I
n
te
r
n
ati
o
n
al
Jo
u
r
n
al
o
f
El
e
c
tr
i
c
a
l
an
d
C
o
m
p
u
te
r
En
gi
n
e
e
r
i
n
g
(I
JEC
E
)
V
o
l
.
10
,
N
o
.
2
,
A
p
r
i
l
2020
,
p
p.
2
102
~
210
9
IS
S
N
:
2088
-
8708
,
D
O
I
:
10.
1
1591
/
i
j
e
c
e
.
v
10
i
2
.
pp2
102
-
210
9
2102
Jou
r
n
al
h
o
m
e
pa
ge
:
ht
t
p:
/
/
i
j
e
c
e
.
i
ae
s
c
or
e
.
c
om
/
i
nd
e
x
.
php
/
IJ
E
CE
Im
p
r
o
v
i
n
g
t
h
e
r
o
l
e
o
f
l
a
n
g
u
a
g
e
m
o
d
e
l
i
n
st
a
t
i
st
i
c
a
l
m
a
c
h
i
n
e
t
r
a
n
sl
a
t
i
o
n
(
In
d
o
n
e
s
i
a
n
-
J
a
v
a
n
e
se
)
H
e
r
r
y
S
u
jai
n
i
D
e
pa
r
t
e
m
e
nt
o
f
I
nf
o
r
m
a
t
i
c
s
,
T
a
nj
u
ng
pur
a
U
n
i
v
e
r
s
i
t
y
,
I
do
ne
s
i
a
A
r
ti
c
l
e
I
n
fo
A
B
S
TR
A
C
T
Ar
t
i
c
l
e
h
i
s
t
or
y
:
R
e
c
e
i
v
e
d
M
a
y
4
,
2
019
R
e
v
i
s
e
d
O
c
t
3
0,
2
019
A
c
c
e
pt
e
d
N
o
v
15
,
2019
T
he
s
t
a
t
i
s
t
i
c
a
l
m
a
c
hi
n
e
t
r
a
ns
l
a
t
i
o
n
(
S
M
T
)
i
s
w
i
de
l
y
us
e
d
by
r
e
s
e
a
r
c
he
r
s
a
n
d
pr
a
c
t
i
t
i
o
ne
r
s
i
n
r
e
c
e
n
t
y
e
a
r
s
.
S
M
T
w
o
r
ks
w
i
t
h
qua
l
i
t
y
t
ha
t
i
s
de
t
e
r
m
i
ne
d
by
s
e
v
e
r
a
l
i
m
po
r
t
a
nt
f
a
c
t
o
r
s
,
t
w
o
o
f
w
hi
c
h
a
r
e
l
a
ng
ua
g
e
a
nd
t
r
a
ns
l
a
t
i
o
n
m
o
de
l
.
R
e
s
e
a
r
c
h
o
n
i
m
p
r
o
v
i
ng
t
he
t
r
a
n
s
l
a
t
i
o
n
m
o
de
l
ha
s
b
e
e
n
do
ne
qu
i
t
e
a
l
o
t
,
bu
t
t
he
p
r
o
bl
e
m
o
f
o
pt
i
m
i
z
i
ng
t
he
l
a
ng
ua
g
e
m
o
de
l
f
o
r
us
e
o
n
m
a
c
h
i
ne
t
r
a
n
s
l
a
t
o
r
s
ha
s
no
t
r
e
c
e
i
v
e
d
m
uc
h
a
t
t
e
n
t
i
o
n.
O
n
t
r
a
n
s
l
a
t
o
r
m
a
c
hi
ne
s
,
l
a
ng
ua
g
e
m
o
de
l
s
us
ua
l
l
y
us
e
t
r
i
g
r
a
m
m
o
de
l
s
a
s
s
t
a
nda
r
d
.
I
n
t
h
i
s
pa
pe
r
,
w
e
c
o
nduc
t
e
d
e
xpe
r
i
m
e
nt
s
w
i
t
h
f
o
ur
s
t
r
a
t
e
g
i
e
s
t
o
a
na
l
y
z
e
t
he
r
o
l
e
o
f
t
he
l
a
ng
ua
g
e
m
o
de
l
us
e
d
i
n
t
he
I
ndo
ne
s
i
a
n
-
J
a
v
a
ne
s
e
t
r
a
n
s
l
a
t
i
o
n
m
a
c
hi
n
e
a
n
d
s
ho
w
i
m
pr
o
v
e
m
e
nt
c
om
pa
r
e
d
t
o
t
he
b
a
s
e
l
i
ne
s
y
s
t
e
m
w
i
t
h
t
he
s
t
a
n
da
r
d
l
a
ng
ua
g
e
m
o
de
l
.
T
he
r
e
s
u
l
t
s
o
f
t
hi
s
r
e
s
e
a
r
c
h
i
nd
i
c
a
t
e
t
ha
t
t
he
u
s
e
o
f
3
-
g
r
a
m
l
a
ng
ua
g
e
m
o
de
l
s
i
s
hi
g
h
l
y
r
e
c
o
m
m
e
nde
d
i
n
S
M
T
.
Ke
y
w
or
d
s
:
In
do
n
e
s
i
a
n
-
J
a
v
a
n
e
s
e
l
a
n
gu
a
ge
m
o
de
l
S
t
a
t
i
s
t
i
c
a
l
m
a
c
h
i
n
e
t
ra
n
s
l
a
t
i
o
n
C
opy
r
i
gh
t
©
2020
I
n
s
t
i
t
ut
e
o
f
A
dv
anc
e
d
E
ng
i
ne
e
r
i
ng
and
S
c
i
e
nc
e
.
A
l
l
r
i
gh
t
s
r
e
s
e
r
v
e
d
.
Cor
r
e
s
pon
di
n
g
Au
t
h
or
:
H
e
rr
y
S
uj
a
i
n
i
,
D
e
pa
rt
m
e
n
t
o
f
In
f
o
r
m
a
t
i
c
s
,
T
a
n
j
u
n
gp
u
r
a
U
n
i
v
e
r
s
i
t
y
,
J
l
.
P
r
o
f
.
D
r.
H
.
H
a
da
ri
N
a
w
a
w
i
,
P
o
n
t
i
a
na
k
78124
,
I
n
do
n
e
s
i
a
.
E
m
a
i
l
:
hs
@
u
nt
t
a
n.
a
c
.
i
d
1.
I
N
TR
O
D
U
C
TI
O
N
S
t
a
t
i
s
t
i
c
a
l
m
a
c
hi
n
e
t
ra
n
s
l
a
t
i
o
n
(S
M
T
)
o
r
k
n
o
w
n
a
s
s
t
a
t
i
s
t
i
c
a
l
-
b
a
s
e
d
m
a
c
hi
n
e
t
r
a
n
s
l
a
t
i
o
n
,
i
s
a
pa
ra
di
g
m
o
f
m
a
c
h
i
n
e
t
ra
n
s
l
a
t
i
o
n
w
h
e
r
e
t
h
e
i
nt
e
rp
r
e
t
a
t
i
o
n
i
s
c
r
e
a
t
e
d
de
pe
n
de
n
t
on
a
s
t
a
t
i
s
t
i
c
a
l
m
o
de
l
w
h
i
c
h
pa
ra
m
e
t
e
r
s
c
o
m
e
f
r
o
m
b
i
l
i
ngua
l
c
o
r
pus
(pa
ra
l
l
e
l
c
o
r
p
us
)
a
na
l
y
s
i
s
.
Co
r
pus
i
s
a
c
o
l
l
e
c
t
i
o
n
o
r
s
a
m
pl
e
o
f
w
r
i
t
t
e
n
o
r
o
r
a
l
t
e
xt
i
n
t
h
e
f
o
r
m
o
f
da
t
a
t
ha
t
c
a
n
b
e
r
e
a
d
b
y
us
i
n
g
a
s
e
t
o
f
m
a
c
h
i
n
e
s
a
nd
c
a
n
b
e
n
o
t
e
d
i
n
t
h
e
fo
r
m
o
f
v
a
ri
o
us
l
i
n
g
u
i
s
t
i
c
i
n
f
o
r
m
a
t
i
o
n
f
o
r
m
s
[1].
A
q
ua
l
i
t
y
c
o
r
pus
g
r
e
a
t
l
y
i
n
f
l
ue
n
c
e
s
t
h
e
o
ut
c
o
m
e
of
a
s
t
a
t
i
s
t
i
c
a
l
o
r
n
e
u
ra
l
-
b
a
s
e
d
t
ra
n
s
l
a
t
o
r
m
a
c
h
i
n
e
.
M
a
n
y
pr
e
v
i
o
us
r
e
s
e
a
r
c
h
e
r
s
ha
v
e
e
xpe
r
i
m
e
nt
e
d
w
i
t
h
i
m
p
r
o
v
i
n
g
t
h
e
qu
a
l
i
t
y
of
t
h
e
c
o
r
pus
[
2
-
6
].
T
h
e
b
e
s
t
h
y
po
t
h
e
s
i
s
f
o
r
e
a
c
h
i
nput
o
f
s
e
n
t
e
n
c
e
f
i
s
t
h
e
go
a
l
o
f
b
i
l
i
n
g
ua
l
c
o
r
pus
a
na
l
y
s
i
s
by
:
(1)
(
̅
|
̅
)
i
s
a
t
ra
n
s
l
a
t
i
o
n
m
o
de
l
t
ha
t
e
xp
r
e
s
s
e
s
t
h
e
p
r
o
b
a
b
i
l
i
t
y
o
f
t
h
e
r
e
l
a
t
i
o
n
s
h
i
p
b
e
t
w
e
e
n
t
h
e
s
o
ur
c
e
l
a
n
g
ua
ge
a
n
d
t
h
e
t
a
r
ge
t
l
a
ngua
ge
.
