I
nte
rna
t
io
na
l J
o
urna
l o
f
I
nfo
rm
a
t
ics a
nd
Co
m
m
un
ica
t
io
n T
ec
hn
o
lo
g
y
(
I
J
-
I
CT
)
Vo
l.
15
,
No
.
3
,
Sep
tem
b
er
20
26
,
p
p
.
1
3
4
0
~
1
3
5
1
I
SS
N:
2252
-
8
7
7
6
,
DOI
:
1
0
.
1
1
5
9
1
/iji
ct
.
v15
i
3
.
pp
1
3
4
0
-
1
3
5
1
1340
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ict.
ia
esco
r
e.
co
m
Ev
a
lua
tion o
f
text
correction
using
a
com
bina
tion o
f
Lev
enshtein d
ista
nce
a
nd
Tri
e
a
lg
o
rithm
Cy
nthia
Na
t
a
lie
,
Abba
Su
g
a
nd
a
G
irsa
ng
D
e
p
a
r
t
me
n
t
o
f
C
o
mp
u
t
e
r
S
c
i
e
n
c
e
,
B
I
N
U
S
G
r
a
d
u
a
t
e
P
r
o
g
r
a
m
M
a
st
e
r
o
f
C
o
mp
u
t
e
r
S
c
i
e
n
c
e
,
B
i
n
a
N
u
sa
n
t
a
r
a
U
n
i
v
e
r
si
t
y
,
W
e
s
t
Ja
k
a
r
t
a
,
I
n
d
o
n
e
s
i
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
u
l 1
0
,
2
0
2
4
R
ev
is
ed
J
u
n
2
4
,
2
0
2
6
Acc
ep
ted
J
u
l 5
,
2
0
2
6
No
wa
d
a
y
s,
tec
h
n
o
l
o
g
y
is
a
d
v
a
n
c
in
g
with
v
a
ri
o
u
s
a
p
p
li
c
a
ti
o
n
s,
e
sp
e
c
ially
i
n
tex
t
p
ro
c
e
ss
in
g
,
su
c
h
a
s
n
e
w
s
re
c
o
m
m
e
n
d
a
ti
o
n
s,
se
n
ti
m
e
n
t
a
n
a
ly
sis,
a
u
to
m
a
ti
c
sc
o
rin
g
,
a
n
d
lan
g
u
a
g
e
tran
sla
ti
o
n
.
In
so
m
e
c
a
se
s,
sp
e
ll
in
g
e
rro
rs
o
ften
o
c
c
u
r
wh
e
n
in
p
u
t
ti
n
g
tex
t
f
o
r
th
e
tran
sla
ti
o
n
p
r
o
c
e
ss
,
n
e
c
e
ss
it
a
ti
n
g
tex
t
c
o
rre
c
ti
o
n
m
e
th
o
d
s
to
d
isp
lay
s
u
g
g
e
stio
n
s
a
s
a
re
su
lt
.
Th
e
re
fo
re
,
th
e
p
ro
b
lem
sta
tem
e
n
t
ra
ise
d
is
a
b
o
u
t
h
o
w
t
o
i
m
p
ro
v
e
t
h
e
a
c
c
u
ra
c
y
o
f
tex
t
c
o
rre
c
ti
o
n
a
n
d
e
v
a
lu
a
te
th
e
tran
sla
ti
o
n
q
u
a
li
t
y
a
t
th
e
wo
rd
lev
e
l
a
fter
c
o
rre
c
ti
n
g
in
p
u
t
te
x
t
i
n
th
e
c
o
n
tex
t
o
f
tran
sla
ti
o
n
fro
m
I
n
d
o
n
e
sia
n
to
En
g
li
sh
.
T
h
is
re
se
a
rc
h
a
ims
to
d
e
v
e
lo
p
a
n
d
e
v
a
l
u
a
te
th
e
c
o
m
b
i
n
a
ti
o
n
o
f
Lev
e
n
sh
tein
d
istan
c
e
a
lg
o
rit
h
m
a
n
d
Tri
e
to
c
o
rre
c
t
in
p
u
t
te
x
t
a
n
d
e
v
a
lu
a
te
th
e
tran
sla
ti
o
n
q
u
a
li
t
y
a
t
th
e
wo
rd
lev
e
l
a
fter
c
o
rre
c
ti
n
g
tex
t.
T
h
e
re
a
re
v
a
rio
u
s
tex
t
c
o
rre
c
ti
o
n
m
e
th
o
d
s,
su
c
h
a
s
Ha
m
m
in
g
d
istan
c
e
,
Lev
e
n
sh
tei
n
d
istan
c
e
,
Da
m
e
ra
u
-
Lev
e
n
sh
tein
d
istan
c
e
,
a
n
d
N
-
G
ra
m
.
A
m
o
n
g
se
v
e
ra
l
tex
t
c
o
rre
c
ti
o
n
m
e
th
o
d
s.
Lev
e
n
sh
tei
n
d
istan
c
e
a
lg
o
rit
h
m
is
c
o
m
m
o
n
l
y
u
se
d
to
c
a
lcu
late
th
e
d
istan
c
e
b
e
twe
e
n
tex
ts
a
n
d
c
a
n
b
e
e
n
h
a
n
c
e
d
b
y
u
sin
g
a
Tr
ie
fo
r
m
o
re
e
fficie
n
t
c
o
m
p
u
tati
o
n
i
n
e
v
a
lu
a
ti
n
g
tex
t
c
o
rre
c
ti
o
n
.
T
h
is
re
se
a
rc
h
m
e
t
h
o
d
re
su
lt
e
d
i
n
a
n
a
c
c
u
ra
c
y
o
f
8
2
.
2
5
%
wit
h
a
n
F
1
sc
o
re
o
f
8
4
.
3
9
%
,
wh
e
re
th
e
d
e
v
e
lo
p
e
d
tex
t
c
o
rre
c
ti
o
n
m
o
d
e
l
p
ro
d
u
c
e
d
a
g
o
o
d
tra
n
sla
ti
o
n
u
si
n
g
BLE
U
sc
o
re
with
a
n
in
c
re
a
se
o
f
1
.
5
5
%
a
fter
tex
t
c
o
rre
c
ti
o
n
.
K
ey
w
o
r
d
s
:
C
h
atGPT
Go
o
g
le
tr
an
s
late
L
ev
en
s
h
tein
d
is
tan
ce
T
ex
t c
o
r
r
ec
tio
n
T
r
ie
alg
o
r
ith
m
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
:
Ab
b
a
Su
g
an
d
a
Gir
s
an
g
Dep
ar
tm
en
t o
f
C
o
m
p
u
ter
Scie
n
ce
,
B
I
NUS
Gr
ad
u
ate
Pro
g
r
a
m
Ma
s
ter
o
f
C
o
m
p
u
te
r
Scien
c
e
B
in
a
Nu
s
an
tar
a
Un
iv
er
s
ity
Stre
et
K.
H.
Sy
ah
d
an
9
,
Kem
a
n
g
g
is
an
,
Palm
er
ah
,
W
est J
ak
ar
ta
,
I
n
d
o
n
esia
E
m
ail:
ag
ir
s
an
g
@
b
in
u
s
.
ed
u
1.
I
NT
RO
D
UCT
I
O
N
Fo
r
eig
n
lan
g
u
ag
e
tr
an
s
latio
n
i
s
th
e
in
ter
p
r
etatio
n
o
f
tex
t
f
r
o
m
th
e
n
ativ
e
lan
g
u
a
g
e,
r
esu
ltin
g
in
a
tex
t
th
at
co
n
v
e
y
s
a
s
im
ilar
m
ess
ag
e
[
1
]
.
W
ith
th
e
ad
v
a
n
ce
m
en
t
o
f
tech
n
o
lo
g
y
,
f
o
r
eig
n
la
n
g
u
ag
e
tr
an
s
latio
n
ca
n
n
o
w
b
e
lear
n
e
d
an
d
p
er
f
o
r
m
ed
u
s
in
g
ap
p
licatio
n
s
,
o
n
e
o
f
wh
ich
is
Go
o
g
le
T
r
an
s
late
[
2
]
.
I
n
s
o
m
e
ca
s
es,
s
p
e
l
li
n
g
e
r
r
o
r
s
o
f
te
n
o
c
c
u
r
w
h
e
n
i
n
p
u
t
t
i
n
g
t
e
x
t
f
o
r
t
h
e
t
r
a
n
s
l
at
i
o
n
p
r
o
c
e
s
s
,
n
e
c
ess
i
t
at
i
n
g
te
x
t
c
o
r
r
e
c
t
i
o
n
m
et
h
o
d
s
t
o
d
i
s
p
l
a
y
s
u
g
g
e
s
ti
o
n
s
as
a
r
e
s
u
l
t
o
f
i
n
p
u
t
t
e
x
t
c
o
r
r
e
ct
i
o
n
t
o
h
e
lp
u
s
e
r
s
o
b
t
a
i
n
o
p
ti
m
a
l
t
r
a
n
s
l
at
io
n
r
e
s
u
l
t
s
.
Var
io
u
s
m
eth
o
d
s
h
av
e
b
ee
n
p
r
o
p
o
s
ed
to
h
an
d
le
tex
t
c
o
r
r
e
ctio
n
p
r
o
b
lem
s
[
3
]
-
[
5
]
,
s
u
ch
as
N
-
Gr
am
an
d
L
e
v
en
s
h
tein
d
is
tan
ce
[
6
]
,
wh
ich
ca
n
p
r
o
v
id
e
g
o
o
d
r
esu
lts
,
b
u
t
th
ese
m
eth
o
d
s
o
f
ten
d
is
p
lay
to
o
m
an
y
s
u
g
g
esti
o
n
s
.
Me
an
wh
ile,
th
e
r
esear
ch
o
n
L
ev
en
s
h
tein
d
i
s
tan
ce
an
d
C
o
s
in
e
Similar
ity
h
as
n
o
t
p
r
o
v
id
e
d
ap
p
r
o
p
r
iate
s
u
g
g
esti
o
n
s
d
u
e
t
o
th
e
lack
o
f
w
o
r
d
g
r
o
u
p
in
g
.
E
d
it
Dis
tan
ce
an
d
B
E
R
T
-
b
ased
m
ask
lan
g
u
ag
e
m
o
d
el
m
eth
o
d
s
also
n
ee
d
to
b
e
d
ev
elo
p
e
d
f
o
r
te
x
t
co
r
r
ec
ti
o
n
b
ased
o
n
e
x
is
tin
g
co
n
tex
ts
[
7
]
.
T
h
er
e
f
o
r
e,
th
e
p
r
o
b
lem
s
tatem
en
t
r
aised
is
ab
o
u
t
h
o
w
to
im
p
r
o
v
e
th
e
ac
cu
r
a
cy
o
f
tex
t
co
r
r
ec
tio
n
an
d
ev
al
u
ate
th
e
tr
a
n
s
latio
n
q
u
ality
at
th
e
wo
r
d
lev
el
af
te
r
co
r
r
ec
tin
g
i
n
p
u
t te
x
t i
n
th
e
co
n
tex
t o
f
tr
a
n
s
latio
n
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 I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
I
SS
N:
2252
-
8
7
7
6
E
va
lu
a
tio
n
o
f te
xt
co
r
r
ec
tio
n
u
s
in
g
a
co
mb
in
a
tio
n
o
f
L
ev
en
s
h
tein
d
is
ta
n
ce
a
n
d
Tr
ie
… (
C
yn
th
ia
N
a
ta
lie
)
1341
Pre
v
io
u
s
r
esear
ch
co
n
d
u
cted
b
y
Yo
u
n
ess
C
h
aa
b
i
an
d
h
is
co
ll
ea
g
u
es,
ap
p
l
y
in
g
Dam
er
au
-
L
e
v
en
s
h
tein
alg
o
r
ith
m
an
d
N
-
g
r
am
h
as
h
a
n
d
led
s
p
ellin
g
er
r
o
r
s
in
Am
az
ig
h
lan
g
u
a
g
e,
h
o
wev
er
,
th
is
c
o
m
b
in
atio
n
c
o
r
r
ec
ts
o
n
ly
s
p
ellin
g
e
r
r
o
r
s
[
6
]
.
I
n
c
o
n
tr
ast,
Vin
y
C
h
r
is
tan
ti
M
an
d
h
er
team
'
s
s
tu
d
y
s
u
cc
ess
f
u
lly
h
an
d
le
d
s
p
ellin
g
er
r
o
r
s
u
s
in
g
T
r
ie
an
d
Dam
er
au
-
L
ev
en
s
h
tein
d
is
tan
ce
B
ig
r
am
.
Ho
wev
er
,
th
is
ap
p
r
o
ac
h
r
eq
u
ir
es
s
u
b
s
tan
tial
m
em
o
r
y
u
s
ag
e
f
o
r
wo
r
d
co
r
r
ec
tio
n
[
8
]
.
