
n
g
s
(Io
T)
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
ra
b
d
u
ll
a
h
1
5
0
6
@
g
m
a
il
.
c
o
m.
Evaluation Warning : The document was created with Spire.PDF for Python.