L
a
n
gu
a
ge
m
o
de
l
s
t
h
a
t
de
t
e
rm
i
n
e
t
h
e
pr
o
b
a
b
i
l
i
t
y
of
s
t
r
i
n
gs
i
n
t
h
e
t
a
r
ge
t
l
a
n
gu
a
ge
a
r
e
de
n
o
t
e
d
by
̅
,
n
o
rm
a
l
l
y
us
e
s
t
h
e
s
t
a
nda
r
d
w
o
r
d
o
f
t
ri
g
ra
m
m
o
d
e
l
f
r
o
m
:
(2)
w
h
i
c
h
̅
=
e
1
,
.
.
.
,
e
l
.
I
n
t
h
e
t
r
i
g
r
a
m
m
o
de
l
f
o
r
m
,
e
a
c
h
w
o
r
d
i
s
p
r
e
di
c
t
e
d
b
a
s
e
d
o
n
t
h
e
p
r
e
v
i
o
us
t
w
o
-
w
o
r
d
hi
s
t
o
r
y
.
Evaluation Warning : The document was created with Spire.PDF for Python.
Int
J
E
l
e
c
&
Co
m
p
E
n
g
IS
S
N
:
2088
-
8708
Im
pr
ov
i
ng
t
he
r
ol
e
o
f
l
angu
age
m
od
e
l
i
n
s
t
a
t
i
s
t
i
c
a
l
m
ac
h
i
ne
t
r
ans
l
at
i
on
…
(
H
e
r
r
y
Su
j
ai
ni
)
2103
A
l
t
h
o
ug
h
m
a
c
h
i
n
e
t
ra
n
s
l
a
t
o
r
m
o
de
l
s
h
a
v
e
c
o
n
t
i
n
ue
d
t
o
de
ve
l
o
p
i
n
r
e
c
e
n
t
y
e
a
r
s
,
s
t
a
t
i
s
t
i
c
a
l
m
a
c
h
i
n
e
t
r
a
n
s
l
a
t
i
o
n
(S
M
T
)
c
o
nt
i
nue
s
t
o
gr
o
w
ra
pi
d
l
y
,
w
i
t
h
m
o
r
e
a
n
d
m
o
r
e
p
r
o
po
s
e
d
n
e
w
t
ra
n
s
l
a
t
i
o
n
m
o
de
l
s
b
e
i
n
g
pra
c
t
i
c
e
d
i
n
v
a
ri
o
us
l
a
n
gu
a
g
es
[7
-
9]
.
M
o
s
t
o
f
t
h
e
w
o
r
k
i
n
SMT
c
o
n
c
e
n
t
r
a
t
e
s
o
n
de
v
e
l
o
pi
n
g
b
e
t
t
e
r
t
ra
n
s
l
a
t
i
o
n
m
o
de
l
s
.
L
i
t
t
l
e
e
xe
rt
i
o
n
ha
s
b
e
e
n
m
a
de
t
o
m
a
x
i
m
i
z
e
t
h
e
r
o
l
e
of
l
a
n
gu
a
ge
m
o
de
l
i
n
g
f
o
r
m
a
c
h
i
n
e
t
r
a
n
s
l
a
t
i
o
n.
T
h
e
pu
r
po
s
e
of
t
h
i
s
r
e
s
e
a
r
c
h
w
a
s
t
o
i
m
p
r
o
v
e
t
h
e
r
o
l
e
of
l
a
n
gu
a
ge
m
o
de
l
i
ng
,
w
hi
c
h
i
n
t
u
rn
w
i
l
l
i
m
p
r
o
v
e
t
h
e
a
c
c
u
r
a
c
y
o
f
t
h
e
t
ra
n
s
l
a
t
i
o
n
r
e
s
ul
t
s
o
f
a
n
S
MT
.
F
i
g
u
r
e
1
s
h
o
w
s
t
h
e
ge
n
e
r
a
l
s
t
a
t
i
s
t
i
c
a
l
l
a
n
gu
a
g
e
m
a
c
h
i
n
e
a
r
c
hi
t
e
c
t
u
r
e
.
T
h
e
de
c
o
de
r
f
un
c
t
i
o
n
s
a
s
a
t
ra
n
s
l
a
t
o
r
m
a
c
hi
n
e
w
h
o
s
e
j
ob
i
t
i
s
t
o
t
ra
n
s
l
a
t
e
s
e
nt
e
n
c
e
s
f
r
o
m
o
n
e
l
a
ngua
ge
t
o
a
n
o
t
h
e
r
.
T
h
e
r
e
s
ul
t
s
o
f
t
h
e
w
o
r
k
o
f
t
h
e
de
c
o
de
r
c
a
n
d
i
f
fe
r
f
r
o
m
o
n
e
a
n
o
t
h
e
r.
T
h
e
s
e
re
s
ul
t
s
a
r
e
i
n
f
l
ue
n
c
e
d
by
t
h
e
m
o
de
l
s
us
e
d,
na
m
e
l
y
t
h
e
t
r
a
n
s
l
a
t
i
o
n
m
o
de
l
(T
M
)
a
nd
t
h
e
l
a
n
g
ua
ge
m
o
de
l
(L
M
)
a
s
t
h
e
m
a
i
n
m
o
de
l
,
a
n
d
t
h
e
f
e
a
t
u
r
e
m
o
de
l
(F
M
)
b
e
s
i
de
s
.
T
M
i
s
ge
n
e
r
a
t
e
d
t
hr
o
ug
h
t
h
e
t
r
a
i
ni
n
g
p
r
o
c
e
s
s
of
a
pa
r
a
l
l
e
l
c
o
r
pus
,
w
hi
l
e
t
h
e
t
ra
i
ni
n
g
p
r
o
c
e
s
s
of
a
m
o
n
o
l
i
ngua
l
c
o
r
pus
f
r
o
m
t
h
e
t
a
r
ge
t
l
a
n
gu
a
ge
ge
n
e
r
a
t
e
d
LM
.
F
M
i
s
us
ua
l
l
y
us
e
d
a
s
a
n
e
f
fo
r
t
t
o
i
m
p
r
o
v
e
t
h
e
a
c
c
ur
a
c
y
of
m
a
c
h
i
n
e
t
ra
n
s
l
a
t
o
r
s
by
a
ddi
n
g
l
i
ngui
s
t
i
c
fe
a
t
u
r
e
s
s
uc
h
a
s
P
a
r
t
o
f
S
p
e
e
c
h
(P
o
S
)
[10
-
12].
T
h
e
ge
n
e
ra
t
e
d
P
o
S
c
a
n
b
e
d
o
n
e
w
i
t
h
a
s
upe
r
v
i
s
e
d
o
r
un
s
upe
rv
i
s
e
d
a
ppr
o
a
c
h
[13]
.
T
h
e
m
a
i
n
s
y
s
t
e
m
f
un
c
t
i
o
n
s
a
s
a
t
ra
n
s
l
a
t
o
r
m
a
c
h
i
n
e
t
o
p
r
o
duc
e
t
h
e
t
a
r
ge
t
l
a
n
gu
a
ge
f
r
o
m
s
e
n
t
e
n
c
e
i
n
pu
t
i
n
t
h
e
s
o
ur
c
e
l
a
ngua
ge
c
a
l
l
e
d
t
h
e
de
c
o
de
r
.
A
s
s
h
o
w
n
i
n
F
i
gu
r
e
1,
t
h
e
pa
ra
l
l
e
l
c
o
r
p
us
i
s
t
h
e
p
r
i
m
a
r
y
so
ur
c
e
fo
r
b
ui
l
di
ng
a
n
S
M
T
,
w
hi
l
e
t
h
e
m
o
n
o
l
i
ngua
l
c
o
r
pus
c
a
n
us
e
s
e
nt
e
n
c
e
s
t
ha
t
a
r
e
o
n
t
h
e
t
a
r
ge
t
s
i
de
o
f
t
h
e
pa
ra
l
l
e
l
c
o
r
pus
.
T
h
e
s
i
z
e
o
f
t
h
e
m
o
n
o
l
i
n
gu
a
l
c
o
r
pus
c
a
n
b
e
e
n
l
a
r
ge
d
by
a
ddi
n
g
o
t
h
e
r
s
e
nt
e
n
c
e
s
i
n
t
h
e
s
a
m
e
l
a
n
gu
a
ge
,
e
v
e
n
t
h
o
ug
h
i
t
do
e
s
n
o
t
ha
v
e
a
pa
i
r
i
n
t
h
e
p
a
r
a
l
l
e
l
c
o
r
pus
.
F
i
gu
r
e
1
.
SMT
a
r
c
hi
t
e
c
t
u
r
e
S
e
ve
r
a
l
s
t
udi
e
s
h
a
v
e
b
e
e
n
c
o
n
duc
t
e
d
t
o
i
m
p
r
o
v
e
t
h
e
r
o
l
e
of
l
i
n
g
ui
s
t
i
c
m
o
de
l
s
i
n
v
a
r
i
o
us
l
a
n
gu
a
ge
s
a
n
d
m
e
t
h
o
ds
.
Y
u
e
t
a
l
.
[14]
e
xpl
a
i
n
ed
l
a
n
gu
a
ge
m
o
de
l
s
t
ha
t
t
r
i
gge
r
e
d
n
e
w
t
o
pi
c
s
by
c
a
l
c
ul
a
t
i
n
g
c
o
n
t
e
xt
s
a
n
d
t
o
pi
c
s
a
n
d
e
s
t
i
m
a
t
e
n
-
g
ra
m
p
r
o
b
a
b
i
l
i
t
i
e
s
u
n
de
r
a
gi
v
e
n
t
o
pi
c
a
nd
a
dj
us
t
l
a
ngua
ge
m
o
de
l
s
c
o
r
e
s
b
a
s
e
d
o
n
t
h
e
di
s
t
ri
b
ut
i
o
n
o
f
di
f
fe
r
e
n
t
t
o
pi
c
s
o
n
l
i
n
e
.
T
h
e
r
e
s
ul
t
i
ng
t
ra
n
s
l
a
t
i
o
n
p
r
o
v
e
d
t
o
i
m
p
r
o
v
e
t
h
e
h
y
po
t
h
e
s
i
s
c
o
n
s
i
de
r
e
d
b
e
s
t
by
t
h
e
f
i
r
s
t
s
t
a
ge
o
f
t
h
e
s
y
s
t
e
m
.