Mo
r
e
o
v
er
,
R
o
m
ila
Aziz
an
d
team
h
as
im
p
lem
en
ted
Dam
er
au
-
L
ev
e
n
s
h
tein
d
is
tan
c
e
T
r
ig
r
am
in
c
o
r
r
ec
tin
g
co
n
te
x
t
er
r
o
r
s
,
s
till
th
is
r
esear
ch
ca
n
b
e
en
h
a
n
ce
d
to
d
etec
t
an
d
co
r
r
ec
t
m
u
ltip
le
co
n
te
x
tu
al
er
r
o
r
s
in
a
s
in
g
l
e
s
en
ten
ce
[
9
]
.
Oth
er
r
esea
r
ch
r
elate
d
to
th
e
co
m
b
in
atio
n
o
f
L
ev
e
n
s
h
tein
d
is
tan
ce
an
d
R
ab
in
-
Kar
p
alg
o
r
ith
m
s
co
n
d
u
cted
b
y
An
d
r
e
Hasu
d
u
n
g
an
L
u
b
is
an
d
team
,
s
u
cc
ee
d
ed
in
s
h
o
win
g
th
at
th
e
c
o
m
b
in
ati
o
n
o
f
th
e
t
wo
alg
o
r
ith
m
s
p
er
f
o
r
m
s
g
o
o
d
a
cc
u
r
ac
y
an
d
its
ap
p
licatio
n
ca
n
b
e
im
p
r
o
v
e
d
b
ased
o
n
ce
r
tain
p
ar
am
et
er
s
,
s
u
ch
as
N
-
Gr
a
m
,
B
ase
an
d
Mo
d
u
lo
[
1
0
]
.
Similar
ly
,
Aaq
ila
Dh
iy
aa
n
is
af
a
Go
en
awa
n
ap
p
lied
T
r
ie
an
d
d
ep
th
-
f
ir
s
t
s
ea
r
c
h
alg
o
r
ith
m
s
t
o
im
p
lem
e
n
t
s
ea
r
ch
s
u
g
g
esti
o
n
s
,
y
et
th
is
r
esear
ch
'
s
lim
i
tatio
n
lies
in
its
in
ab
ilit
y
to
d
is
p
lay
f
r
eq
u
en
tly
u
s
er
-
in
p
u
tted
wo
r
d
r
ec
o
m
m
en
d
atio
n
s
[
1
1
]
.
An
o
t
h
er
s
tu
d
y
b
y
Kav
ita
T
.
Patil
an
d
co
lleag
u
es
co
r
r
ec
te
d
Ma
r
ath
i
wo
r
d
s
u
s
in
g
co
m
b
in
atio
n
s
o
f
L
ev
e
n
s
h
tein
d
is
tan
ce
an
d
C
o
s
in
e
Similar
it
y
.
Ho
wev
er
,
wo
r
d
s
u
g
g
esti
o
n
s
in
Ma
r
ath
i
d
id
n
o
t
y
ield
p
r
ec
is
e
r
esu
lts
d
u
e
to
u
n
g
r
o
u
p
ed
wo
r
d
s
in
th
e
v
o
ca
b
u
lar
y
s
et
[
1
2
]
.
B
ased
o
n
p
r
e
v
io
u
s
r
esear
ch
,
s
ev
er
al
is
s
u
es
s
u
ch
as
ex
ce
s
s
iv
e
an
d
u
n
g
r
o
u
p
ed
wo
r
d
co
r
r
ec
tio
n
r
esu
lts
,
im
p
r
ec
is
e
wo
r
d
s
u
g
g
esti
o
n
s
,
an
d
h
ig
h
m
em
o
r
y
u
s
ag
e
r
eq
u
ir
e
f
u
r
t
h
er
ev
al
u
atio
n
.
E
n
h
a
n
cin
g
L
ev
en
s
h
tein
d
is
tan
ce
an
d
T
r
ie
alg
o
r
ith
m
c
o
u
ld
lead
to
m
o
r
e
ef
f
icien
t
te
x
t
co
r
r
ec
tio
n
ev
alu
atio
n
s
[
1
3
]
.
T
r
ie
d
ata
s
tr
u
ctu
r
es
ca
n
b
e
s
to
r
ed
f
o
r
tex
t
p
r
o
ce
s
s
in
g
,
r
ed
u
cin
g
m
em
o
r
y
u
s
a
g
e
in
g
r
o
u
p
in
g
tex
ts
b
ased
o
n
s
im
ilar
p
r
ef
ix
es,
co
m
b
in
ed
with
L
ev
en
s
h
tein
d
is
tan
ce
alg
o
r
ith
m
to
ca
lcu
la
te
th
e
d
is
tan
ce
b
etwe
en
tex
ts
.
T
h
is
c
o
m
b
in
atio
n
o
f
f
er
s
an
ex
ce
llen
t
b
alan
ce
b
e
twee
n
s
p
ee
d
an
d
ac
cu
r
ac
y
.
T
h
e
ap
p
licatio
n
o
f
T
r
ie
allo
ws
f
o
r
f
ast
an
d
ef
f
icien
t
s
im
ilar
p
r
ef
ix
s
ea
r
ch
es
[
1
4
]
,
wh
i
le
L
ev
en
s
h
tein
d
is
tan
ce
alg
o
r
ith
m
p
r
o
v
id
es
h
ig
h
ac
cu
r
a
cy
in
d
etec
tin
g
an
d
co
r
r
ec
tin
g
s
p
ellin
g
er
r
o
r
s
an
d
is
n
o
t
af
f
ec
ted
b
y
th
e
len
g
th
o
f
th
e
tex
t.
T
h
e
co
n
tr
i
b
u
tio
n
s
o
f
o
u
r
w
o
r
k
in
clu
d
e
th
e
f
o
llo
win
g
item
s
:
-
I
n
tr
o
d
u
ce
th
e
c
o
m
b
in
atio
n
o
f
L
ev
en
s
h
tein
d
is
tan
ce
an
d
T
r
ie
alg
o
r
ith
m
f
o
r
tex
t c
o
r
r
ec
tio
n
p
u
r
p
o
s
e.
-
E
v
alu
ate
th
e
co
m
b
in
atio
n
o
f
L
ev
e
n
s
h
tein
d
is
tan
ce
an
d
T
r
ie
alg
o
r
ith
m
u
s
in
g
C
o
n
f
u
s
io
n
Ma
tr
ix
,
AUC
-
R
O
C
C
u
r
v
e
an
d
B
L
E
U
Sco
r
e
m
ea
s
u
r
em
en
t.
T
h
is
p
ap
er
is
s
tr
u
ctu
r
ed
as
f
o
l
lo
ws:
1
.
I
n
tr
o
d
u
ctio
n
,
2
.
T
h
e
Pro
p
o
s
e
d
Me
th
o
d
3
.
Me
th
o
d
,
4
.
R
esu
lt
s
an
d
Dis
cu
s
s
io
n
,
an
d
5
.
C
o
n
cl
u
s
io
n
.
Sectio
n
1
i
n
tr
o
d
u
ce
s
th
e
p
r
o
p
o
s
ed
ap
p
r
o
ac
h
.
Sectio
n
2
d
escr
ib
es
r
elate
d
wo
r
k
d
o
n
e
i
n
th
is
ar
ea
.
Sectio
n
3
d
escr
ib
es
r
esear
ch
m
eth
o
d
.
Sectio
n
4
d
escr
ib
es
th
e
r
es
u
lts
o
f
th
e
p
r
o
p
o
s
ed
ap
p
r
o
ac
h
f
o
llo
we
d
b
y
d
is
cu
s
s
io
n
,
an
d
s
ec
tio
n
5
c
o
n
clu
d
es th
e
p
ap
er
.
2.
T
H
E
P
RO
P
O
SE
D
M
E
T
H
O
D
Var
io
u
s
r
esear
ch
es
h
av
e
b
ee
n
co
n
d
u
cted
in
th
e
co
n
tex
t
o
f
tex
t
co
r
r
ec
tio
n
u
s
in
g
co
m
b
in
at
io
n
s
o
f
th
e
L
ev
en
s
h
tein
d
is
tan
ce
Alg
o
r
ith
m
.
R
esear
ch
o
n
th
e
co
m
b
i
n
atio
n
o
f
Dam
er
au
L
e
v
en
s
h
tein
d
is
tan
ce
an
d
N
-
Gr
am
was
co
n
d
u
cted
b
y
Y
o
u
n
ess
C
h
aa
b
i
a
n
d
h
is
co
llea
g
u
es
[
6
]
to
id
en
tif
y
s
p
ellin
g
er
r
o
r
s
in
Am
az
ig
h
co
r
p
u
s
lan
g
u
ag
e.
T
h
e
N
-
Gr
a
m
m
eth
o
d
was
u
s
ed
to
m
ea
s
u
r
e
d
f
o
r
r
an
d
o
m
s
p
ellin
g
er
r
o
r
s
f
r
o
m
th
e
d
ictio
n
ar
y
.
T
h
e
r
esu
lts
s
h
o
wed
th
e
ac
h
ie
v
ed
F
-
m
ea
s
u
r
e
v
alu
e
r
an
g
ed
f
r
o
m
8
6
.
6
2
% to
9
8
.
7
4
%
.
Oth
er
r
esear
ch
o
n
th
e
co
m
b
in
atio
n
o
f
ed
it d
is
tan
ce
alg
o
r
ith
m
s
was
co
n
d
u
cted
b
y
Vin
y
C
h
r
is
tan
ti
an
d
team
[
8
]
b
y
co
m
b
i
n
in
g
Da
m
er
au
-
L
ev
e
n
s
h
tein
d
is
tan
ce
with
T
r
ie
in
th
e
co
n
tex
t
o
f
s
p
ell
ch
ec
k
in
g
.
T
h
e
s
tu
d
y
s
h
o
we
d
a
wo
r
d
co
r
r
ec
tio
n
ac
cu
r
ac
y
o
f
8
4
.
6
2
%
a
n
d
a
s
en
ten
ce
c
o
r
r
ec
tio
n
ac
cu
r
ac
y
o
f
5
0
%,
with
a
p
r
o
ce
s
s
in
g
tim
e
p
er
s
en
ten
ce
o
f
1
8
.
8
9
m
s
.
Fu
r
th
er
m
o
r
e,
t
h
e
r
esear
ch
o
n
th
e
co
m
b
i
n
atio
n
o
f
L
ev
en
s
h
tein
d
is
tan
ce
an
d
R
ab
in
-
Kar
p
alg
o
r
ith
m
s
was
co
n
d
u
cted
b
y
An
d
r
e
Hasu
d
u
n
g
an
L
u
b
is
a
n
d
team
[
1
0
]
t
o
im
p
r
o
v
e
th
e
ac
cu
r
ac
y
o
f
d
o
c
u
m
en
t
s
im
ilar
ity
.
T
h
e
R
ab
in
-
Kar
p
alg
o
r
i
th
m
is
a
s
ea
r
ch
alg
o
r
ith
m
th
at
lo
o
k
s
f
o
r
s
u
b
s
tr
in
g
p
atter
n
s
in
tex
t
u
s
in
g
h
ash
in
g
,
ty
p
ically
u
s
ed
to
m
atch
tex
t
with
v
ar
io
u
s
p
atter
n
s
.
I
n
th
is
s
tu
d
y
,
L
ev
en
s
h
tein
d
is
tan
ce
r
ep
lace
d
th
e
h
ash
ca
l
cu
latio
n
in
th
e
R
ab
in
-
Kar
p
al
g
o
r
ith
m
b
y
ca
lcu
latin
g
th
e
n
u
m
b
er
o
f
h
ash
es
with
th
e
s
am
e
v
alu
e
in
b
o
th
d
o
c
u
m
en
ts
.
B
y
ad
d
in
g
th
e
L
ev
en
s
h
tein
d
is
tan
ce
alg
o
r
ith
m
,
th
e
d
is
tan
ce
ca
lcu
latio
n
b
etwe
en
th
e
two
d
o
cu
m
en
ts
r
esu
lted
in
b
etter
ac
cu
r
ac
y
.
T
h
e
s
tu
d
y
s
h
o
wed
th
at
th
e
co
m
b
in
atio
n
o
f
th
ese
two
alg
o
r
ith
m
s
p
r
o
d
u
c
ed
b
etter
ac
cu
r
ac
y
,
wh
ich
co
u
ld
b
e
f
u
r
th
e
r
im
p
r
o
v
e
d
b
ased
o
n
ce
r
tain
p
ar
am
eter
s
,
s
u
ch
as
N
-
Gr
am
,
B
ase,
an
d
Mo
d
u
lo
.
An
o
th
er
r
esear
ch
c
o
m
b
in
i
n
g
en
h
an
ce
d
N
-
g
r
am
a
n
d
L
e
v
en
s
h
tein
d
is
tan
ce
alg
o
r
ith
m
c
o
n
d
u
cted
b
y
Salah
Al
-
Hag
r
ee
a
n
d
h
is
tea
m
s
h
o
wed
s
im
ilar
ity
m
ea
n
o
f
0
.
9
0
an
d
F
-
m
ea
s
u
r
e
m
ea
n
o
f
0
.
9
1
in
n
am
e
m
atch
in
g
[
1
5
]
.