Z
ha
n
g
e
t
al
.
[15]
ha
ve
r
e
s
e
a
r
c
h
e
d
b
y
i
m
pr
o
v
i
n
g
t
h
e
c
o
di
n
g
o
f
a
ut
o
m
a
t
e
d
v
e
t
e
r
i
na
r
y
di
a
gn
o
s
e
s
t
hr
o
ug
h
l
a
r
ge
-
s
c
a
l
e
l
a
ngua
ge
m
o
de
l
i
n
g
.
T
h
e
a
l
go
ri
t
hm
p
r
o
po
s
e
d
by
t
h
e
m
a
dd
r
e
s
s
e
s
i
m
po
r
t
a
n
t
c
h
a
l
l
e
n
ge
s
i
n
v
e
t
e
r
i
n
a
r
y
m
e
di
c
i
n
e
a
n
d
t
r
a
i
n
i
n
g
i
n
u
n
s
upe
r
v
i
s
e
d
l
e
a
rni
n
g
f
o
r
c
l
i
n
i
c
a
l
l
a
n
gu
a
ge
de
v
e
l
o
pm
e
n
t
.
M
o
h
a
g
h
e
g
h
[16]
r
e
po
r
t
e
d
i
m
p
r
o
v
e
d
a
c
c
ur
a
c
y
by
e
nh
a
n
c
i
ng
t
h
e
r
o
l
e
of
t
h
e
l
a
n
gu
a
ge
m
o
de
l
i
n
t
h
e
E
n
g
l
i
s
h
-
P
e
r
s
i
a
n
t
r
a
n
s
l
a
t
o
r
m
a
c
hi
n
e
.
M
o
n
z
[
17]
r
e
po
rt
e
d
i
m
p
r
o
v
e
d
a
c
c
ur
a
c
y
by
e
n
ha
n
c
i
n
g
t
h
e
r
o
l
e
o
f
t
h
e
l
a
n
gu
a
ge
m
o
de
l
i
n
A
ra
b
i
c
-
a
n
d
C
h
i
n
e
s
e
-
to
-
E
n
gl
i
s
h
t
r
a
n
s
l
a
t
o
r
m
a
c
hi
n
e
s
.
B
a
n
e
r
j
e
e
e
t
al
.
[18]
r
e
po
rt
e
d
t
h
e
i
r
r
e
s
e
a
r
c
h
t
o
i
m
p
r
o
v
e
t
h
e
l
a
ngua
ge
m
o
de
l
by
l
e
a
rn
i
ng
f
r
o
m
s
pe
e
c
h
r
e
c
o
gn
i
t
i
o
n
m
i
s
t
a
ke
s
i
n
a
l
i
s
t
e
n
i
ng
r
e
a
di
n
g
t
ut
o
r
.
S
uj
a
i
ni
e
t
a
l
.
[
19
]
r
e
po
rt
e
d
t
h
e
r
e
s
u
l
t
s
o
f
t
h
e
i
r
r
e
s
e
a
r
c
h
t
o
i
m
p
r
o
v
e
t
h
e
a
c
c
ur
a
c
y
o
f
m
a
c
h
i
n
e
t
ra
n
s
l
a
t
o
r
s
by
us
i
n
g
t
h
e
p
a
rt
o
f
s
pe
e
c
h
f
e
a
t
ur
e
s
.
T
h
e
r
e
s
ul
t
s
o
f
t
hi
s
s
t
udy
c
a
n
i
n
c
r
e
a
s
e
a
c
c
ura
c
y
b
y
6.
45%
w
h
e
n
c
o
m
pa
r
e
d
t
o
m
a
c
h
i
n
e
t
r
a
n
s
l
a
t
o
r
s
w
i
t
h
o
ut
us
i
ng
pa
rt
o
f
s
pe
e
c
h
.
J
a
y
a
a
nd
G
upt
a
[
20
]
p
r
o
po
s
e
d
a
b
e
t
t
e
r
qua
l
i
t
y
S
M
T
t
h
a
t
w
a
s
i
m
p
r
o
v
e
d
by
2
p
o
i
n
t
s
i
n
t
h
e
E
n
g
l
i
s
h
t
o
H
i
n
di
s
y
s
t
e
m
a
n
d
2.
93
po
i
n
t
s
i
n
t
h
e
H
i
n
-
E
ng
s
y
s
t
e
m
.
T
h
e
s
e
r
e
s
ul
t
s
w
e
r
e
o
b
t
a
i
n
e
d
a
s
t
h
e
y
e
xpl
o
r
e
d
t
h
e
c
o
r
pus
a
ugm
e
n
t
a
t
i
o
n
a
pp
r
o
a
c
h
f
o
r
t
h
e
E
ngl
i
s
h
a
nd
H
i
n
d
i
T
w
o
-
W
a
y
S
M
T
.
Evaluation Warning : The document was created with Spire.PDF for Python.
IS
S
N
:
2088
-
8708
Int
J
E
l
e
c
&
Co
m
p
E
n
g
,
V
o
l
.
10
,
N
o
.
2
,
A
p
ri
l
2020
:
2
102
-
210
9
2104
T
h
e
l
a
n
gu
a
ge
m
o
de
l
i
s
de
s
i
gn
e
d
t
o
ob
t
a
i
n
t
h
e
o
c
c
urr
e
n
c
e
pr
o
b
a
b
i
l
i
t
y
of
w
o
r
ds
(o
r
t
o
ke
n
).
If
W
1
=
(
w
1
,
.
.
.
,
w
L
)
s
h
ow
s
t
h
e
s
t
ri
n
g
t
o
ke
n
o
f
L
o
n
f
i
xe
d
vo
c
a
b
ul
a
r
y
.
T
h
e
n
-
g
ra
m
l
a
n
gu
a
ge
m
o
de
l
pr
o
v
i
de
s
pr
o
b
a
b
i
l
i
t
y
t
o
a
c
c
o
r
di
n
g
t
o
:
(3)
w
h
e
r
e
t
h
e
a
pp
r
o
xi
m
a
t
i
o
n
r
e
f
l
e
c
t
s
M
a
r
ko
v
’s
a
s
s
um
pt
i
o
n
t
ha
t
o
nl
y
n
-
1
t
o
ke
n
t
ha
t
t
h
e
n
e
w
e
s
t
r
e
l
e
v
a
n
t
i
n
pr
e
di
c
t
i
n
g
t
h
e
n
e
x
t
w
o
r
d.
F
o
r
e
a
c
h
w
s
u
b
s
t
r
i
ng,
f
o
r
e
xa
m
pl
e
,
f
(w
)
s
h
ow
s
t
h
e
fr
e
qu
e
n
c
y
of
s
ub
s
t
r
i
n
g
o
c
c
ur
r
e
n
c
e
i
n
t
h
e
s
pe
c
i
f
i
e
d
t
a
r
ge
t
l
a
ngua
ge
s
e
que
n
c
e
,
us
ua
l
l
y
v
e
r
y
l
o
n
g
,
w
h
i
c
h
c
a
l
l
e
d
t
ra
i
ni
n
g
da
t
a
.
T
h
e
m
a
xi
m
um
-
l
i
ke
l
i
h
o
o
d
p
r
o
b
a
b
i
l
i
t
y
fo
r
n
-
g
ra
m
i
s
gi
v
e
n
by
i
t
s
r
e
l
a
t
i
v
e
f
r
e
que
n
c
y
.
(
4
)
In
p
ri
n
c
i
p
l
e
,
t
h
e
p
r
e
di
c
t
i
v
e
a
c
c
ur
a
c
y
of
t
h
e
l
a
n
gua
ge
m
o
de
l
c
a
n
b
e
e
n
ha
n
c
e
d
by
i
n
c
r
e
a
s
i
ng
t
h
e
o
r
de
r
o
f
n
-
g
ra
m
s
[21]
.
H
ow
e
v
e
r
,
unde
r
c
e
rt
a
i
n
c
o
n
di
t
i
o
n
s
,
t
hi
s
c
a
n
r
e
duc
e
t
h
e
a
c
c
u
r
a
c
y
of
t
r
a
n
s
l
a
t
i
o
n
w
h
e
n
us
i
n
g
c
o
m
pl
e
x
da
t
a
,
e
s
pe
c
i
a
l
l
y
i
f
t
h
e
r
e
a
r
e
m
a
n
y
e
r
r
o
r
s
i
n
c
o
r
pus
da
t
a
.
T
h
i
s
s
t
udy
di
s
c
us
s
e
s
t
h
e
b
e
s
t
a
c
c
ur
a
c
y
t
h
a
t
c
a
n
b
e
pr
o
duc
e
d
by
m
a
c
hi
n
e
t
ra
n
s
l
a
t
o
r
s
b
y
c
o
n
duc
t
i
n
g
e
xpe
r
i
m
e
n
t
s
o
n
t
h
e
us
e
o
f
t
h
e
o
rde
r
o
f
n
-
g
r
a
m
s
o
n
L
M
.
2.
R
ES
EA
R
C
H
M
ET
H
O
D
2.
1
.
Ex
p
e
r
i
m
e
n
ta
l
s
ta
ge
s
T
h
e
t
r
a
i
n
i
n
g
d
a
t
a
i
s
a
p
a
r
a
l
l
e
l
c
o
r
pus
o
f
In
do
n
e
s
i
a
–
K
r
o
m
o
J
a
v
a
n
e
s
e
l
a
n
gu
a
ge
t
a
ke
n
f
r
o
m
f
o
l
kl
o
r
e
m
a
n
u
a
l
l
y
t
r
a
n
s
l
a
t
e
d
a
s
m
a
n
y
a
s
5108
s
e
nt
e
n
c
e
s
.
I
n
t
h
e
p
r
o
c
e
s
s
of
t
r
a
i
n
i
ng,
4500
pa
i
r
s
o
f
s
e
n
t
e
n
c
e
s
a
n
d
608
pa
i
r
s
o
f
s
e
n
t
e
n
c
e
s
w
e
r
e
us
e
d
fo
r
t
h
e
t
e
s
t
i
ng
p
r
o
c
e
s
s
.