A
s
im
ilar
s
tu
d
y
o
n
th
e
au
to
c
o
m
p
lete
te
x
t
f
e
atu
r
e
in
an
I
n
d
o
n
esian
d
ictio
n
ar
y
c
o
n
d
u
cted
b
y
Go
en
awa
n
an
d
team
[
1
1
]
w
as
also
im
p
lem
en
ted
with
t
h
e
T
r
ie
a
n
d
d
ep
th
-
f
ir
s
t
s
ea
r
ch
alg
o
r
ith
m
.
T
h
is
co
m
b
in
ati
o
n
a
p
p
lied
to
s
h
o
r
te
n
th
e
u
s
er
'
s
ty
p
in
g
tim
e,
wh
er
e
th
is
f
ea
tu
r
e
wo
u
ld
d
is
p
lay
a
lis
t o
f
wo
r
d
s
th
at
th
e
u
s
er
m
ig
h
t
m
ea
n
with
o
u
t
h
a
v
in
g
to
ty
p
e
th
e
wo
r
d
c
o
m
p
l
etely
.
T
h
e
r
esu
lts
in
clu
d
ed
i
m
p
lem
en
tin
g
s
ea
r
ch
s
u
g
g
esti
o
n
s
b
ased
o
n
n
o
d
e
lo
c
atio
n
in
th
e
test
in
g
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
7
7
6
I
n
t J I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
,
Vo
l.
15
,
No
.
3
,
Sep
tem
b
er
20
26
:
1
3
4
0
-
1
3
5
1
1342
Similar
s
tu
d
y
was
c
o
n
d
u
cted
o
n
lan
g
u
ag
e
m
o
d
els
(
L
Ms)
b
y
ap
p
ly
in
g
a
s
im
ilar
alg
o
r
it
h
m
,
b
y
te
p
ai
r
en
co
d
in
g
(
B
PE)
,
to
ev
alu
ate
t
h
e
m
o
d
el
b
y
co
m
p
ar
in
g
th
e
i
m
p
lem
en
tatio
n
o
f
B
PE
to
k
e
n
i
za
tio
n
an
d
Un
ig
r
am
LM
to
k
en
izatio
n
[
1
6
]
.
T
h
e
e
x
p
er
im
en
tal
r
esu
lts
s
h
o
wed
t
h
a
t
th
e
a
d
ju
s
tm
en
t
m
o
d
el
tr
ain
e
d
with
U
n
ig
r
am
LM
to
k
en
izatio
n
p
er
f
o
r
m
ed
b
etter
th
an
t
h
e
ad
j
u
s
tm
en
t
m
o
d
el
tr
ain
ed
with
B
PE
to
k
e
n
izatio
n
.
T
h
is
s
tu
d
y
s
h
o
wed
th
at
alth
o
u
g
h
th
e
B
PE
alg
o
r
it
h
m
was
q
u
ite
u
s
ef
u
l
in
tr
an
s
la
tin
g
OOV
wo
r
d
s
i
n
th
e
d
ataset,
m
o
s
t
OOV
wo
r
d
s
wer
e
s
till
in
co
r
r
ec
tly
tr
an
s
lated
[1
7
]
.
R
esear
ch
co
m
b
in
in
g
th
e
E
d
it
Dis
tan
ce
alg
o
r
ith
m
was
a
g
ain
co
n
d
u
cte
d
b
y
Fatem
eh
T
o
h
id
i
an
[
7
]
with
a
B
E
R
T
-
b
ased
m
ask
ed
lan
g
u
ag
e
m
o
d
e
l
f
o
r
s
p
ell
co
r
r
ec
t
io
n
.
B
E
R
T
is
a
tr
an
s
f
o
r
m
e
r
-
b
ased
ar
ch
itectu
r
e
in
itially
tr
ain
ed
o
n
a
m
ask
e
d
l
an
g
u
ag
e
m
o
d
el
to
f
in
d
m
is
s
p
e
lled
wo
r
d
ca
n
d
id
ates
an
d
s
elec
t
th
e
b
est
ca
n
d
id
ate
b
ased
o
n
E
d
it
Dis
tan
ce
ca
lcu
latio
n
s
.
T
h
e
s
tu
d
y
s
h
o
wed
th
at
th
e
co
m
b
in
atio
n
o
f
m
ask
ed
lan
g
u
ag
e
m
o
d
el
an
d
E
d
it
Dis
tan
ce
r
esu
lted
in
a
r
ec
all
o
f
8
1
.
2
1
%
in
s
p
ell
co
r
r
ec
tio
n
o
b
tain
e
d
f
r
o
m
p
r
ed
i
ctio
n
r
an
k
in
g
an
d
co
m
b
in
in
g
ch
ar
ac
ter
-
lev
el
cr
iter
ia
(
ed
it
d
is
tan
ce
)
with
B
E
R
T
p
r
ed
ictio
n
s
co
r
es.
I
n
th
e
s
am
e
y
ea
r
,
a
co
m
p
ar
ativ
e
s
tu
d
y
was
co
n
d
u
cted
co
m
p
a
r
in
g
th
e
u
s
e
o
f
t
h
e
m
in
im
u
m
ed
it
d
is
tan
ce
alg
o
r
ith
m
with
C
o
s
in
e
Similar
ity
to
c
h
ec
k
an
d
co
r
r
e
ct
s
p
ellin
g
er
r
o
r
s
in
Ma
r
ath
i.
T
h
e
m
in
im
u
m
e
d
it
d
is
tan
ce
i
s
a
ch
ar
ac
ter
-
b
ased
ap
p
r
o
ac
h
,
wh
ile
C
o
s
in
e
s
im
ilar
ity
is
a
s
im
ilar
ity
a
p
p
r
o
ac
h
b
ased
o
n
ce
r
tain
te
r
m
s
.
T
h
e
s
tu
d
y
s
h
o
we
d
th
e
b
est
ac
cu
r
ac
y
o
f
8
5
.
8
8
% a
n
d
8
6
.
7
6
% with
th
e
u
s
e
o
f
m
in
im
u
m
e
d
it d
is
tan
ce
an
d
C
o
s
in
e
s
im
ilar
ity
[
1
2
]
.
T
h
e
latest
r
esear
ch
o
n
th
e
L
e
v
en
s
h
tein
d
is
tan
ce
alg
o
r
ith
m
co
m
b
in
ed
with
s
ev
er
al
s
tr
in
g
m
atch
in
g
alg
o
r
ith
m
s
,
s
u
ch
as
th
e
Gestalt
an
d
SweetCo
at
-
2
D
alg
o
r
ith
m
s
,
was
co
n
d
u
cted
to
f
in
d
c
o
m
p
ar
is
o
n
p
atter
n
s
o
f
th
e
two
s
tr
in
g
s
i
n
th
e
B
an
g
la
lan
g
u
a
g
e.
T
h
e
Gestalt
alg
o
r
it
h
m
d
eter
m
in
es
tex
t
d
ata
p
atte
r
n
s
u
s
in
g
m
ac
h
in
e
lear
n
in
g
an
d
ca
n
p
r
ed
ict
te
x
t
b
ased
o
n
th
ese
p
atter
n
s
u
s
in
g
th
e
SweetCo
at
-
2
D
m
o
d
el.
SweetCo
at
-
2
D
is
b
u
ilt
o
n
a
two
-
d
im
e
n
s
io
n
al
m
o
d
el,
wh
er
e
th
e
p
o
s
itio
n
o
f
a
p
o
in
t
ca
n
b
e
d
eter
m
in
ed
u
s
in
g
x
an
d
y
-
ax
is
v
al
u
es.
T
h
e
r
esu
lts
o
f
th
is
s
tu
d
y
s
h
o
wed
th
at
th
e
a
p
p
licatio
n
o
f
s
p
ellin
g
s
u
g
g
esti
o
n
s
was
s
u
cc
ess
f
u
lly
im
p
r
o
v
ed
b
y
9
2
.
4
0
4
%,
with
ac
c
u
r
ac
y
ca
lc
u
lated
b
ased
o
n
co
r
r
ec
t
s
p
el
lin
g
s
u
g
g
esti
o
n
s
in
th
e
B
an
g
la
lan
g
u
a
g
e
[
1
8
]
.
Her
ea
f
ter
in
th
e
s
am
e
y
ea
r
,
th
e
r
esear
ch
u
s
in
g
au
g
m
e
n
ted
Dam
er
au
-
L
ev
en
s
h
tein
d
i
s
tan
ce
s
u
c
ce
s
s
f
u
lly
d
ev
elo
p
e
d
b
y
N
u
r
zh
a
n
Mu
k
az
h
an
o
v
a
n
d
team
,
r
esu
lted
b
est
ac
cu
r
ac
y
o
f
9
2
.
8
%
in
Kaz
ak
h
tex
t
[
1
9
]
.
Su
m
m
ar
y
o
f
th
e
liter
atu
r
e
r
ev
i
ew
f
o
r
co
m
b
in
atio
n
o
f
L
e
v
en
s
h
tein
d
is
tan
ce
an
d
T
r
ie
p
r
esen
t
ed
in
T
ab
le
1
.
T
ab
le
1
.
R
elate
d
wo
r
k
o
f
c
o
m
b
in
atio
n
o
f
L
ev
e
n
s
h
tein
d
is
tan
ce
an
d
T
r
ie
al
g
o
r
ith
m
Y
e
a
r
M
e
t
h
o
d
s
La
n
g
u
a
g
e
D
a
t
a
s
e
t
R
e
s
u
l
t
2
0
1
8
[
8
]
Tr
i
e
a
n
d
d
a
mera
u
-
Le
v
e
n
s
h
t
e
i
n
d
i
st
a
n
c
e
b
i
g
r
a
m
I
n
d
o
n
e
si
a
n
K
o
mp
a
s New
s
A
c
c
u
r
a
c
y
8
4
.
6
2
Ti
me
1
8
.
8
9
ms
2
0
1
8
[
1
0
]
Le
v
e
n
s
h
t
e
i
n
d
i
st
a
n
c
e
a
n
d
r
a
b
i
n
k
a
r
p
En
g
l
i
sh
D
o
c
u
me
n
t
s
1
0
%
o
f
d
o
c
u
m
e
n
t
s
i
mi
l
a
r
i
t
y
2
0
1
9
[
1
5
]
N
-
g
r
a
m
a
n
d
L
e
v
e
n
sh
t
e
i
n
d
i
s
t
a
n
c
e
En
g
l
i
sh
,
P
o
r
t
u
g
e
se,
a
n
d
A
r
a
b
i
c
En
g
l
i
sh
,
P
o
r
t
u
g
e
se,
a
n
d
A
r
a
b
i
c
n
a
m
e
s
S
i
mi
l
a
r
i
t
y
me
a
n
0
.
9
0
F
-
M
e
a
s
u
r
e
mea
n
0
.
9
1
2
0
2
0
[
1
6
]
B
y
t
e
p
a
i
r
e
n
c
o
d
i
n
g
En
g
l
i
sh
-
J
a
p
a
n
e
se
W
i
k
i
p
e
d
i
a
M
o
d
e
l
t
r
a
i
n
e
d
w
i
t
h
U
n
i
g
r
a
m
LM
p
e
r
f
o
r
me
d
b
e
t
t
e
r
2
0
2
2
[
1
7
]
B
y
t
e
p
a
i
r
e
n
c
o
d
i
n
g
Ge
r
man
-
E
n
g
l
i
sh
,
R
u
ss
i
a
n
-
E
n
g
l
i
s
h
,
a
n
d
R
o
m
a
n
i
a
n
-
E
n
g
l
i
s
h
W
M
T
2
0
2
0
,
W
M
T
2
0
1
6
,
W
M
T
2
0
1
7
B
P
E
a
l
g
o
r
i
t
h
m w
a
s
q
u
i
t
e
u
sef
u
l
i
n
t
r
a
n
s
l
a
t
i
n
g
O
O
V
w
o
r
d
s
i
n
t
h
e
d
a
t
a
se
t
2
0
2
2
[
6
]
D
a
mera
u
L
e
v
e
n
s
h
t
e
i
n
d
i
s
t
a
n
c
e
a
n
d
N
-
g
r
a
m
A
maz
i
g
h
A
maz
i
g
h
c
o
r
p
u
s
F
-
mea
su
r
e
r
a
n
g
e
d
f
r
o
m
8
6
.
6
2
%
t
o
9
8
.
7
4
%
2
0
2
2
[
1
1
]
Tr
i
e
a
n
d
d
e
p
t
h
-
f
i
r
s
t
sea
r
c
h
I
n
d
o
n
e
si
a
n
I
n
d
o
n
e
si
a
n
D
i
c
t
i
o
n
a
r
y
I
mp
l
e
me
n
t
i
n
g
s
e
a
r
c
h
su
g
g
e
st
i
o
n
s
b
a
s
e
d
o
n
n
o
d
e
l
o
c
a
t
i
o
n
i
n
t
h
e
t
e
st
i
n
g
2
0
2
3
[
7
]
B
ER
T
-
b
a
se
d
ma
sk
e
d
l
a
n
g
u
a
g
e
mo
d
e
l
a
n
d
e
d
i
t
d
i
s
t
a
n
c
e
En
g
l
i
sh
N
e
u
s
p
e
l
l
d
a
t
a
s
e
t
R
e
c
a
l
l
8
1
.
2
1
%
2
0
2
3
[
1
2
]
M
i
n
i
m
u
m
e
d
i
t
d
i
s
t
a
n
c
e
a
n
d
c
o
s
i
n
e
s
i
mi
l
a
r
i
t
y
M
a
r
a
t
h
i
M
a
r
a
t
h
i
d
o
c
u
me
n
t
s
M
ED
a
c
c
u
r
a
c
y
8
5
.
8
8
%
C
o
s
i
n
e
a
c
c
u
r
a
c
y
8
6
.
7
6
%
2
0
2
3
[
1
8
]
Le
v
e
n
s
h
t
e
i
n
e
d
i
t
d
i
s
t
a
n
c
e
a
n
d
s
t
r
i
n
g
-
m
a
t
c
h
i
n
g
a
l
g
o
r
i
t
h
m
B
e
n
g
a
l
i
B
e
n
g
a
l
i
d
o
c
u
me
n
t
s
A
c
c
u
r
a
c
y
9
2
.
4
0
4
%
2
0
2
3
[
1
9
]
D
a
mera
u
L
e
v
e
n
s
h
t
e
i
n
d
i
s
t
a
n
c
e
K
a
z
a
k
h
K
a
z
a
k
h
t
e
x
t
s
A
c
c
u
r
a
c
y
9
2
.
8
%.
3.
M
E
T
H
O
D
T
h
is
s
ec
tio
n
d
escr
ib
ed
th
e
co
m
b
in
atio
n
o
f
L
ev
en
s
h
tein
d
is
t
an
ce
an
d
T
r
ie
alg
o
r
ith
m
as
th
e
m
eth
o
d
.
T
h
is
co
m
b
in
ati
o
n
m
eth
o
d
u
s
ed
to
e
v
alu
atin
g
tex
t
co
r
r
e
ctio
n
s
to
o
b
tain
ap
p
r
o
p
r
iate
tr
an
s
latio
n
r
esu
lts
.
Fig
u
r
e
1
illu
s
tr
ated
th
e
f
o
llo
wi
n
g
s
tep
s
o
f
th
e
r
esear
c
h
m
eth
o
d
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
I
SS
N:
2252
-
8
7
7
6
E
va
lu
a
tio
n
o
f te
xt
co
r
r
ec
tio
n
u
s
in
g
a
co
mb
in
a
tio
n
o
f
L
ev
en
s
h
tein
d
is
ta
n
ce
a
n
d
Tr
ie
… (
C
yn
th
ia
N
a
ta
lie
)
1343
3
.
1
.
Da
t
a
c
o
llect
io
n
I
n
th
e
d
ata
co
llectio
n
s
ec
tio
n
,
d
ata
u
s
ed
in
th
is
r
esear
ch
i
n
clu
d
es
th
e
I
n
d
o
n
esian
la
n
g
u
a
g
e
d
ictio
n
ar
y
as
a
co
m
p
ar
is
o
n
to
th
e
in
p
u
t
tex
t
u
s
in
g
th
e
k
b
b
i
-
p
y
th
o
n
lib
r
ar
y
an
d
2
0
0
in
p
u
t
tex
t
d
ata
co
llected
f
r
o
m
I
n
d
o
n
esian
n
ews
with
v
ar
io
u
s
s
p
ellin
g
er
r
o
r
s
[
2
0
]
.
T
h
e
s
p
ellin
g
er
r
o
r
s
wer
e
g
en
e
r
ated
b
y
a
m
ac
h
in
e
p
r
ev
io
u
s
ly
p
r
o
ce
s
s
ed
in
r
esear
ch
co
n
d
u
cted
in
2
0
2
0
,
ca
teg
o
r
ized
b
ased
o
n
t
h
e
tex
t
len
g
t
h
:
s
h
o
r
t
tex
t,
m
ed
iu
m
tex
t,
an
d
lo
n
g
tex
t.
T
o
tal
am
o
u
n
t
o
f
in
p
u
t
tex
t
d
ata
u
s
ed
is
2
0
0
c
o
n
tain
s
o
f
5
7
.
0
9
8
w
o
r
d
s
,
co
n
s
is
tin
g
o
f
1
0
0
tex
ts
with
o
u
t
s
p
ellin
g
er
r
o
r
s
an
d
1
0
0
tex
ts
with
v
ar
io
u
s
ty
p
es
o
f
s
p
ellin
g
er
r
o
r
s
,
s
p
ec
if
ically
lex
ical
er
r
o
r
s
,
with
3
0
% tr
ain
in
g
a
n
d
7
0
% testi
n
g
d
ata,
am
o
u
n
tin
g
to
1
4
0
tr
ain
in
g
d
ata
a
n
d
6
0
test
i
n
g
d
ata
Fig
u
r
e
1
.
R
esear
ch
m
eth
o
d
3
.
2
.
Da
t
a
prepro
ce
s
s
ing
B
ef
o
r
e
p
r
o
ce
s
s
in
g
d
ata
u
s
in
g
th
e
co
m
b
in
ati
o
n
o
f
L
ev
e
n
s
h
te
in
d
is
tan
ce
an
d
T
r
ie
alg
o
r
ith
m
,
th
e
tex
t
d
ata
m
u
s
t g
o
th
r
o
u
g
h
p
r
ep
r
o
ce
s
s
in
g
s
tep
s
.
Pre
p
r
o
ce
s
s
in
g
u
s
ed
to
r
em
o
v
e
d
ata
i
n
co
n
s
is
ten
cies
in
th
e
f
o
llo
win
g
s
tep
s
,
s
u
ch
as
p
ar
s
in
g
,
ca
s
e
f
o
l
d
in
g
,
an
d
to
k
en
izin
g
.
I
n
th
is
co
n
tex
t,
th
e
p
r
e
p
r
o
ce
s
s
in
g
s
tep
s
d
o
n
o
t
co
r
r
ec
t
th
e
tex
t d
ata
[2
1
]
.
T
h
e
p
r
e
p
r
o
ce
s
s
in
g
s
tep
s
illu
s
tr
ated
in
Fig
u
r
e
2
[
2
2
]
.
Fig
u
r
e
2
.
Data
p
r
ep
r
o
ce
s
s
in
g
3
.
1
.
T
RIE
AP
P
L
I
CAT
I
O
N
I
n
Alg
o
r
ith
m
1
T
r
ie
d
ata
s
tr
u
ctu
r
e
ca
n
b
e
ap
p
lied
b
y
c
r
ea
tin
g
a
class
to
s
ea
r
ch
f
o
r
tex
t
w
ith
s
im
ilar
p
r
ef
ix
es
[
2
3
]
.
T
h
e
p
u
r
p
o
s
e
is
f
o
r
g
r
o
u
p
in
g
s
ev
er
al
te
x
ts
th
at
h
av
e
s
im
ilar
ities
with
an
ac
c
u
r
ac
y
o
f
m
o
r
e
th
a
n
5
0
% to
p
r
o
ce
ed
to
th
e
n
e
x
t step
[2
4
]
.
Alg
o
r
ith
m
1
.
T
r
ie
d
ata
s
tr
u
ctu
r
e
alg
o
r
ith
m
class
Trie
Node:
def __init__(self):
self.children = {}
self.is_end_of_word = False
self.frequency = 0
class
Trie
:
def __init__(self):
self.root =
Trie
Node()
def insert(self, word):
node = self.root
for char in word:
if char not in node.children:
node.children[char] =
Trie
Node()
node = node.children[char]
node.is_end_of_word = True
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
7
7
6
I
n
t J I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
,
Vo
l.
15
,
No
.
3
,
Sep
tem
b
er
20
26
:
1
3
4
0
-
1
3
5
1
1344
node
.frequency += 1
def search(self, word):
node = self.root
for char in word:
if char not in node.children:
return False
node = node.children[char]
return node.is_end_of_word
Ap
p
ly
in
g
T
r
ie
d
ata
s
tr
u
ctu
r
es
s
p
ee
d
u
p
s
ea
r
ch
in
g
tim
e.
b
ased
o
n
s
im
ilar
p
r
ef
i
x
es.
T
r
ie
d
ata
s
tr
u
ctu
r
es
g
r
o
u
p
ed
all
wo
r
d
s
with
th
e
s
am
e
p
r
e
f
ix
s
to
r
e
d
in
th
e
lis
t
o
f
t
ex
ts
.
Fo
r
e
x
am
p
le,
T
r
ie
d
ata
s
t
r
u
ctu
r
es
ap
p
lied
as
s
h
o
wn
in
T
ab
le
2
.
As
s
h
o
wn
in
T
ab
le
2
,
ea
ch
te
x
t
d
ata,
wh
eth
er
with
o
r
with
o
u
t
s
p
ellin
g
er
r
o
r
s
,
h
ad
g
r
o
u
p
ed
s
im
ilar
tex
t
d
ata
to
th
e
in
p
u
t
tex
t
in
p
u
r
p
o
s
e
to
f
in
d
tex
ts
with
th
e
s
am
e
p
r
ef
ix
.
T
r
ie
d
ata
s
tr
u
ctu
r
e
s
ea
r
ch
ed
i
n
I
n
d
o
n
esian
lan
g
u
ag
e
d
ictio
n
a
r
y
u
s
in
g
th
e
wo
r
d
o
f
‘
ay
a
n
’
b
ased
o
n
two
p
r
ef
ix
es
t
o
f
in
d
all
wo
r
d
s
with
th
e
s
am
e
‘
ay
’
p
r
ef
ix
.
T
h
e
s
am
e
p
r
ef
ix
es st
o
r
ed
in
th
e
lis
t
o
f
te
x
ts
b
ef
o
r
e
m
o
v
e
th
r
o
u
g
h
n
ex
t ste
p
.
T
ab
le
2
.
T
r
ie
d
ata
s
tr
u
ctu
r
e
a
p
p
licatio
n
Te
x
t
S
p
e
l
l
i
n
g
e
r
r
o
r
t
e
x
t
R
i
g
h
t
t
e
x
t
Tr
i
e
d
a
t
a
st
r
u
c
t
u
r
e
a
y
a
n
(
Fa
l
se
)
a
y
a
n
(
Fa
l
se
)
a
y
a
m (
T
ru
e
)
a
y
a
h
|
a
y
a
m |
a
y
a
n
|
a
y
o
m
b
a
l
i
(
T
r
u
e
)
b
a
l
i
(
T
r
u
e
)
b
a
l
i
|
b
a
l
i
k
|
b
a
l
i
t
a
b
e
t
u
t
u
(
T
ru
e
)
b
e
t
u
t
u
(
T
ru
e
)
b
e
t
u
l
|
b
e
t
u
t
u
d
i
m
a
sa
(
T
r
u
e
)
d
i
m
a
sa
(
T
r
u
e
)
d
i
m
a
sa
|
d
i
mas
a
k
|
d
i
mas
u
k
i
3
.
3
.
L
ev
ens
hte
in dis
t
a
nce
T
h
e
ca
lcu
latio
n
o
f
th
e
L
e
v
en
s
h
tein
d
is
tan
ce
alg
o
r
ith
m
is
p
e
r
f
o
r
m
e
d
u
s
in
g
s
tr
in
g
o
p
e
r
atio
n
s
s
u
ch
as
in
s
er
tio
n
,
d
eletio
n
,
an
d
s
u
b
s
ti
tu
tio
n
to
co
m
p
u
te
th
e
ch
ar
ac
t
er
d
is
tan
ce
[
1
5
]
.
L
ev
e
n
s
h
tein
d
is
tan
ce
alg
o
r
ith
m
ca
lcu
lated
b
etwe
en
th
e
in
p
u
t
tex
t
an
d
th
e
lis
t
o
f
tex
ts
to
f
i
n
d
m
i
n
im
u
m
ch
ar
ac
te
r
d
is
tan
ce
an
d
d
is
p
lay
th
e
co
r
r
ec
ted
tex
t
b
ased
o
n
th
e
m
i
n
im
u
m
c
h
ar
ac
ter
d
is
tan
ce
[
2
5
]
.
T
h
e
d
is
tan
ce
is
d
eter
m
in
e
d
b
y
th
e
(
1
)
,
(
2
)
,
an
d
(
3
)
f
u
n
ctio
n
b
elo
w.
,
(
,
)
=
{
0
{
,
(
−
1
,
)
+
1
(
1
)
,
(
,
−
1
)
+
1
(
2
)
,
(
−
1
,
−
1
)
+
1
[
≠
]
(
3
)
T
h
e
f
u
n
ctio
n
o
f
th
e
L
ev
en
s
h
te
in
d
is
tan
ce
alg
o
r
ith
m
in
(
1
)
,
(
2
)
,
an
d
(
3
)
im
p
lem
en
ted
o
n
tw
o
ex
am
p
le
s
tr
in
g
s
(
s
tr
in
g
A:
ay
an
;
s
tr
in
g
B
:
ay
am
)
.