T
h
e
e
xpe
r
i
m
e
n
t
a
l
s
t
a
ge
s
c
o
n
duc
t
e
d
c
a
n
b
e
s
e
e
n
i
n
F
i
g
u
r
e
2.
Co
rpus
p
r
e
p
a
r
a
t
i
o
n
(p
r
e
p
r
o
c
e
s
s
i
n
g)
w
a
s
c
o
n
du
c
t
e
d
by
pe
r
fo
r
m
i
ng
t
h
e
p
r
o
c
e
s
s
of
c
l
e
a
n
i
ng,
t
o
ke
n
i
z
i
n
g
,
a
nd
l
o
w
e
r
c
a
s
i
ng
t
o
t
h
e
pa
ra
l
l
e
l
c
o
r
pus
t
ha
t
h
a
s
b
e
e
n
p
r
e
pa
r
e
d.
T
h
e
l
a
n
gu
a
ge
m
o
de
l
us
e
d
i
n
t
h
e
b
a
s
e
l
i
n
e
s
y
s
t
e
m
w
a
s
t
h
e
t
r
i
g
ra
m
m
o
de
l
of
J
a
v
a
n
e
s
e
l
a
n
g
ua
ge
t
r
a
i
n
e
d
by
us
i
n
g
t
o
o
l
ki
t
S
R
IL
M
[22],
w
h
i
l
e
pa
r
a
l
l
e
l
c
o
r
pus
t
ha
t
w
a
s
r
e
a
dy
t
o
us
e
w
a
s
t
h
e
n
t
ra
i
n
e
d
t
o
ob
t
a
i
n
w
o
r
d
a
l
i
g
nm
e
n
t
s
,
p
hra
s
e
t
a
b
l
e
,
l
a
n
gu
a
ge
m
o
de
l
,
a
n
d
m
o
de
l
c
o
m
b
i
na
t
i
o
n
w
e
i
gh
t
s
.
T
h
e
b
a
s
e
l
i
n
e
us
e
d
i
n
t
h
i
s
r
e
s
e
a
r
c
h
w
a
s
t
ra
i
n
e
d
by
us
i
n
g
s
t
a
nda
rd
t
o
o
l
s
,
n
a
m
e
l
y
G
IZ
A
+
+
[23],
t
o
t
ra
i
n
t
h
e
w
o
r
d
a
l
i
g
nm
e
nt
a
n
d
M
o
s
e
s
fo
r
p
hr
a
s
e
-
b
a
s
e
d
c
o
di
n
g.
M
o
s
e
s
i
s
a
t
o
o
l
t
h
a
t
i
s
a
n
i
m
pl
e
m
e
n
t
a
t
i
o
n
o
f
S
t
a
t
i
s
t
i
c
M
a
c
h
i
n
e
T
ra
n
s
l
a
t
i
o
n
.
M
o
s
e
s
i
s
us
e
d
t
o
t
ra
i
ni
n
g
a
s
t
a
t
i
s
t
i
c
a
l
m
o
de
l
of
t
r
a
n
s
l
a
t
e
d
t
e
x
t
f
r
o
m
t
h
e
s
o
ur
c
e
l
a
n
gu
a
ge
t
o
t
h
e
t
a
r
ge
t
l
a
n
gu
a
ge
.
I
n
t
ra
n
s
l
a
t
i
n
g
t
h
e
l
a
n
gu
a
ge
,
M
o
s
e
s
r
e
qui
r
e
s
a
c
o
r
pus
i
n
t
w
o
l
a
n
gu
a
ge
s
,
s
o
u
r
c
e
l
a
n
gu
a
ge
a
nd
t
a
r
ge
t
l
a
n
gu
a
ge
.
M
o
s
e
s
i
s
r
e
l
e
a
s
e
d
u
n
de
r
t
h
e
l
i
c
e
n
s
e
pf
L
G
P
L
(L
e
s
s
e
r
G
e
n
e
ra
l
P
ub
l
i
c
L
i
c
e
n
s
e
)
a
n
d
i
s
a
v
a
i
l
a
b
l
e
a
s
s
o
urc
e
c
o
de
a
n
d
b
i
n
a
r
y
f
o
r
W
i
n
do
w
s
a
n
d
L
i
n
ux
.
It
s
de
v
e
l
o
pm
e
n
t
i
s
s
uppo
rt
e
d
by
t
h
e
E
u
r
o
M
a
t
ri
x
p
r
o
j
e
c
t
,
w
i
t
h
t
h
e
f
un
di
ng
by
E
ur
o
pe
a
n
Co
m
m
i
s
s
i
o
n
[
24].
T
h
e
d
e
c
o
de
r
,
a
s
a
t
ra
n
s
l
a
t
o
r
m
a
c
hi
n
e
,
w
a
s
s
e
t
fo
l
l
ow
i
n
g
t
h
e
e
xpe
r
i
m
e
n
t
a
l
s
t
ra
t
e
gy
c
o
n
duc
t
e
d,
w
h
i
c
h
w
a
s
b
y
c
h
a
ngi
n
g
t
h
e
l
a
n
gu
a
ge
m
o
de
l
v
a
r
i
a
b
l
e
s
us
e
d.
F
o
r
e
a
c
h
s
e
t
t
i
ng,
t
e
s
t
i
n
g
w
a
s
pe
r
f
o
r
m
e
d
by
i
n
p
ut
t
i
n
g
608
s
e
n
t
e
n
c
e
s
t
h
a
t
h
a
d
b
e
e
n
p
r
e
pa
r
e
d
p
r
e
v
i
o
us
l
y
.
T
h
e
t
e
s
t
s
w
e
r
e
pe
r
f
o
r
m
e
d
us
i
n
g
t
h
e
B
L
E
U
a
ut
o
m
a
t
i
c
e
v
a
l
ua
t
i
o
n
m
e
t
h
o
d
[
25
]
.
F
i
gu
r
e
2
.
E
xp
e
r
i
m
e
n
t
a
l
s
t
a
ge
s
Evaluation Warning : The document was created with Spire.PDF for Python.
Int
J
E
l
e
c
&
Co
m
p
E
n
g
IS
S
N
:
2088
-
8708
Im
pr
ov
i
ng
t
he
r
ol
e
o
f
l
angu
age
m
od
e
l
i
n
s
t
a
t
i
s
t
i
c
a
l
m
ac
h
i
ne
t
r
ans
l
at
i
on
…
(
H
e
r
r
y
Su
j
ai
ni
)
2105
2.
2
.
Ex
p
e
r
i
m
e
n
t
s
tr
at
e
gy
T
o
s
e
e
t
h
e
r
o
l
e
of
t
h
e
l
a
ngua
ge
m
o
de
l
us
e
d
i
n
I
n
do
n
e
s
i
a
n
-
J
a
v
a
SMT
,
i
n
t
hi
s
e
xpe
r
i
m
e
nt
,
f
o
ur
s
t
ra
t
e
gi
e
s
w
e
r
e
pe
r
f
o
r
m
e
d
.
a.
T
h
e
l
a
n
gu
a
ge
m
o
de
l
w
a
s
t
r
a
i
n
e
d
f
r
o
m
4500
s
e
n
t
e
n
c
e
s
o
f
t
h
e
pa
r
a
l
l
e
l
c
o
r
p
us
t
a
r
ge
t
;
i
n
o
t
h
e
r
w
o
r
ds
,
t
h
e
t
e
s
t
r
e
f
e
r
e
n
c
e
s
e
n
t
e
n
c
e
w
a
s
n
o
t
i
n
c
l
ude
d
i
n
t
h
e
t
ra
i
ni
n
g
.
F
u
rt
he
r
m
o
r
e
,
t
hi
s
f
i
r
s
t
s
t
r
a
t
e
gy
w
a
s
t
e
s
t
e
d
fo
r
3
t
o
7
-
g
r
a
m
m
o
de
l
s
.
b.
T
h
e
l
a
n
g
ua
ge
m
o
de
l
w
a
s
t
ra
i
n
e
d
f
r
o
m
4500
s
e
n
t
e
n
c
e
s
of
pa
r
a
l
l
e
l
c
o
r
pus
t
a
r
ge
t
p
l
us
608
r
e
f
e
r
e
n
c
e
s
e
n
t
e
n
c
e
s
;
i
n
o
t
h
e
r
w
o
r
ds
,
t
h
e
t
e
s
t
r
e
f
e
r
e
n
c
e
s
e
n
t
e
n
c
e
w
a
s
i
nc
l
ude
d
i
n
t
h
e
t
ra
i
ni
n
g
.
F
urt
h
e
r
m
o
r
e
,
t
h
i
s
f
i
r
s
t
s
t
ra
t
e
gy
w
a
s
t
e
s
t
e
d
fo
r
3
t
o
7
-
g
ra
m
m
o
de
l
s
.
c.
T
h
e
l
a
n
g
ua
ge
m
o
de
l
w
a
s
t
r
a
i
n
e
d
f
r
o
m
608
r
e
f
e
r
e
n
c
e
s
e
n
t
e
n
c
e
s
a
n
d
3892
s
e
n
t
e
n
c
e
s
of
pa
ra
l
l
e
l
c
o
r
pus
t
a
r
ge
t
,
t
h
e
n
a
d
de
d
w
i
t
h
10
0
s
e
nt
e
n
c
e
s
of
t
h
e
r
e
m
a
i
ni
n
g
pa
r
a
l
l
e
l
c
o
r
p
us
t
a
r
ge
t
s
f
o
r
e
a
c
h
e
xpe
r
i
m
e
nt
.
S
i
x
e
xpe
r
i
m
e
nt
s
w
e
r
e
a
dde
d
;
t
h
e
r
e
fo
r
e
,
t
h
e
c
o
r
pus
us
e
d
i
n
e
a
c
h
e
xpe
ri
m
e
n
t
w
a
s
4600,
470
0,
4800
,
4900
,
5000,
a
nd
5
100
s
e
n
t
e
n
c
e
s
.
d.