All
ch
ar
ac
ter
s
in
b
o
th
s
tr
in
g
s
c
o
m
p
ar
e
d
ea
c
h
o
th
e
r
to
f
in
d
eith
er
th
e
ch
ar
ac
ter
is
th
e
s
am
e
o
r
n
o
t
b
y
u
s
in
g
L
ev
e
n
s
h
tein
d
is
tan
ce
ca
lcu
latio
n
.
Af
ter
war
d
s
,
a
ca
lc
u
latio
n
tab
le
ca
n
b
e
g
en
er
ated
as sh
o
wn
in
T
ab
le
3
.
T
ab
le
3
.
L
e
v
en
s
h
tein
d
is
tan
ce
alg
o
r
ith
m
ca
lcu
latio
n
P
o
si
t
i
o
n
C
h
a
r
a
c
t
e
r
1
C
h
a
r
a
c
t
e
r
2
D
i
st
a
n
c
e
s
F
o
r
mu
l
a
R
e
s
u
l
t
D
(
1
,
1
)
a
a
Th
e
r
e
i
s
n
’
t
a
n
y
D(1
-
1
,
1
-
1)
0
D
(
1
,
2
)
a
y
Th
e
r
e
i
s
D
(
1
,
2
-
1
)
+
1
1
D
(
1
,
3
)
a
a
Th
e
r
e
i
s
n
’
t
a
n
y
D(1
-
1
,
3
-
1)
2
D
(
1
,
4
)
a
m
Th
e
r
e
i
s
D
(
1
,
4
-
1
)
+
1
3
D
(
2
,
1
)
y
a
Th
e
r
e
i
s
D
(
2
,
1
-
1
)
+
1
1
D
(
2
,
2
)
y
y
Th
e
r
e
i
s
n
’
t
a
n
y
D(2
-
1
,
2
-
1)
0
D
(
2
,
3
)
y
a
Th
e
r
e
i
s
D
(
2
,
3
-
1
)
+
1
1
D
(
2
,
4
)
y
m
Th
e
r
e
i
s
D
(
2
,
4
-
1
)
+
1
2
D
(
3
,
1
)
a
a
Th
e
r
e
i
s
n
’
t
a
n
y
D(3
-
1
,
1
-
1)
1
D
(
3
,
2
)
a
y
Th
e
r
e
i
s
D
(
3
,
2
-
1
)
+
1
2
D
(
3
,
3
)
a
a
Th
e
r
e
i
s
n
’
t
a
n
y
D(3
-
1
,
3
-
1)
0
D
(
3
,
4
)
a
m
Th
e
r
e
i
s
D
(
3
,
4
-
1
)
+
1
1
D
(
4
,
1
)
n
a
Th
e
r
e
i
s
D
(
4
,
1
-
1
)
+
1
2
D
(
4
,
2
)
n
y
Th
e
r
e
i
s
D
(
4
,
2
-
1
)
+
1
2
D
(
4
,
3
)
n
a
Th
e
r
e
i
s
D
(
4
,
3
-
1
)
+
1
1
D
(
4
,
4
)
n
m
Th
e
r
e
i
s
D
(
4
,
4
-
1
)
+
1
1
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
I
SS
N:
2252
-
8
7
7
6
E
va
lu
a
tio
n
o
f te
xt
co
r
r
ec
tio
n
u
s
in
g
a
co
mb
in
a
tio
n
o
f
L
ev
en
s
h
tein
d
is
ta
n
ce
a
n
d
Tr
ie
… (
C
yn
th
ia
N
a
ta
lie
)
1345
B
ased
o
n
th
e
r
esu
lts
o
f
th
e
L
e
v
en
s
h
tein
d
is
tan
ce
alg
o
r
ith
m
ca
lcu
latio
n
in
T
ab
le
3
,
t
h
e
m
a
tr
ix
ca
n
b
e
f
illed
in
ac
co
r
d
in
g
to
ch
ar
ac
t
er
p
o
s
itio
n
.
E
ac
h
co
lu
m
n
s
d
e
f
in
ed
‘
ch
ar
ac
ter
1
’
as
th
e
tex
t
with
s
p
ellin
g
er
r
o
r
an
d
ea
ch
r
o
ws
d
ef
in
ed
‘
ch
a
r
a
cter
2
’
as
th
e
wo
r
d
f
r
o
m
th
e
lis
t
o
f
tex
ts
g
en
er
ated
f
r
o
m
T
r
ie
da
ta
s
tr
u
ctu
r
e.
Fin
al
m
atr
ix
g
en
er
ated
as
s
h
o
wn
in
T
ab
le
4
.
B
ased
o
n
T
ab
le
4
,
it
ca
n
b
e
s
ee
n
th
at
D(
4
,
4
)
=
1
,
s
h
o
win
g
th
at
th
er
e
is
o
n
e
c
h
ar
ac
ter
d
if
f
e
r
en
ce
o
u
t
o
f
th
e
f
o
u
r
c
h
ar
ac
ter
s
co
m
p
ar
ed
.
T
h
e
wo
r
d
s
im
ilar
ity
s
co
r
e
ca
lcu
latio
n
r
esu
lt
is
7
5
%.
W
ith
th
is
s
co
r
e,
th
e
co
m
b
i
n
atio
n
alg
o
r
ith
m
h
ad
d
is
p
lay
ed
s
u
g
g
esti
o
n
s
in
th
e
tex
t
co
r
r
ec
tio
n
r
ec
o
m
m
en
d
atio
n
tab
le
f
o
r
u
s
er
to
ch
o
o
s
e
o
n
e
as th
e
co
r
r
ec
t te
x
t c
o
r
r
ec
tio
n
[
2
6
]
.
T
h
u
s
,
ac
cu
r
ate
tex
t c
o
r
r
ec
tio
n
r
esu
lted
in
a
g
o
o
d
a
n
d
c
o
r
r
ec
t
tex
t tr
an
s
latio
n
.
T
ab
le
4
.
L
e
v
en
s
h
tein
d
is
tan
ce
alg
o
r
ith
m
r
esu
lt
-
a
y
a
n
-
0
1
2
3
4
a
1
0
1
2
3
y
2
1
0
1
2
a
3
1
2
0
1
m
4
2
2
1
1
3
.
4
.
L
ev
ens
hte
in dis
t
a
nce
a
n
d
T
rie
a
lg
o
rit
hm
I
m
p
lem
en
tatio
n
o
f
L
ev
e
n
s
h
tein
d
is
tan
ce
an
d
T
r
ie
alg
o
r
ith
m
s
is
p
er
f
o
r
m
e
d
u
s
in
g
Py
th
o
n
p
r
o
g
r
a
m
m
in
g
la
n
g
u
a
g
e.
T
h
is
im
p
lem
en
tatio
n
r
e
q
u
ir
ed
a
n
in
p
u
t
tex
t
in
p
u
r
p
o
s
e
to
b
e
co
r
r
e
cted
an
d
g
en
e
r
ated
tr
an
s
lated
tex
t
as
th
e
o
u
tp
u
t.
T
h
e
tex
t
c
o
r
r
ec
tio
n
f
lo
wc
h
a
r
t
ca
n
b
e
s
ee
n
in
Fig
u
r
e
3
.
B
ased
o
n
Fig
u
r
e
3
,
tex
t
c
o
r
r
ec
tio
n
is
ca
r
r
ied
o
u
t
b
y
in
p
u
ttin
g
tex
t
in
th
e
co
n
tex
t
o
f
lan
g
u
ag
e
tr
an
s
latio
n
.
Sp
ellin
g
er
r
o
r
s
h
ad
d
etec
ted
in
th
e
in
p
u
t
tex
t
an
d
i
f
s
p
ellin
g
er
r
o
r
is
d
etec
ted
,
T
r
ie
d
ata
s
tr
u
ctu
r
e
s
ea
r
ch
b
ased
o
n
s
im
ilar
p
r
ef
ix
es
[
1
4
]
.
Fu
r
th
er
m
o
r
e,
T
r
ie
s
ea
r
ch
r
esu
lts
s
to
r
ed
in
a
lis
t to
b
e
ca
lcu
lated
u
s
in
g
L
ev
e
n
s
h
tein
d
is
tan
ce
alg
o
r
ith
m
.
T
h
is
ex
p
er
im
e
n
t
co
llected
d
at
aset
in
I
n
d
o
n
esian
lan
g
u
a
g
e
an
d
s
p
litt
ed
i
n
to
3
0
%
tr
ain
in
g
d
ata
an
d
7
0
%
test
in
g
d
ata
as
m
en
tio
n
ed
in
s
u
b
-
s
ec
tio
n
3
.
1
[
2
0
]
.
Data
s
et
h
ad
to
b
e
p
r
o
ce
s
s
ed
in
p
r
ep
r
o
ce
s
s
in
g
s
tag
e
to
g
et
clea
n
s
ed
d
ataset
an
d
ca
n
b
e
p
r
o
p
e
r
ly
p
r
o
ce
s
s
ed
b
y
th
e
s
y
s
tem
.
At
th
i
s
s
tag
e,
th
e
p
r
e
p
r
o
ce
s
s
in
g
p
r
o
ce
s
s
wo
u
ld
n
o
t
d
ir
ec
tly
co
r
r
ec
t
s
p
ellin
g
er
r
o
r
m
a
r
k
ed
b
y
r
ed
in
T
ab
le
5
an
d
o
n
ly
clea
n
th
e
tex
t
d
ata
in
to
n
o
r
m
alize
d
tex
t
d
ata.
T
h
is
s
tag
e
is
co
n
d
u
cted
in
s
ev
er
al
s
tep
s
,
s
u
ch
as
p
ar
s
in
g
,
ca
s
e
f
o
ld
in
g
,
an
d
to
k
en
izin
g
.
T
ex
t p
r
ep
r
o
ce
s
s
in
g
r
esu
lts
ar
e
also
s
h
o
wn
in
T
ab
le
5
.
Fig
u
r
e
3
.
Pro
ce
s
s
f
lo
wch
a
r
t
T
ab
le
5
.
Pre
p
r
o
ce
s
s
in
g
r
esu
lt
Te
x
t
P
a
r
si
n
g
C
a
se
F
o
l
d
i
n
g
To
k
e
n
i
z
i
n
g
Jo
sh
Ea
r
n
e
s
t
m
e
n
y
a
t
a
k
a
n
t
i
d
a
k
m
u
n
g
k
i
n
A
m
e
r
i
k
a
S
e
r
i
k
a
t
me
n
g
e
r
a
h
k
a
n
p
a
s
u
k
a
n
l
a
g
i
k
e
I
r
a
k
.
Jo
sh
Ea
r
n
e
s
t
m
e
n
y
a
t
a
k
a
n
t
i
d
a
k
m
u
n
g
k
i
n
A
m
e
r
i
k
a
S
e
r
i
k
a
t
me
n
g
e
r
a
h
k
a
n
p
a
s
u
k
a
n
l
a
g
i
k
e
I
r
a
k
.
j
o
s
h
e
a
r
n
e
st
me
n
y
a
t
a
k
a
n
t
i
d
a
k
m
u
n
g
k
i
n
a
mer
i
k
a
seri
k
a
t
me
n
g
e
r
a
h
k
a
n
p
a
s
u
k
a
n
l
a
g
i
k
e
i
r
a
k
[
‘
j
o
sh
’
,
‘
e
a
r
n
e
s
t
’
,
‘
m
e
n
y
a
t
a
k
a
n
’
,
‘
t
i
d
a
k
’
,
‘
m
u
n
g
k
i
n
’
,
‘
a
m
e
r
i
k
a
’
,
‘
seri
k
a
t
’
,
‘
me
n
g
e
r
a
h
k
a
n
’
,
‘
p
a
su
k
a
n
’
,
‘
l
a
g
i
’
,
‘
k
e
’
,
‘
i
r
a
k
’
]
J
o
s
h
E
a
r
n
e
s
t
s
t
t
e
d
t
h
a
t
i
t
i
s
n
o
t
p
o
ssi
b
l
e
f
o
r
t
h
e
U
n
i
t
e
d
S
t
a
t
e
s
t
o
d
e
p
l
o
y
t
ro
o
p
s
t
o
I
ra
q
a
g
a
i
n
.
J
o
s
h
E
a
r
n
e
s
t
s
t
t
e
d
t
h
a
t
i
t
i
s
n
o
t
p
o
ssi
b
l
e
f
o
r
t
h
e
U
n
i
t
e
d
S
t
a
t
e
s
t
o
d
e
p
l
o
y
t
ro
o
p
s
t
o
I
ra
q
a
g
a
i
n
.
j
o
s
h
e
a
r
n
e
s
t
s
t
t
e
d
t
h
a
t
i
t
i
s
n
o
t
p
o
ssi
b
l
e
f
o
r
t
h
e
u
n
i
t
e
d
st
a
t
e
s
t
o
d
e
p
l
o
y
t
r
o
o
p
s
t
o
i
ra
q
a
g
a
i
n
.
[
‘
j
o
sh
’
,
‘
e
a
r
n
e
st
’
,
’
st
t
e
d
’
,
’
t
h
a
t
’
,
‘
i
t
’
,
‘
i
s’
,
‘
n
o
t
’
,
‘
p
o
ss
i
b
l
e
’
,
‘
f
o
r’
,
‘
t
h
e
’
,
‘
u
n
i
t
e
d
’
,
‘
st
a
t
e
s’
,
‘
t
o
’
,
‘
d
e
p
l
o
y
’
,
‘
t
ro
o
p
s’
,
‘
t
o
’
,
‘
i
ra
q
’
,
‘
a
g
a
i
n
’
]
T
r
ie
d
ata
s
tr
u
ctu
r
e
is
ap
p
lied
t
o
s
ea
r
ch
f
o
r
tex
t
d
ata
with
s
im
ilar
p
r
ef
ix
es
in
th
e
d
ictio
n
a
r
y
u
s
ed
as
a
co
m
p
ar
is
o
n
f
o
r
tex
t
co
r
r
ec
tio
n
p
u
r
p
o
s
es
[
2
4
]
.
L
ev
en
s
h
tein
d
is
tan
ce
alg
o
r
ith
m
ca
lcu
lated
to
f
in
d
th
e
s
m
allest
d
is
tan
ce
b
etwe
en
th
e
o
r
ig
in
al
tex
t
an
d
th
e
lis
t
o
f
tex
ts
f
r
o
m
th
e
d
ictio
n
ar
y
u
s
ed
a
f
ter
s
ea
r
ch
in
g
f
o
r
tex
t
d
ata
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
7
7
6
I
n
t J I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
,
Vo
l.
15
,
No
.
3
,
Sep
tem
b
er
20
26
:
1
3
4
0
-
1
3
5
1
1346
with
s
im
ilar
p
r
ef
ix
es
u
s
in
g
T
r
ie
d
ata
s
tr
u
ctu
r
e
to
f
in
d
th
e
s
m
allest
d
is
tan
ce
in
th
e
p
u
r
p
o
s
e
o
f
tex
t
co
r
r
ec
tio
n
.
L
ev
en
s
h
tein
d
is
tan
ce
ca
lcu
lat
io
n
r
esu
lted
as
s
h
o
wn
in
T
a
b
le
6
.
L
ev
e
n
s
h
tein
d
is
tan
ce
alg
o
r
ith
m
u
s
ed
to
ca
lcu
late
th
e
s
m
allest
d
i
s
tan
c
e
b
etwe
en
I
n
d
o
n
esian
tex
ts
as
s
h
o
wn
in
T
ab
le
6
.
Af
ter
th
e
ca
lcu
latio
n
r
esu
lts
o
b
tain
ed
,
th
e
d
is
tan
ce
b
etwe
e
n
tex
ts
s
o
r
ted
f
r
o
m
t
h
e
s
m
allest
d
is
tan
ce
o
b
tain
ed
to
th
e
lar
g
est
d
is
tan
ce
in
th
e
s
u
g
g
esti
o
n
lis
t
d
is
p
lay
ed
.
T
h
e
to
p
c
o
r
r
ec
tio
n
r
esu
lt
is
d
is
p
lay
ed
as
th
e
b
est
m
atch
es
t
ex
t
co
r
r
ec
tio
n
to
th
e
in
p
u
t
tex
t
as
in
T
ab
le
7
.
B
ased
o
n
T
a
b
le
7
,
it
ca
n
b
e
s
ee
n
th
at
s
u
g
g
es
tio
n
s
s
o
r
te
d
b
ased
o
n
L
e
v
en
s
h
tein
d
is
tan
ce
ca
lcu
latio
n
d
is
tan
ce
as
th
e
r
esu
lt
o
f
tex
t
c
o
r
r
ec
tio
n
.
.
I
t
s
h
o
wn
th
at
f
ir
s
t
s
u
g
g
est
io
n
h
a
d
t
h
e
s
h
o
r
test
d
is
tan
ce
u
s
in
g
th
e
co
m
b
in
ati
o
n
o
f
L
ev
e
n
s
h
tein
d
is
tan
ce
an
d
T
r
ie
alg
o
r
ith
m
.
First
s
u
g
g
esti
o
n
o
f
th
e
to
p
s
u
g
g
es
tio
n
s
s
elec
ted
as th
e
r
esu
lt o
f
tex
t c
o
r
r
ec
tio
n
,
tr
an
s
lated
an
d
d
is
p
lay
ed
as tr
an
s
lated
t
ex
t.
T
ab
le
6
.
L
e
v
en
s
h
tein
d
is
tan
ce
ca
lcu
latio
n
r
esu
lts
P
o
si
t
i
o
n
C
h
a
r
a
c
t
e
r
1
C
h
a
r
a
c
t
e
r
2
D
i
st
a
n
c
e
s
F
o
r
mu
l
a
R
e
s
u
l
t
d
[
1
]
[
1
]
j
j
Th
e
r
e
i
s
n
’
t
a
n
y
d
[
1
-
1
]
[
1
-
1]
0
d
[
1
]
[
2
]
j
o
Th
e
r
e
i
s
d
[
1
]
[
2
-
1
]
+
1
1
d
[
1
]
[
3
]
j
s
Th
e
r
e
i
s
d
[
1
]
[
3
-
1
]
+
1
2
d
[
1
]
[
4
]
j
h
Th
e
r
e
i
s
d
[
1
]
[
4
-
1
]
+
1
3
d
[
1
]
[
5
]
j
Th
e
r
e
i
s
d
[
1
]
[
5
-
1
]
+
1
4
d
[
1
]
[
6
]
j
e
Th
e
r
e
i
s
d
[
1
]
[
6
-
1
]
+
1
5
d
[
1
]
[
7
]
j
a
Th
e
r
e
i
s
d
[
1
]
[
7
-
1
]
+
1
6
d
[
1
]
[
8
]
j
r
Th
e
r
e
i
s
d
[
1
]
[
8
-
1
]
+
1
7
d
[
1
]
[
9
]
j
n
Th
e
r
e
i
s
d
[
1
]
[
9
-
1
]
+
1
8
d
[
1
]
[
1
0
]
j
e
Th
e
r
e
i
s
d
[
1
]
[
1
0
-
1
]
+
1
9
d
[
1
]
[
1
1
]
j
s
Th
e
r
e
i
s
d
[
1
]
[
1
1
-
1
]
+
1
10
d
[
1
]
[
1
2
]
j
t
Th
e
r
e
i
s
d
[
1
]
[
1
2
-
1
]
+
1
11
d
[
1
]
[
1
3
]
j
Th
e
r
e
i
s
d
[
1
]
[
1
3
-
1
]
+
1
12
d
[
1
]
[
1
4
]
j
m
Th
e
r
e
i
s
d
[
1
]
[
1
4
-
1
]
+
1
13
d
[
1
]
[
1
5
]
j
e
Th
e
r
e
i
s
d
[
1
]
[
1
5
-
1
]
+
1
14
d
[
1
]
[
1
6
]
j
n
Th
e
r
e
i
s
d
[
1
]
[
1
6
-
1
]
+
1
15
d
[
1
]
[
1
7
]
j
y
Th
e
r
e
i
s
d
[
1
]
[
1
7
-
1
]
+
1
16
d
[
1
]
[
1
8
]
j
a
Th
e
r
e
i
s
d
[
1
]
[
1
8
-
1
]
+
1
17
d
[
1
]
[
1
9
]
j
t
Th
e
r
e
i
s
d
[
1
]
[
1
9
-
1
]
+
1
18
d
[
1
]
[
2
0
]
j
a
Th
e
r
e
i
s
d
[
1
]
[
2
0
-
1
]
+
1
19
d
[
1
]
[
2
1
]
j
k
Th
e
r
e
i
s
d
[
1
]
[
2
1
-
1
]
+
1
20
d
[
1
]
[
2
2
]
j
a
Th
e
r
e
i
s
d
[
1
]
[
2
2
-
1
]
+
1
21
d
[
1
]
[
2
3
]
j
n
Th
e
r
e
i
s
d
[
1
]
[
2
3
-
1
]
+
1
22
…
…
…
…
….
…
T
ab
le
7
.
So
r
te
d
s
u
g
g
esti
o
n
s
te
x
t
R
a
n
k
O
r
i
g
i
n
a
l
T
e
x
t
S
u
g
g
e
s
t
i
o
n
T
e
x
t
b
a
s
e
d
o
n
D
i
c
t
i
o
n
a
r
y
D
i
st
a
n
c
e
s
1
st
j
o
s
h
e
a
r
n
e
st
me
n
y
t
a
k
a
n
t
i
d
a
k
mu
n
g
k
i
n
a
meri
k
a
seri
k
a
t
m
e
n
g
e
r
a
h
k
a
n
p
a
su
k
a
n
l
a
g
i
k
e
i
r
a
k
j
o
s
h
e
a
r
n
e
st
me
n
y
a
t
a
k
a
n
t
i
d
a
k
m
u
n
g
k
i
n
a
mer
i
k
a
s
e
r
i
k
a
t
men
g
e
r
a
h
k
a
n
p
a
s
u
k
a
n
l
a
g
i
k
e
i
r
a
k
1
(
su
g
g
e
s
t
e
d
)
j
o
s
h
e
a
r
n
e
s
t
s
t
t
e
d
t
h
a
t
i
t
i
s
n
o
t
p
o
ssi
b
l
e
f
o
r
t
h
e
u
n
i
t
e
d
st
a
t
e
s
t
o
d
e
p
l
o
y
t
ro
o
p
s
t
o
i
r
a
q
a
g
a
i
n
.
j
o
s
h
e
a
r
n
e
s
t
s
t
a
t
e
d
t
h
a
t
i
t
i
s
n
o
t
p
o
ssi
b
l
e
f
o
r
t
h
e
u
n
i
t
e
d
st
a
t
e
s
t
o
d
e
p
l
o
y
t
r
o
o
p
s
t
o
i
r
a
q
a
g
a
i
n
.
2
n
d
j
o
s
h
e
a
r
n
e
st
me
n
y
t
a
k
a
n
t
i
d
a
k
mu
n
g
k
i
n
a
meri
k
a
seri
k
a
t
m
e
n
g
e
r
a
h
k
a
n
p
a
su
k
a
n
l
a
g
i
k
e
i
r
a
k
seri
k
a
t
p
e
k
e
r
j
a
j
a
k
a
r
t
a
i
n
t
e
r
n
a
t
i
o
n
a
l
s
c
h
o
o
l
j
i
s m
e
n
d
a
t
a
n
g
i
k
o
m
i
si
k
e
p
o
l
i
s
i
a
n
n
a
s
i
o
n
a
l
k
o
mp
o
l
n
a
s
u
n
t
u
k
me
l
a
y
a
n
g
k
a
n
p
e
n
g
a
d
u
a
n
……
1
5
4
1
j
o
s
h
e
a
r
n
e
s
t
s
t
t
e
d
t
h
a
t
i
t
i
s
n
o
t
p
o
ssi
b
l
e
f
o
r
t
h
e
u
n
i
t
e
d
st
a
t
e
s
t
o
d
e
p
l
o
y
t
ro
o
p
s
t
o
i
r
a
q
a
g
a
i
n
.
t
h
e
j
a
k
a
r
t
a
i
n
t
e
rn
a
t
i
o
n
a
l
sc
h
o
o
l
(
j
i
s)
w
o
r
k
e
rs
u
n
i
o
n
v
i
si
t
e
d
t
h
e
n
a
t
i
o
n
a
l
p
o
l
i
c
e
c
o
m
m
i
ssi
o
n
(
k
o
m
p
o
l
n
a
s)
t
o
f
i
l
e
a
c
o
m
p
l
a
i
n
t
…
…
3
r
d
j
o
s
h
e
a
r
n
e
st
me
n
y
t
a
k
a
n
t
i
d
a
k
mu
n
g
k
i
n
a
meri
k
a
seri
k
a
t
m
e
n
g
e
r
a
h
k
a
n
p
a
su
k
a
n
l
a
g
i
k
e
i
r
a
k
seri
k
a
t
p
e
k
e
r
j
a
j
a
k
a
r
t
a
i
n
t
e
r
n
a
t
i
o
n
a
l
s
c
h
o
o
l
j
i
s m
e
n
d
a
t
a
n
g
i
k
o
m
i
si
k
e
p
o
l
i
s
i
a
n
n
a
s
i
o
n
a
l
k
o
mp
o
l
n
a
s
u
n
t
u
k
me
n
g
a
d
u
k
a
n
k
e
b
e
r
a
t
a
n
…
…
2
0
9
7
j
o
s
h
e
a
r
n
e
s
t
s
t
t
e
d
t
h
a
t
i
t
i
s
n
o
t
p
o
ssi
b
l
e
f
o
r
t
h
e
u
n
i
t
e
d
st
a
t
e
s
t
o
d
e
p
l
o
y
t
ro
o
p
s
t
o
i
r
a
q
a
g
a
i
n
.
t
h
e
j
a
k
a
r
t
a
i
n
t
e
rn
a
t
i
o
n
a
l
sc
h
o
o
l
(
j
i
s)
w
o
r
k
e
rs
u
n
i
o
n
v
i
si
t
e
d
t
h
e
n
a
t
i
o
n
a
l
p
o
l
i
c
e
c
o
m
m
i
ssi
o
n
(
k
o
m
p
o
l
n
a
s)
t
o
l
o
d
g
e
a
c
o
m
p
l
a
i
n
t
…
…
4.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
T
h
is
r
esear
ch
co
n
d
u
cted
in
o
r
d
er
to
e
v
alu
atin
g
t
h
e
co
m
b
in
atio
n
o
f
L
ev
en
s
h
tein
d
is
tan
ce
an
d
T
r
i
e
alg
o
r
ith
m
in
th
e
co
n
tex
t
o
f
te
x
t
co
r
r
ec
tio
n
.