T
h
e
l
a
n
gu
a
ge
m
o
de
l
w
a
s
t
r
a
i
n
e
d
f
r
o
m
4500
t
a
r
ge
t
s
e
nt
e
n
c
e
s
,
t
h
e
n
a
d
de
d
100
r
e
f
e
r
e
n
c
e
s
e
n
t
e
n
c
e
s
fo
r
e
a
c
h
e
xpe
r
i
m
e
nt
.
S
i
x
e
xpe
ri
m
e
n
t
s
w
e
r
e
a
dde
d
;
t
h
e
r
e
f
o
r
e
,
t
h
e
c
o
r
p
us
us
e
d
i
n
e
a
c
h
e
xpe
ri
m
e
n
t
w
a
s
4600
,
4700
,
4800,
490
0,
5000
,
a
n
d
510
0
s
e
n
t
e
n
c
e
s
.
2.
3
.
R
e
s
u
l
t
an
d
d
i
s
c
u
s
s
i
o
n
T
h
e
t
r
a
i
n
i
ng
d
a
t
a
i
s
i
n
t
h
e
f
o
r
m
o
f
t
h
e
I
n
do
n
e
s
i
a
n
-
J
a
v
a
p
a
r
a
l
l
e
l
c
o
r
pus
a
s
s
h
o
w
n
i
n
F
i
g
u
r
e
3
.
T
h
e
l
e
f
t
c
o
l
um
n
i
s
a
c
o
l
l
e
c
t
i
o
n
o
f
s
e
n
t
e
n
c
e
s
i
n
t
h
e
I
n
do
n
e
s
i
a
n
l
a
ngua
ge
,
w
h
i
l
e
t
h
e
r
i
g
ht
c
o
l
um
n
i
s
a
s
e
n
t
e
n
c
e
c
l
us
t
e
r
i
n
J
a
v
a
n
e
s
e
,
w
h
e
r
e
e
a
c
h
l
i
n
e
i
s
a
t
r
a
n
s
l
a
t
i
o
n
o
f
t
h
e
c
o
r
r
e
s
po
n
d
i
ng
s
e
nt
e
n
c
e
.
E
xa
m
pl
e
s
o
f
s
e
n
t
e
n
c
e
s
t
ha
t
ha
v
e
be
e
n
pa
s
s
e
d
t
h
e
pr
o
c
e
s
s
of
c
l
e
a
n
i
n
g
,
t
o
ke
ni
z
i
n
g
,
a
n
d
l
o
w
e
r
c
a
s
i
n
g
a
r
e
:
"
B
ar
u
pu
l
ang
,
K
an
g?
Mana
A
bah?"
T
a
ny
a
N
y
i
It
e
ung
R
e
s
ul
t
:
"
l
agi
m
ul
i
h
,
k
a
ng?
e
nd
i
abah?
"
pi
t
a
k
one
n
y
i
i
t
e
un
g
T
h
e
l
a
n
gu
a
ge
m
o
de
l
w
a
s
ge
n
e
r
a
t
e
d
f
r
o
m
t
h
e
t
ra
i
ni
n
g
p
r
o
c
e
s
s
c
o
n
duc
t
e
d
o
n
t
h
e
t
a
rge
t
l
a
n
gu
a
ge
o
f
t
h
e
pa
r
a
l
l
e
l
c
o
r
pus
,
i
.
e
.
,
J
a
v
a
l
a
n
g
ua
ge
.
A
s
a
b
a
s
e
l
i
n
e
,
a
t
r
i
g
ra
m
(3
-
g
r
a
m
)
t
ra
i
ni
n
g
w
a
s
c
o
n
duc
t
e
d,
t
h
e
n
t
r
a
i
ni
n
g
w
a
s
a
l
s
o
c
o
n
duc
t
e
d
t
o
pr
o
duc
e
a
c
o
m
pa
r
i
s
o
n
m
a
c
hi
n
e
w
i
t
h
4
-
g
r
a
m
,
5
-
g
r
a
m
,
6
-
g
ra
m
,
a
nd
7
-
g
r
a
m
m
o
de
l
s
.
T
h
e
e
xa
m
pl
e
of
t
h
e
3
-
gra
m
l
a
n
gu
a
ge
m
o
de
l
c
a
n
be
fo
un
d
i
n
F
i
g
u
r
e
4
,
w
h
i
l
e
t
h
e
e
xa
m
pl
e
o
f
t
h
e
7
-
g
r
a
m
l
a
ng
ua
ge
m
o
de
l
c
a
n
b
e
f
o
un
d
i
n
F
i
g
u
r
e
5
.
F
o
r
i
n
s
t
a
n
c
e
,
F
i
g
u
r
e
4
.
s
a
y
s
t
h
a
t
t
h
e
p
r
o
b
a
b
i
l
i
t
y
of
t
h
e
f
i
r
s
t
w
o
r
d
i
n
a
s
e
n
t
e
n
c
e
be
i
n
g
"
d
i
n
a
e
s
uke
"
i
s
10
-
0.
3
746
373
=
0.
422,
t
h
e
pr
o
b
a
b
i
l
i
t
y
g
a
ve
t
h
e
pa
i
r
w
o
r
d
"
s
a
w
a
t
a
r
a
d
i
n
a
"
t
h
a
t
t
h
e
n
e
xt
t
hi
n
g
t
h
a
t
h
a
ppe
n
s
i
s
t
h
a
t
t
h
e
s
e
nt
e
n
c
e
e
n
ds
10
-
0
.
736
3669
=
0.
1
83,
a
n
d
s
o
fo
r
t
h
.
F
r
o
m
t
h
e
t
r
a
i
n
i
ng
r
e
s
ul
t
s
,
t
h
e
n
u
m
b
e
r
o
f
t
o
k
e
n
pa
i
r
s
w
i
t
h
t
h
e
i
r
p
r
o
b
a
b
i
l
i
t
i
e
s
f
o
r
e
a
c
h
n
-
g
r
a
m
a
r
e
:
1
-
g
r
a
m
=
5
598,
2
-
g
r
a
m
=
2
6350
,
3
-
g
r
a
m
=
3924
,
4
-
g
r
a
m
=
1768
,
5
-
g
r
a
m
=
6
46,
6
-
g
ra
m
=
18
1
a
n
d
7
-
g
ra
m
=
53
.
L
a
h
i
r
n
y
a
It
o
k
.
L
a
i
re
It
o
k
.
S
e
t
e
l
a
h
N
y
i
It
e
u
n
g
h
a
m
i
l
,
o
ra
n
g
s
e
ru
m
a
h
s
e
m
u
a
d
i
r
e
p
o
t
k
a
n
.
S
a
w
i
s
e
N
y
i
It
e
u
n
g
m
b
o
b
o
t
,
w
o
n
g
s
a
o
m
a
h
k
a
b
e
h
d
i
re
p
o
t
a
k
e
.
M
a
k
l
u
m
n
a
m
a
n
y
a
b
a
ru
h
a
m
i
l
m
u
d
a
,
a
d
a
-
a
d
a
s
a
j
a
y
a
n
g
d
i
m
i
n
t
a
d
a
n
y
a
n
g
a
n
e
h
-
a
n
e
h
.
M
a
k
l
u
m
j
e
n
e
n
g
e
l
a
g
i
n
g
a
n
d
h
e
g
e
n
o
m
,
a
n
a
-
a
n
a
w
a
e
s
i
n
g
d
i
j
a
l
u
k
l
a
n
s
i
n
g
a
n
e
h
-
a
n
e
h
.
H
a
l
i
n
i
t
e
n
t
u
s
a
j
a
m
e
m
b
u
a
t
b
i
n
g
u
n
g
o
ra
n
g
s
e
ru
m
a
h
.
Ba
b
i
k
i
m
e
s
t
h
i
w
a
e
g
a
w
e
b
i
n
g
u
n
g
e
w
o
n
g
s
a
o
m
a
h
.
S
i
K
a
b
a
y
a
n
b
i
n
g
u
n
g
s
e
k
a
l
i
m
e
n
g
h
a
d
a
p
i
s
i
k
a
p
d
a
n
p
e
r
m
i
n
t
a
a
n
m
a
i
n
a
n
S
i
K
a
b
a
y
a
n
b
i
n
g
u
n
g
b
a
n
g
e
t
n
g
a
d
h
e
p
i
s
i
k
e
p
l
a
n
p
a
n
j
a
l
u
k
e
b
o
j
o
n
e
.
S
e
d
a
n
g
A
b
a
h
d
a
n
A
m
b
u
y
a
n
g
s
e
s
u
d
a
h
w
a
n
i
t
a
p
e
n
g
a
l
a
m
a
n
b
i
s
a
m
e
n
g
e
rt
i
h
a
l
i
t
u
.
D
e
n
e
A
b
a
h
l
a
n
A
m
b
u
s
i
n
g
w
i
s
d
u
w
e
p
e
n
g
a
l
a
m
a
n
b
i
s
a
n
g
e
r
t
e
n
i
b
a
b
i
k
u
.
Ba
g
i
S
i
K
a
b
a
y
a
n
,
s
e
m
u
a
i
t
u
m
e
m
b
u
a
t
d
i
ri
n
y
a
s
e
r
b
a
r
e
p
o
t
.
T
u
m
ra
p
e
S
i
K
a
b
a
y
a
n
,
k
a
b
e
h
m
a
u
n
d
a
d
e
k
a
k
e
d
h
e
w
e
k
e
s
a
r
w
a
re
p
o
t
.
P
e
r
m
i
n
t
a
a
n
n
y
a
N
y
i
It
e
u
n
g
h
a
ru
s
c
e
p
a
t
d
i
t
u
ru
t
i
d
e
n
g
a
n
a
l
a
s
a
n
m
e
w
u
j
u
d
k
a
n
b
a
w
a
a
n
j
a
b
a
n
g
b
a
y
i
y
a
n
g
a
d
a
d
i
d
a
l
a
m
p
e
ru
t
n
y
a
.