Pre
v
io
u
s
r
esear
ch
h
av
e
p
r
o
p
o
s
ed
v
ar
io
u
s
m
et
h
o
d
s
to
h
an
d
le
te
x
t
co
r
r
ec
tio
n
p
r
o
b
lem
s
,
h
o
wev
er
,
th
er
e’
s
lim
itatio
n
o
f
th
e
p
r
ev
io
u
s
r
esear
ch
,
s
u
ch
as
ex
ce
s
s
i
v
e
wo
r
d
co
r
r
ec
tio
n
r
esu
lts
ca
u
s
ed
o
f
u
n
g
r
o
u
p
ed
wo
r
d
,
im
p
r
ec
is
e
wo
r
d
s
u
g
g
es
tio
n
s
,
an
d
h
ig
h
m
em
o
r
y
u
s
ag
e.
W
e
f
o
u
n
d
th
at
en
h
an
cin
g
L
ev
e
n
s
h
tein
d
is
tan
ce
an
d
T
r
ie
alg
o
r
ith
m
c
o
u
ld
lead
to
m
o
r
e
ef
f
icien
t
tex
t
c
o
r
r
ec
tio
n
.
T
r
ie
d
ata
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
I
SS
N:
2252
-
8
7
7
6
E
va
lu
a
tio
n
o
f te
xt
co
r
r
ec
tio
n
u
s
in
g
a
co
mb
in
a
tio
n
o
f
L
ev
en
s
h
tein
d
is
ta
n
ce
a
n
d
Tr
ie
… (
C
yn
th
ia
N
a
ta
lie
)
1347
s
tr
u
ctu
r
es
r
ed
u
ce
d
m
em
o
r
y
u
s
ag
e
in
g
r
o
u
p
i
n
g
b
ased
o
n
s
im
ilar
p
r
ef
ix
es,
co
m
b
in
e
d
with
L
ev
e
n
s
h
tein
d
is
tan
ce
to
ca
lcu
late
d
is
tan
ce
.
As m
en
tio
n
ed
in
s
u
b
-
s
ec
tio
n
3
.
1
,
d
ataset
u
s
ed
in
co
n
s
is
tin
g
o
f
1
0
0
te
x
ts
with
o
u
t sp
ellin
g
er
r
o
r
s
an
d
1
0
0
te
x
ts
with
v
ar
i
o
u
s
ty
p
es
o
f
s
p
ellin
g
er
r
o
r
s
.
A
f
ter
th
e
e
x
p
er
im
e
n
t
d
o
n
e,
e
v
al
u
atio
n
m
ea
s
u
r
e
d
b
y
ca
lcu
latin
g
p
er
f
o
r
m
a
n
ce
ev
alu
atio
n
m
etr
ics.
5.
CO
NF
USI
O
N
M
AT
RIX
E
V
AL
UA
T
I
O
N
E
v
alu
atio
n
m
ea
s
u
r
e
d
b
y
ca
lcu
latin
g
ac
cu
r
ac
y
,
p
r
ec
is
io
n
,
r
ec
all
an
d
F
-
m
ea
s
u
r
e
as
th
e
p
er
f
o
r
m
a
n
ce
ev
alu
atio
n
m
etr
ics.
Pre
cisi
o
n
is
d
ef
in
e
d
as
t
h
e
n
u
m
b
e
r
o
f
c
o
r
r
ec
tly
d
etec
ted
s
p
ellin
g
er
r
o
r
s
c
o
m
p
ar
e
d
to
all
d
etec
ted
s
p
ellin
g
er
r
o
r
s
.
R
ec
all
is
d
ef
in
ed
as
th
e
n
u
m
b
er
o
f
co
r
r
ec
tly
d
etec
t
ed
s
p
ellin
g
er
r
o
r
s
d
iv
id
ed
b
y
th
e
to
tal
n
u
m
b
e
r
o
f
c
o
r
r
ec
ted
tex
t
in
t
h
e
d
ataset.
T
h
e
ex
p
e
r
im
en
tal
r
esu
lts
s
h
o
wn
in
T
ab
le
8
.
T
h
e
p
er
f
o
r
m
an
ce
ev
alu
atio
n
m
etr
ics
h
av
e
to
b
e
co
m
p
a
r
ed
t
o
o
th
er
alg
o
r
ith
m
co
m
b
in
atio
n
s
as
b
en
ch
m
ar
k
in
g
.
E
v
alu
atio
n
r
esu
lts
o
f
t
h
e
co
m
b
in
atio
n
o
f
L
e
v
en
s
h
tein
d
is
tan
ce
an
d
T
r
ie
alg
o
r
ith
m
u
s
in
g
th
e
C
o
n
f
u
s
io
n
Ma
tr
ix
ar
e
s
h
o
wn
in
T
a
b
le
9
.
T
ab
le
8
.
E
x
p
er
im
en
tal
r
esu
lts
u
s
in
g
th
e
co
m
b
in
atio
n
o
f
L
e
v
e
n
s
h
tein
d
is
tan
ce
an
d
T
r
ie
Ev
a
l
u
a
t
i
o
n
R
e
s
u
l
t
To
t
a
l
e
r
r
o
r
s
i
n
d
a
t
a
se
t
4
0
0
D
e
t
e
c
t
e
d
s
p
e
l
l
i
n
g
e
r
r
o
r
s
a
n
d
c
o
r
r
e
c
t
e
d
(
TP)
1
9
2
D
e
t
e
c
t
e
d
s
p
e
l
l
i
n
g
e
r
r
o
r
s
a
n
d
n
o
t
c
o
r
r
e
c
t
e
d
(
F
N
)
8
N
o
t
d
e
t
e
c
t
e
d
sp
e
l
l
i
n
g
e
r
r
o
r
s
a
n
d
c
o
r
r
e
c
t
e
d
(
F
P
)
63
N
o
t
d
e
t
e
c
t
e
d
sp
e
l
l
i
n
g
e
r
r
o
r
s
a
n
d
n
o
t
c
o
r
r
e
c
t
e
d
(
TN
)
1
3
7
R
e
c
a
l
l
r
a
t
e
1
9
2
/
(
1
9
2
+
8
)
=
0
.
9
6
0
0
P
r
e
c
i
s
i
o
n
r
a
t
e
1
9
2
/
(
1
9
2
+
6
3
)
=
0
.
7
5
2
9
F
1
S
c
o
r
e
r
a
t
e
2
(
0
.
9
6
0
0
)
(
0
.
7
5
2
9
)
/
(
0
.
9
6
0
0
+
0
.
7
5
2
9
)
=
0
.
8
4
3
9
T
ab
le
9
.
C
o
n
f
u
s
io
n
m
atr
ix
ev
a
lu
atio
n
Ev
a
l
u
a
t
i
o
n
LD
a
n
d
Tr
i
e
(
P
r
o
p
o
se
d
)
LD
a
n
d
N
-
G
r
a
m
[
1
5
]
LD
a
n
d
R
a
b
i
n
K
a
r
p
[
1
0
]
A
c
c
u
r
a
c
y
0
.
8
2
2
5
0
.
7
5
0
0
0
.
2
8
2
5
R
e
c
a
l
l
0
.
9
6
0
0
0
.
5
0
0
0
0
.
5
0
5
0
P
r
e
c
i
s
i
o
n
0
.
7
5
2
9
1
.
0
0
0
0
0
.
3
4
9
5
F
1
S
c
o
r
e
0
.
8
4
3
9
0
.
6
6
6
7
0
.
4
1
3
1
B
ased
o
n
T
ab
le
9
,
t
h
e
ev
al
u
atio
n
was
co
n
d
u
cted
to
m
ea
s
u
r
e
th
e
p
e
r
f
o
r
m
an
ce
o
f
t
h
e
co
m
b
in
atio
n
o
f
L
ev
en
s
h
tein
d
is
tan
ce
alg
o
r
ith
m
an
d
T
r
ie
in
tex
t
co
r
r
ec
tio
n
b
y
ca
lcu
latin
g
ac
cu
r
ac
y
,
r
ec
al
l,
p
r
ec
is
io
n
,
an
d
F
1
s
co
r
e.
T
h
is
e
v
alu
atio
n
co
m
p
ar
ed
with
th
e
c
o
m
b
in
atio
n
o
f
o
th
er
alg
o
r
ith
m
co
m
b
in
at
io
n
s
,
s
u
ch
as
th
e
co
m
b
in
atio
n
o
f
L
ev
en
s
h
tein
d
is
tan
ce
an
d
N
-
Gr
am
,
an
d
th
e
co
m
b
in
atio
n
o
f
L
ev
e
n
s
h
tein
d
is
t
an
ce
an
d
R
ab
in
-
Kar
p
alg
o
r
ith
m
.
Fro
m
th
e
r
esu
lt
illu
s
tr
ated
in
T
ab
le
9
,
we
f
o
u
n
d
th
at
th
e
co
m
b
in
at
io
n
o
f
L
ev
en
s
h
tein
d
is
tan
ce
an
d
T
r
ie
p
er
f
o
r
m
s
b
et
ter
th
an
th
e
o
th
er
alg
o
r
ith
m
c
o
m
b
in
atio
n
s
.
5
.
1
.
AUC
-
RO
C
ev
a
lua
t
io
n
T
h
e
ev
alu
atio
n
r
esu
lts
ca
n
b
e
v
is
u
alize
d
u
s
in
g
t
h
r
esh
o
l
d
s
ettin
g
s
with
th
e
AUC
R
OC
cu
r
v
e.
T
h
er
ef
o
r
e,
ca
lcu
latio
n
s
wer
e
p
er
f
o
r
m
ed
u
s
in
g
t
h
e
v
alu
es
g
en
er
ated
f
r
o
m
th
e
co
n
f
u
s
io
n
m
atr
ix
to
ca
lcu
late
tr
u
e
p
o
s
itiv
e
r
ate
(
T
PR
)
an
d
f
a
ls
e
p
o
s
itiv
e
r
ate
(
FP
R
)
.
T
h
e
c
alcu
latio
n
r
es
u
lts
ar
e
s
h
o
wn
in
T
ab
le
1
0
.
T
ab
le
1
0
.
T
PR
-
FP
R
ca
lcu
lat
io
n
Th
r
e
s
h
o
l
d
TPR
FPR
0
.
1
0
.
0
1
0
2
0
4
0
.
3
4
9
0
5
7
0
.
2
0
.
0
3
3
8
3
5
0
.
5
2
9
8
5
1
0
.
3
0
.
0
7
0
2
4
8
0
.
6
5
1
8
9
9
0
.
4
0
.
1
0
7
4
7
7
0
.
7
3
6
5
5
9
0
.
5
0
.
1
7
6
7
6
8
0
.
8
1
6
8
3
2
0
.
6
0
.
2
4
4
1
8
6
0
.
8
6
8
4
2
1
0
.
7
0
.
3
3
5
6
1
6
0
.
9
0
9
4
4
9
0
.
8
0
.
4
6
8
7
5
0
.
9
5
5
8
8
2
0
.
9
0
.
6
6
3
2
6
5
0
.
9
7
6
8
2
1
1
.
0
1
1
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
7
7
6
I
n
t J I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
,
Vo
l.
15
,
No
.
3
,
Sep
tem
b
er
20
26
:
1
3
4
0
-
1
3
5
1
1348
B
ased
o
n
T
ab
le
1
0
,
th
e
AUC
R
OC
cu
r
v
e
ca
n
b
e
c
r
ea
ted
u
s
i
n
g
th
e
ca
lc
u
lated
tr
u
e
p
o
s
itiv
e
r
ate
(
T
PR
)
an
d
f
alse
p
o
s
itiv
e
r
ate
(
FP
R
)
.
T
h
e
h
ig
h
er
T
PR
v
alu
e
is
,
it
ca
n
b
e
s
ee
n
th
at
th
e
co
m
b
in
atio
n
o
f
L
ev
en
s
h
tein
d
is
tan
ce
an
d
T
r
ie
alg
o
r
ith
m
p
r
o
v
id
e
b
etter
r
esu
lts
th
an
th
e
o
th
er
co
m
b
in
atio
n
in
th
e
co
n
tex
t
o
f
te
x
t
co
r
r
ec
tio
n
.
AUC
-
R
O
C
C
u
r
v
e
ar
e
s
h
o
wn
in
Fig
u
r
e
4
.
Fig
u
r
e
4
.
AUC
-
R
OC
C
u
r
v
e
5
.
2
.
B
leu sco
re
ev
a
lua
t
io
n
E
v
alu
atio
n
r
esu
lts
ca
n
b
e
en
h
an
ce
d
to
m
ea
s
u
r
e
t
h
e
q
u
ality
o
f
tr
an
s
latio
n
r
esu
lts
af
ter
tex
t
co
r
r
ec
tio
n
b
y
ca
lcu
latin
g
th
e
b
ilin
g
u
al
e
v
alu
atio
n
u
n
d
er
s
tu
d
y
s
co
r
e
(
B
L
E
U
)
u
s
in
g
Un
ig
r
am
Pre
cisi
o
n
.
Go
o
d
tr
an
s
latio
n
q
u
ality
ca
n
b
e
p
r
o
v
e
n
b
y
B
L
E
U
s
co
r
e
a
p
p
r
o
ac
h
in
g
to
1
.
As
s
h
o
wn
in
T
ab
le
1
1
,
B
L
E
U
s
co
r
e
in
c
r
ea
s
ed
b
y
0
.
0
1
5
5
o
r
ab
o
u
t 1
.
5
5
% a
f
ter
te
x
t c
o
r
r
ec
tio
n
was p
er
f
o
r
m
ed
.
T
ab
le
1
1
.
B
L
E
U
s
co
r
e
e
v
alu
at
io
n
Ev
a
l
u
t
i
o
n
B
LEU
s
c
o
r
e
B
LEU
S
c
o
r
e
b
e
f
o
r
e
t
e
x
t
c
o
r
r
e
c
t
i
o
n
0
.
6
6
0
2
B
LEU
S
c
o
r
e
a
f
t
e
r
t
e
x
t
c
o
r
r
e
c
t
i
o
n
0
.
6
7
5
7
6.
CO
NCLU
SI
O
N
B
ased
o
n
th
e
r
esu
lts
an
d
d
is
c
u
s
s
io
n
s
th
at
h
av
e
b
ee
n
co
n
d
u
cted
,
th
e
r
esear
ch
s
u
cc
ess
f
u
lly
d
ev
elo
p
ed
an
d
ev
alu
ate
d
tex
t
co
r
r
ec
tio
n
u
s
in
g
a
co
m
b
in
atio
n
o
f
L
ev
e
n
s
h
tein
d
is
tan
ce
alg
o
r
ith
m
to
m
ea
s
u
r
e
th
e
d
is
tan
ce
b
etwe
en
tex
ts
,
u
s
in
g
t
h
e
ap
p
licatio
n
o
f
T
r
ie
d
ata
s
tr
u
ctu
r
e
i
n
tex
t
s
ea
r
ch
b
ased
o
n
th
e
p
r
e
f
ix
o
f
th
e
in
p
u
t
tex
t,
tr
ain
ed
u
s
in
g
7
0
%
o
f
th
e
tr
ai
n
in
g
d
ata
an
d
test
ed
with
3
0
%
o
f
th
e
test
in
g
d
ata
f
r
o
m
2
0
0
tex
t
d
ata
s
cr
ap
ed
.
C
o
m
b
in
atio
n
o
f
L
ev
en
s
h
tein
d
is
tan
ce
alg
o
r
ith
m
an
d
T
r
ie
ac
h
iev
ed
an
ac
c
u
r
ac
y
r
ate
o
f
8
2
.
2
5
%
with
an
F1
s
co
r
e
o
f
8
4
.
3
9
%.
T
h
is
te
x
t
co
r
r
e
ctio
n
m
o
d
el
p
er
f
o
r
m
e
d
g
o
o
d
tr
an
s
latio
n
s
u
s
in
g
B
L
E
U
s
co
r
e
with
a
n
in
cr
ea
s
e
o
f
1
.
5
5
% a
f
ter
te
x
t c
o
r
r
ec
tio
n
was p
er
f
o
r
m
e
d
.
T
h
is
r
esear
ch
ev
alu
ated
tex
t
co
r
r
ec
tio
n
u
s
in
g
co
m
b
in
ati
o
n
o
f
L
ev
e
n
s
h
tein
d
is
tan
ce
an
d
T
r
ie
alg
o
r
ith
m
.
T
h
e
co
m
b
in
ati
o
n
u
s
ed
d
ictio
n
ar
y
o
f
I
n
d
o
n
esian
l
an
g
u
ag
e
to
f
in
d
an
d
co
r
r
ec
t
s
p
ellin
g
er
r
o
r
f
o
cu
s
ed
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
I
SS
N:
2252
-
8
7
7
6
E
va
lu
a
tio
n
o
f te
xt
co
r
r
ec
tio
n
u
s
in
g
a
co
mb
in
a
tio
n
o
f
L
ev
en
s
h
tein
d
is
ta
n
ce
a
n
d
Tr
ie
… (
C
yn
th
ia
N
a
ta
lie
)
1349
in
lex
ical
er
r
o
r
.
Su
g
g
esti
o
n
f
o
r
f
u
r
th
er
r
esear
ch
u
s
in
g
th
e
c
o
m
b
in
atio
n
o
f
L
ev
e
n
s
h
tein
d
is
tan
ce
an
d
T
r
ie
ca
n
b
e
co
n
d
u
cted
b
y
ap
p
ly
i
n
g
th
i
s
co
m
b
in
atio
n
to
m
u
ltil
an
g
u
a
g
e
tex
ts
with
s
em
an
tic
lev
el,
in
clu
d
in
g
b
y
ad
d
in
g
m
o
r
e
tr
ain
in
g
d
ata
a
n
d
test
d
at
a
in
ter
m
s
o
f
in
c
r
ea
s
in
g
th
e
ac
cu
r
ac
y
v
al
u
e
an
d
F1
Sco
r
e.
ACK
NO
WL
E
DG
E
M
E
NT
S
Au
th
o
r
w
o
u
ld
lik
e
t
o
th
a
n
k
B
in
a
Nu
s
an
tar
a
Un
iv
er
s
ity
f
o
r
its
s
u
p
p
o
r
t
an
d
r
eso
u
r
ce
s
p
r
o
v
i
d
ed
th
r
o
u
g
h
o
u
t
th
is
r
esear
ch
.
Au
th
o
r
also
ac
k
n
o
wled
g
e
Pro
f
.
Ab
b
a
Su
g
an
d
a
Gir
s
an
g
f
o
r
h
is
v
a
lu
ab
le
s
u
g
g
esti
o
n
s
an
d
g
u
id
a
n
ce
th
at
h
elp
e
d
im
p
r
o
v
e
th
e
q
u
ality
o
f
th
is
r
esear
ch
.
All
in
d
iv
id
u
als
ac
k
n
o
wled
g
ed
h
av
e
p
r
o
v
id
ed
co
n
s
en
t to
b
e
m
en
tio
n
e
d
in
th
i
s
s
ec
tio
n
.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
T
h
is
r
esea
r
ch
is
s
u
p
p
o
r
t
e
d
b
y
t
h
e
f
u
n
d
i
n
g
f
r
o
m
Di
r
e
ct
o
r
ate
o
f
R
es
ea
r
c
h
,
T
ec
h
n
o
l
o
g
y
,
an
d
C
o
m
m
u
n
it
y
Ser
v
i
ce
o
f
Mi
n
is
t
r
y
o
f
E
d
u
ca
ti
o
n
,
C
u
l
t
u
r
e,
R
ese
a
r
c
h
,
a
n
d
T
e
c
h
n
o
lo
g
y
o
f
th
e
R
ep
u
b
li
c
of
I
n
d
o
n
esi
a
.
AUTHO
R
CO
NT
RI
B
UT
I
O
NS ST
A
T
E
M
E
N
T
T
h
is
jo
u
r
n
al
u
s
es
th
e
C
o
n
tr
ib
u
to
r
R
o
les
T
ax
o
n
o
m
y
(
C
R
ed
iT)
to
r
ec
o
g
n
ize
in
d
iv
id
u
al
au
th
o
r
co
n
tr
ib
u
tio
n
s
,
r
ed
u
ce
au
th
o
r
s
h
ip
d
is
p
u
tes,
an
d
f
ac
ilit
ate
co
llab
o
r
atio
n
.
Na
m
e
o
f
Aut
ho
r
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
C
y
n
th
ia
Nata
lie
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
Ab
b
a
Su
g
an
d
a
Gir
s
an
g
✓
✓
✓
✓
C
:
C
o
n
c
e
p
t
u
a
l
i
z
a
t
i
o
n
M
:
M
e
t
h
o
d
o
l
o
g
y
So
:
So
f
t
w
a
r
e
Va
:
Va
l
i
d
a
t
i
o
n
Fo
:
Fo
r
mal
a
n
a
l
y
s
i
s
I
:
I
n
v
e
s
t
i
g
a
t
i
o
n
R
:
R
e
so
u
r
c
e
s
D
:
D
a
t
a
C
u
r
a
t
i
o
n
O
:
W
r
i
t
i
n
g
-
O
r
i
g
i
n
a
l
D
r
a
f
t
E
:
W
r
i
t
i
n
g
-
R
e
v
i
e
w
&
E
d
i
t
i
n
g
Vi
:
Vi
su
a
l
i
z
a
t
i
o
n
Su
:
Su
p
e
r
v
i
s
i
o
n
P
:
P
r
o
j
e
c
t
a
d
mi
n
i
st
r
a
t
i
o
n
Fu
:
Fu
n
d
i
n
g
a
c
q
u
i
si
t
i
o
n
CO
NF
L
I
C
T
O
F
I
N
T
E
R
E
S
T
ST
A
T
E
M
E
NT
Au
th
o
r
s
s
tate
n
o
co
n
f
lict o
f
in
t
er
est.
I
NF
O
RM
E
D
CO
NS
E
N
T
I
n
f
o
r
m
ed
co
n
s
en
t
was
n
o
t
ap
p
licab
le
to
th
is
r
esear
ch
b
ec
a
u
s
e
n
o
h
u
m
an
p
ar
ticip
a
n
ts
wer
e
d
ir
ec
tly
in
v
o
lv
ed
.
T
h
is
r
esear
ch
u
tili
ze
d
s
ec
o
n
d
ar
y
tex
t
u
al
d
at
a
o
b
tain
e
d
f
r
o
m
p
u
b
licly
av
ailab
le
s
o
u
r
ce
s
,
in
clu
d
in
g
an
I
n
d
o
n
esian
lan
g
u
ag
e
d
ictio
n
a
r
y
ac
ce
s
s
ed
th
r
o
u
g
h
th
e
k
b
b
i
-
p
y
th
o
n
lib
r
ar
y
an
d
I
n
d
o
n
esian
n
ews te
x
t sam
p
les.
E
T
H
I
CAL AP
P
RO
V
AL
E
th
ical
ap
p
r
o
v
al
was
n
o
t
r
eq
u
ir
ed
f
o
r
th
is
r
esear
ch
b
ec
au
s
e
it
d
id
n
o
t
in
v
o
l
v
e
h
u
m
a
n
p
ar
ticip
an
ts
,
an
im
als,
o
r
s
en
s
itiv
e
p
er
s
o
n
al
d
ata.
T
h
is
r
esear
c
h
was
c
o
n
d
u
cted
u
s
in
g
s
ec
o
n
d
a
r
y
tex
tu
al
d
ata,
in
clu
d
i
n
g
an
I
n
d
o
n
esian
lan
g
u
ag
e
d
ictio
n
ar
y
ac
ce
s
s
ed
th
r
o
u
g
h
t
h
e
k
b
b
i
-
p
y
th
o
n
lib
r
a
r
y
an
d
I
n
d
o
n
esian
n
ews
tex
t
s
am
p
les
f
o
r
tex
t m
i
n
in
g
a
n
d
s
p
ellin
g
-
c
o
r
r
ec
tio
n
e
v
alu
atio
n
.
DATA AV
AI
L
AB
I
L
I
T
Y
T
h
e
d
ata
s
u
p
p
o
r
ti
n
g
th
e
f
in
d
in
g
s
o
f
t
h
is
r
esear
ch
co
n
s
is
t
o
f
a
n
I
n
d
o
n
esian
lan
g
u
ag
e
d
ictio
n
ar
y
ac
ce
s
s
ed
th
r
o
u
g
h
th
e
k
b
b
i
-
p
y
th
o
n
lib
r
ar
y
an
d
2
0
0
I
n
d
o
n
esia
n
n
ews
tex
t
s
am
p
les
co
n
tain
in
g
b
o
th
co
r
r
ec
t
an
d
m
is
s
p
elled
wo
r
d
s
,
r
an
d
o
m
l
y
s
am
p
led
f
r
o
m
th
e
I
n
d
o
n
esia
New
s
Data
s
et
av
ailab
le
o
n
Kag
g
le
(
h
ttp
s
://
www.
k
ag
g
le.
co
m
/d
ata
s
ets/
az
izain
u
n
n
ajib
/in
d
o
n
esia
-
n
ews)
.
Evaluation Warning : The document was created with Spire.PDF for Python.