P
a
n
j
a
l
u
k
e
N
y
i
It
e
u
n
g
k
u
d
u
e
n
g
g
a
l
d
i
t
i
n
d
a
k
a
k
e
k
a
n
t
h
i
a
l
e
s
a
n
m
u
j
u
d
a
k
e
g
a
w
a
n
j
a
b
a
n
g
b
a
y
i
s
i
n
g
a
n
a
i
n
g
n
j
e
r
o
w
e
t
e
n
g
e
.
J
i
k
a
s
u
d
a
h
b
e
g
i
t
u
S
i
K
a
b
a
y
a
n
t
i
d
a
k
b
i
s
a
m
e
n
g
e
l
a
k
.
M
a
n
a
w
a
w
i
s
m
a
n
g
k
o
n
o
S
i
K
a
b
a
y
a
n
o
ra
b
i
s
a
s
u
w
a
l
a
.
S
e
p
e
rt
i
d
i
h
a
ri
i
n
i
,
N
y
i
I
t
e
u
n
g
m
e
n
g
a
t
a
k
a
n
k
e
i
n
g
i
n
a
n
n
y
a
k
e
p
a
d
a
K
a
b
a
y
a
n
y
a
n
g
b
a
ru
p
u
l
a
n
g
d
a
ri
k
e
b
u
n
,
s
e
t
e
l
a
h
m
e
m
b
a
n
t
u
A
b
a
h
m
e
n
a
n
a
m
u
b
i
.
K
a
y
a
i
n
g
d
i
n
a
i
k
i
,
N
y
i
It
e
u
n
g
n
g
a
n
d
h
a
k
a
k
e
p
e
p
i
n
g
i
n
a
n
e
m
a
ra
n
g
K
a
b
a
y
a
n
s
i
n
g
l
a
g
i
m
u
l
i
h
s
a
k
a
k
e
b
o
n
,
s
a
w
i
s
e
m
b
i
y
a
n
t
u
A
b
a
h
n
a
n
d
u
r
p
o
h
u
n
g
.
"
Ba
ru
p
u
l
a
n
g
,
K
a
n
g
?
M
a
n
a
A
b
a
h
?
"
T
a
n
y
a
N
y
i
It
e
u
n
g
.
"
L
a
g
i
m
u
l
i
h
,
K
a
n
g
?
E
n
d
i
A
b
a
h
?
"
P
i
t
a
k
o
n
e
N
y
i
I
t
e
u
n
g
.
"
A
l
h
a
m
d
u
l
i
l
l
a
h
,
b
a
ru
s
a
j
a
s
e
l
e
s
a
i
N
y
i
.
"
"
A
l
h
a
m
d
u
l
i
l
l
a
h
,
l
a
g
i
w
a
e
ra
m
p
u
n
g
N
y
i
.
"
"
A
b
a
h
b
a
ru
b
a
s
u
h
d
i
j
a
m
b
a
n
.
"
"
A
b
a
h
l
a
g
i
w
i
s
u
h
i
n
g
j
a
m
b
a
n
.
"
J
a
w
a
b
S
i
K
a
b
a
y
a
n
d
e
n
g
a
n
d
u
d
u
k
d
i
l
i
n
c
a
k
.
W
a
n
g
s
u
l
a
n
e
S
i
K
a
b
a
y
a
n
k
a
ro
l
u
n
g
g
u
h
i
n
g
l
i
n
c
a
k
.
"
O
,
s
y
u
k
u
rl
a
h
.
K
a
k
a
n
g
a
p
a
m
a
s
i
h
c
a
p
e
k
?
"
"
O
,
s
y
u
k
u
rl
a
h
.
K
a
k
a
n
g
a
p
a
i
s
i
h
k
e
s
e
l
?
"
T
a
n
y
a
N
y
i
It
e
u
n
g
d
e
n
g
a
n
m
e
m
p
e
r
h
a
t
i
k
a
n
d
i
ri
K
a
b
a
y
a
n
.
P
i
t
a
k
o
n
e
N
y
i
I
t
e
u
n
g
k
a
ro
n
g
a
w
a
s
a
k
e
a
w
a
k
e
K
a
b
a
y
a
n
.
"
L
u
m
a
y
a
n
,
N
y
i
,
o
ra
n
g
n
a
m
a
n
y
a
b
e
k
e
rj
a
d
i
k
e
b
u
n
.
"
"
L
u
m
a
y
a
n
,
N
y
i
,
w
o
n
g
j
e
n
e
n
g
e
n
y
a
m
b
u
t
g
a
w
e
i
n
g
k
e
b
o
n
.
"
F
i
gu
r
e
3
.
I
ndo
n
e
s
i
a
n
-
J
a
v
a
p
a
r
a
l
l
e
l
c
o
r
pus
Evaluation Warning : The document was created with Spire.PDF for Python.
IS
S
N
:
2088
-
8708
Int
J
E
l
e
c
&
Co
m
p
E
n
g
,
V
o
l
.
10
,
N
o
.
2
,
A
p
ri
l
2020
:
2
102
-
210
9
2106
F
i
gu
r
e
4
.
3
-
g
r
a
m
l
a
ngua
ge
m
o
de
l
F
i
gu
r
e
5
.
7
-
g
r
a
m
l
a
ngua
ge
m
o
de
l
T
h
e
f
i
r
s
t
e
xpe
r
i
m
e
nt
a
l
s
t
ra
t
e
gy
w
a
s
us
i
n
g
4500
s
e
n
t
e
n
c
e
s
pa
r
a
l
l
e
l
c
o
r
pus
,
a
n
d
4
500
s
e
nt
e
n
c
e
s
m
o
n
o
l
i
n
gu
a
l
c
o
r
p
us
o
f
,
t
h
e
r
e
s
ul
t
s
o
f
t
h
e
e
xpe
r
i
m
e
n
t
s
p
r
o
du
c
e
d
c
a
n
b
e
f
o
un
d
i
n
T
a
b
l
e
1
.
M
a
c
h
i
n
e
1
.
3
m
e
a
n
s
us
i
n
g
s
t
ra
t
e
gy
1
w
i
t
h
3
-
g
r
a
m
;
m
a
c
hi
n
e
1.
4
m
e
a
n
s
us
i
ng
s
t
ra
t
e
g
y
1
w
i
t
h
4
-
g
r
a
m
,
a
n
d
s
o
o
n
.
T
h
e
e
xpe
ri
m
e
n
t
’s
r
e
s
ul
t
s
s
h
o
w
t
h
a
t
w
i
t
h
t
h
e
a
ddi
t
i
o
n
o
f
n
-
g
ra
m
s
i
n
t
h
e
m
o
no
l
i
n
g
ua
l
c
o
r
pus
t
a
ke
n
f
r
o
m
t
h
e
pa
ra
l
l
e
l
c
o
r
pus
,
i
t
do
e
s
n
o
t
s
h
o
w
a
s
i
gn
i
f
i
c
a
n
t
i
n
c
r
e
a
s
e
i
n
a
c
c
ur
a
c
y
(r
e
pr
e
s
e
nt
e
d
by
BL
E
U
v
a
l
ue
).
T
h
e
hi
g
h
e
s
t
v
a
l
ue
o
n
t
h
e
4
-
g
r
a
m
t
o
7
-
g
ra
m
m
o
de
l
c
a
n
o
nl
y
i
n
c
r
e
a
s
e
t
h
e
a
c
c
ura
c
y
of
((32.
46
-
32.
4
2)
/
32
.
42)
*
100%
=
0
.
12%
.
T
h
e
s
e
c
o
n
d
e
xpe
ri
m
e
n
t
a
l
s
t
ra
t
e
g
y
w
a
s
us
i
n
g
4500
s
e
n
t
e
n
c
e
s
pa
ra
l
l
e
l
c
o
r
pus
,
a
n
d
51
08
s
e
nt
e
n
c
e
s
m
o
n
o
l
i
n
gu
a
l
c
o
r
pus
,
t
h
e
r
e
s
ul
t
s
o
f
t
h
e
e
xpe
r
i
m
e
n
t
s
p
r
o
duc
e
d
c
a
n
b
e
fo
un
d
i
n
T
a
b
l
e
2
.
M
a
c
h
i
n
e
2
.
3
m
e
a
n
s
us
i
n
g
s
t
ra
t
e
gy
2
w
i
t
h
3
-
g
r
a
m
;
m
a
c
hi
n
e
2
.
4
m
e
a
n
s
us
i
ng
s
t
ra
t
e
g
y
2
w
i
t
h
4
-
g
r
a
m
,
a
n
d
s
o
o
n
.
T
h
e
e
xpe
ri
m
e
n
t
’s
r
e
s
ul
t
s
s
h
o
w
t
h
a
t
w
i
t
h
t
h
e
a
d
di
t
i
o
n
o
f
n
-
g
r
a
m
s
i
n
t
h
e
m
o
n
o
l
i
n
gu
a
l
c
o
r
pus
t
a
ke
n
f
r
o
m
t
h
e
pa
r
a
l
l
e
l
c
o
r
pus
,
i
t
do
e
s
n
o
t
s
h
o
w
a
n
i
n
c
r
e
a
s
e
i
n
a
c
c
u
r
a
c
y
(r
e
pr
e
s
e
n
t
e
d
by
BL
E
U
v
a
l
ue
),
e
ve
n
l
o
w
e
r
t
ha
n
t
h
e
3
-
g
r
a
m
b
a
s
e
l
i
n
e
.
T
h
e
h
i
g
h
e
s
t
s
c
o
r
e
r
e
m
a
i
n
s
o
n
t
h
e
3
-
g
r
a
m
m
o
de
l
,
w
hi
c
h
i
s
40
.
79
.
T
a
b
l
e
1
.
R
e
s
ul
t
f
r
o
m
s
t
ra
t
e
gy
1
M
a
c
h
i
n
e
n
-
g
ra
m
BL
E
U
S
c
o
r
e
(%
)
1
.3
3
-
g
ra
m
3
2
.
4
2
1
.4
4
-
g
ra
m
3
2
.
4
6
1
.
5
5
-
g
ra
m
3
2
.
4
6
1
.
6
6
-
g
ra
m
3
2
.
4
6
1
.
7
7
-
g
ra
m
3
2
.
4
6
T
a
b
l
e
2
.
R
e
s
ul
t
f
r
o
m
s
t
ra
t
e
gy
2
M
a
c
h
i
n
e
n
-
g
ra
m
BL
E
U
S
c
o
r
e
(%
)
2
.3
3
-
g
ra
m
4
0
.
7
9
2
.4
4
-
g
ra
m
4
0
.
6
9
2
.5
5
-
g
ra
m
4
0
.
6
9
2
.6
6
-
g
ra
m
4
0
.
6
7
2
.7
7
-
g
ra
m
4
0
.
7
1
-
0
.
8
3
3
2
7
6
9
d
u
w
e
d
h
u
w
i
t
k
a
n
g
g
o
-
0
.
9
1
2
4
5
8
2
i
n
g
d
h
u
w
u
r
p
a
n
g
g
u
n
g
-
0
.
4
3
5
3
3
6
9
p
a
n
t
e
s
d
i
a
n
g
g
o
n
g
g
e
r
e
t
-
0
.
4
3
5
3
3
6
9
w
i
s
d
i
e
n
t
e
n
i
a
b
a
h
-
0
.
8
3
3
2
7
6
9
s
i
n
g
d
i
g
a
w
a
,
-
0
.
1
7
1
3
2
4
9
a
re
p
a
d
i
k
a
y
a
n
g
a
p
a
-
0
.
7
3
6
3
6
6
9
g
e
l
e
m
d
i
k
e
t
h
a
k
,
-
0
.
7
3
6
3
6
6
9
g
e
l
e
m
d
i
k
e
t
h
a
k
s
i
ra
h
e
-
0
.
4
3
5
3
3
6
9
,
d
i
n
a
i
k
i
-
0
.
3
7
4
6
3
7
3
<
s
>
d
i
n
a
e
s
u
k
e
-
0
.
9
7
9
4
0
5
i
n
g
d
i
n
a
i
k
i
-
0
.
5
3
9
3
0
1
8
i
n
g
d
i
n
a
i
k
u
-
0
.
4
3
5
3
3
6
9
p
i
t
u
n
g
d
i
n
a
p
i
t
u
n
g
-
0
.
7
3
6
3
6
6
9
s
a
w
a
t
a
ra
d
i
n
a
<
/
s
>
-
0
.
1
7
1
3
2
4
9
s
a
w
i
j
i
n
i
n
g
d
i
n
a
,
-
0
.
4
3
5
3
3
6
9
w
i
w
i
t
d
i
n
a
i
k
i
-
0
.
8
3
3
2
7
6
9
s
i
n
g
d
i
p
a
r
i
n
g
a
k
e
d
e
n
i
n
g
-
0
.
4
3
5
3
3
6
9
s
i
n
g
d
i
s
e
l
i
p
a
k
e
i
n
g
-
0
.
4
3
5
3
3
6
9
b
i
s
a
d
i
s
i
n
g
k
i
ri
m
a
n
e
h
-
1
.
0
4
6
9
5
5
t
a
,
b
a
h
?
"
p
i
t
a
k
o
n
e
k
a
b
a
y
a
n
<
/
s
>
-
1
.
0
4
6
9
5
5
o
ra
b
a
k
a
l
b
a
l
i
m
a
n
e
h
,
k
a
b
a
y
a
n
?
"
-
1
.
0
4
6
9
5
5
m
e
m
e
d
i
s
i
n
g
a
n
a
n
j
e
r
o
o
m
a
h
k
o
t
h
o
n
g
i
k
u
-
1
.
0
4
6
9
5
5
<
s
>
"
a
h
,
k
o
w
e
k
u
w
i
p
a
n
c
e
n
-
1
.
2
2
3
0
4
6
<
s
>
a
b
a
h
,
a
m
b
u
,
l
a
n
n
y
i
-
1
.
0
4
6
9
5
5
m
e
m
e
d
i
i
k
u
o
ra
b
a
k
a
l
b
a
l
i
m
a
n
e
h
,
-
1
.
0
4
6
9
5
5
w
o
n
g
t
u
w
a
p
i
k
u
n
s
i
n
g
s
e
d
h
e
l
a
m
a
n
e
h
b
a
k
a
l
-
1
.
0
4
6
9
5
5
<
s
>
n
a
l
i
k
a
k
u
w
i
,
ra
d
e
n
m
a
s
b
a
n
t
e
ra
n
g
-
1
.
7
0
0
1
6
7
<
s
>
p
u
t
ri
k
e
n
a
n
g
a
l
a
n
p
u
t
r
i
m
a
w
a
r
m
l
e
n
g
o
s
-
1
.
7
0
0
1
6
7
<
s
>
p
u
t
ri
k
e
n
a
n
g
a
l
a
n
p
u
t
r
i
m
a
w
a
r
p
a
d
h
a
-
1
.
0
4
6
9
5
5
p
i
k
u
n
s
i
n
g
s
e
d
h
e
l
a
m
a
n
e
h
b
a
k
a
l
m
l
e
b
u
k
u
b
u
r
-
1
.
0
4
6
9
5
5
ra
k
k
a
n
g
g
o
s
i
n
g
a
n
a
i
n
g
n
j
e
ro
w
e
t
e
n
g
-
1
.
0
4
6
9
5
5
a
b
a
h
,
a
m
b
u
,
l
a
n
n
y
i
i
t
e
u
n
g
-
0
.
1
2
4
9
3
8
7
<
s
>
"
m
a
t
u
r
n
u
w
u
n
,
p
a
k
.
-
1
.
0
4
6
9
5
5
w
i
s
k
e
k
u
ra
s
a
n
a
i
n
g
p
a
l
a
g
a
n
s
a
k
d
u
ru
n
g
e
-
1
.
0
4
6
9
5
5
a
p
a
,
n
a
k
?
"
p
i
t
a
k
o
n
e
s
i
n
g
d
o
d
o
l
-
1
.
0
4
6
9
5
5
,
b
a
w
a
n
g
,
t
e
m
p
e
,
t
ra
s
i
,
-
1
.
0
4
6
9
5
5
k
a
n
g
g
o
s
i
n
g
a
n
a
i
n
g
n
j
e
ro
w
e
t
e
n
g
i
k
i
Evaluation Warning : The document was created with Spire.PDF for Python.
Int
J
E
l
e
c
&
Co
m
p
E
n
g
IS
S
N
:
2088
-
8708
Im
pr
ov
i
ng
t
he
r
ol
e
o
f
l
angu
age
m
od
e
l
i
n
s
t
a
t
i
s
t
i
c
a
l
m
ac
h
i
ne
t
r
ans
l
at
i
on
…
(
H
e
r
r
y
Su
j
ai
ni
)
2107
T
h
e
t
h
i
r
d
s
t
ra
t
e
gy
e
xpe
r
i
m
e
nt
w
a
s
us
i
n
g
a
p
a
r
a
l
l
e
l
c
o
r
pus
of
4500
s
e
n
t
e
n
c
e
s
a
n
d
a
m
o
n
o
l
i
ngua
l
c
o
r
pus
of
4500
t
o
5100
s
e
nt
e
n
c
e
s
,
4500
b
a
s
e
l
i
n
e
s
e
n
t
e
n
c
e
s
c
o
n
s
i
s
t
o
f
608
r
e
f
e
r
e
n
c
e
s
e
n
t
e
n
c
e
s
a
n
d
3892
s
e
nt
e
n
c
e
s
of
pa
ra
l
l
e
l
c
o
r
pus
t
a
r
ge
t
s
.
T
h
e
e
xpe
r
i
m
e
n
t
’s
re
s
ul
t
p
r
o
duc
e
d
c
a
n
b
e
fo
un
d
i
n
T
a
b
l
e
3
i
n
d
i
c
a
t
es
t
h
a
t
t
h
e
a
dd
i
t
i
o
n
o
f
m
o
n
o
l
i
n
g
ua
l
c
o
r
pus
qua
nt
i
t
i
e
s
t
a
ke
n
f
r
o
m
t
h
e
pa
ra
l
l
e
l
c
o
r
pus
do
e
s
n
o
t
s
h
o
w
s
i
gn
i
f
i
c
a
n
t
i
n
c
r
e
a
s
e
s
at
a
c
c
ur
a
c
y
.
M
a
c
h
i
n
e
3
.
45
m
e
a
n
s
us
i
ng
s
t
r
a
t
e
gy
3
w
i
t
h
4500
s
e
n
t
e
n
c
e
s
;
m
a
c
h
i
n
e
3
.
46
m
e
a
n
s
us
i
n
g
s
t
ra
t
e
gy
3
w
i
t
h
4600
s
e
nt
e
n
c
e
s
,
a
n
d
s
o
o
n
.
T
h
e
hi
g
h
e
s
t
v
a
l
ue
o
n
a
3
.
51
c
a
n
o
n
l
y
i
n
c
r
e
a
s
e
t
h
e
a
c
c
ur
a
c
y
o
f
((40.
8
1
-
40
.
59)
/
40
.
59)
*
100%
=
0
.
54%
.
T
h
e
f
o
ur
t
h
s
t
ra
t
e
g
y
e
xpe
r
i
m
e
n
t
w
a
s
us
i
n
g
a
pa
ra
l
l
e
l
c
o
r
pus
o
f
4500
s
e
n
t
e
n
c
e
s
a
n
d
a
m
o
n
o
l
i
n
g
ua
l
c
o
r
pus
of
4500
t
o
5100
s
e
nt
e
n
c
e
s
,
a
n
d
t
h
e
w
h
o
l
e
4500
b
a
s
e
l
i
n
e
s
e
nt
e
n
c
e
s
w
e
r
e
t
a
ke
n
f
r
o
m
t
h
e
p
a
r
a
l
l
e
l
c
o
r
pus
t
a
r
ge
t
s
e
nt
e
n
c
e
.
T
h
e
r
e
s
ul
t
s
o
f
t
h
e
e
xpe
r
i
m
e
nt
s
p
r
o
duc
e
d
c
a
n
b
e
fo
un
d
i
n
T
a
b
l
e
4
i
ndi
c
a
t
es
t
h
a
t
t
h
e
a
ddi
t
i
o
n
o
f
m
o
n
o
l
i
n
gu
a
l
c
o
r
pus
qu
a
nt
i
t
i
e
s
t
a
ke
n
f
r
o
m
t
h
e
r
e
f
e
r
e
n
c
e
s
e
nt
e
n
c
e
s
h
o
w
s
a
s
i
gni
f
i
c
a
nt
i
n
c
r
e
a
s
e
at
a
c
c
ura
c
y
.
M
a
c
hi
n
e
4
.
45
m
e
a
n
s
us
i
ng
s
t
r
a
t
e
g
y
4
w
i
t
h
4500
s
e
nt
e
n
c
e
s
;
m
a
c
h
i
n
e
4.
4
6
m
e
a
n
s
us
i
n
g
s
t
ra
t
e
gy
4
w
i
t
h
4600
s
e
n
t
e
n
c
e
s
,
a
n
d
s
o
o
n.
T
h
e
hi
g
h
e
s
t
v
a
l
ue
o
n
a
4
.
51
m
a
c
hi
n
e
w
i
t
h
5
100
s
e
n
t
e
n
c
e
s
i
n
m
o
n
o
l
i
n
gu
a
l
c
o
r
pus
c
a
n
i
n
c
r
e
a
s
e
a
c
c
ur
a
c
y
by
((40.
63
-
32.
4
2)
/
3
2.
4
2)
*
10
0%
=
25.
32
%.
T
a
b
l
e
3
.
R
e
s
ul
t
f
r
o
m
s
t
ra
t
e
gy
3
M
a
c
h
i
n
e
M
o
n
o
l
i
n
g
u
a
l
c
o
r
p
u
s
BL
E
U
S
c
o
r
e
(%
)
3
.
4
5
45
00
4
0
.
5
9
3
.
4
6
46
00
4
0
.
4
6
3
.
4
7
47
00
4
0
.
2
0
3
.
4
8
48
00
4
0
.
4
6
3
.
4
9
49
00
4
0
.
6
4
3
.
5
0
50
00
4
0
.
6
3
3
.
5
1
51
00
4
0
.
8
1
T
a
b
l
e
4
.
R
e
s
ul
t
f
r
o
m
s
t
ra
t
e
gy
4
M
a
c
h
i
n
e
M
o
n
o
l
i
n
g
u
a
l
c
o
r
p
u
s
BL
E
U
S
c
o
r
e
(%
)
4
.
4
5
45
00
3
2
.
4
2
4
.
4
6
46
00
3
5
.
4
8
4
.
4
7
47
00
3
7
.
1
9
4
.
4
8
48
00
3
7
.
8
2
4
.
4
9
49
00
3
8
.
5
5
4
.
5
0
50
00
3
9
.
5
2
4
.
5
1
51
00
4
0
.
6
3
E
xpe
r
i
m
e
nt
s
c
o
n
duc
t
e
d
o
n
s
t
ra
t
e
gi
e
s
1
a
nd
2
s
h
o
w
t
h
a
t
t
he
us
e
of
n
-
g
ra
m
m
o
de
l
f
r
o
m
3
-
g
ra
m
t
o
7
-
g
r
a
m
do
e
s
n
o
t
a
f
f
e
c
t
t
h
e
a
c
c
u
r
a
c
y
of
t
h
e
I
n
do
n
e
s
i
a
n
-
J
a
v
a
t
ra
n
s
l
a
t
o
r
m
a
c
hi
n
e
w
i
t
h
a
p
a
r
a
l
l
e
l
c
o
r
pus
o
f
4500
s
e
n
t
e
n
c
e
s
.
T
hi
s
i
s
due
t
o
t
h
e
s
m
a
l
l
num
b
e
r
o
f
s
e
n
t
e
n
c
e
s
us
e
d
i
n
t
h
e
c
o
r
pus
.
T
h
e
s
m
a
l
l
qua
nt
i
t
y
of
c
o
r
pus
s
e
n
t
e
n
c
e
s
r
e
s
ul
t
s
i
n
n
o
v
a
r
i
a
t
i
o
n
i
n
t
h
e
p
r
o
b
a
b
i
l
i
t
y
o
f
e
a
c
h
pa
i
r
o
f
t
o
ke
n
s
,
a
s
s
e
e
n
i
n
t
h
e
7
-
g
r
a
m
l
a
ngua
ge
m
o
de
l
;
t
hus
,
f
o
r
S
M
T
us
i
n
g
t
h
e
s
m
a
l
l
c
o
r
pus
,
i
t
i
s
b
e
s
t
t
o
ke
e
p
us
i
n
g
t
h
e
3
-
g
ra
m
l
a
n
gu
a
ge
m
o
de
l
.
T
h
e
m
o
n
o
l
i
ngua
l
c
o
r
pus
qua
nt
i
t
y
a
ddi
t
i
o
n
e
xpe
ri
m
e
n
t
s
us
e
d
f
o
r
gra
du
a
l
l
a
ngua
ge
m
o
de
l
t
ra
i
ni
n
g,
t
h
e
r
e
s
ul
t
s
a
r
e
de
m
o
n
s
t
ra
t
e
d
by
s
t
r
a
t
e
g
i
e
s
3
a
n
d
4.
F
r
o
m
t
he
e
xp
e
r
i
m
e
nt
a
l
r
e
s
ul
t
s
,
i
t
i
s
f
o
un
d
t
h
a
t
t
h
e
b
e
s
t
r
e
s
ul
t
s
a
r
e
o
b
t
a
i
n
e
d
by
i
n
c
r
e
a
s
i
n
g
t
h
e
qu
a
n
t
i
t
y
of
t
h
e
m
o
n
o
l
i
ngua
l
c
o
r
pus
o
ut
s
i
de
t
h
e
pa
ra
l
l
e
l
c
o
r
pus
i
n
s
t
ra
t
e
gy
4,
i
n
o
t
h
e
r
w
o
r
ds
,
t
h
e
m
o
n
o
l
i
ngua
l
c
o
r
pus
t
a
ke
n
f
r
o
m
t
h
e
pa
ra
l
l
e
l
c
o
r
pus
t
a
r
ge
t
l
a
n
gu
a
ge
,
t
h
e
n
a
d
de
d
w
i
t
h
a
n
o
t
h
e
r
s
e
n
t
e
n
c
e
b
e
y
o
n
d
t
h
e
e
xi
s
t
i
n
g
s
e
n
t
e
n
c
e
i
n
t
h
e
pa
ra
l
l
e
l
c
o
r
pus
.
T
h
e
i
n
c
r
e
a
s
e
of
t
h
e
BL
E
U
s
c
o
r
e
o
f
e
a
c
h
m
a
c
h
i
n
e
t
o
t
h
e
b
a
s
e
l
i
n
e
c
a
n
b
e
s
e
e
n
i
n
F
i
g
u
r
e
.
6.
T
h
e
e
xpe
r
i
m
e
nt
’s
r
e
s
ul
t
s
o
n
s
t
ra
t
e
gy
4
s
h
o
w
a
s
i
g
ni
f
i
c
a
n
t
i
n
c
r
e
a
s
e
f
o
r
e
a
c
h
a
dd
i
t
i
o
n
o
f
100
s
e
nt
e
n
c
e
s
t
o
t
h
e
m
o
n
o
l
i
n
g
ua
l
c
o
r
pus
,
a
s
s
e
e
n
i
n
T
a
b
l
e
5.
F
r
o
m
t
h
e
r
e
s
ul
t
s
o
f
t
h
i
s
s
t
udy
,
i
t
c
a
n
b
e
c
o
n
c
l
ude
d
t
h
a
t
t
h
e
r
o
l
e
of
t
h
e
l
a
n
g
ua
ge
m
o
de
l
i
s
qui
t
e
i
m
po
rt
a
nt
i
n
a
n
t
i
c
i
pa
t
i
n
g
t
h
e
s
e
nt
e
n
c
e
s
t
o
b
e
t
r
a
n
s
l
a
t
e
d
o
n
t
h
e
SMT
,
e
s
pe
c
i
a
l
l
y
w
h
e
n
t
h
e
phra
s
e
i
n
t
h
e
s
e
n
t
e
n
c
e
i
s
n
o
t
c
o
n
t
a
i
n
e
d
i
n
t
h
e
t
r
a
n
s
l
a
t
i
o
n
m
o
de
l
.
T
hi
s
w
i
l
l
c
e
r
t
a
i
nl
y
be
m
o
r
e
a
pp
a
r
e
nt
o
n
S
M
T
w
i
t
h
s
m
a
l
l
r
e
s
o
ur
c
e
s
b
e
c
a
us
e
t
h
e
pos
s
i
b
i
l
i
t
y
of
a
s
e
n
t
e
n
c
e
t
o
b
e
t
r
a
n
s
l
a
t
e
d
do
e
s
n
o
t
e
xi
s
t
i
n
t
h
e
t
ra
n
s
l
a
t
i
o
n
m
o
de
l
i
s
c
e
r
t
a
i
nl
y
v
e
r
y
l
a
r
ge
c
o
m
pa
r
e
d
t
o
S
M
T
w
i
t
h
l
a
rge
r
e
s
o
ur
c
e
s
.
F
i
gu
r
e
6
.
I
n
c
r
e
a
s
i
ng
o
f
B
L
E
U
s
c
o
r
e
s
0
10
20
30
40
50
4
.
4
5
4
.
4
6
4
.
4
7
4
.
4
8
4
.
4
9
4
.
5
0
4
.
5
1
B
L
E
U
Evaluation Warning : The document was created with Spire.PDF for Python.
IS
S
N
:
2088
-
8708
Int
J
E
l
e
c
&
Co
m
p
E
n
g
,
V
o
l
.
10
,
N
o
.
2
,
A
p
ri
l
2020
:
2
102
-
210
9
2108
T
a
b
l
e
5
.
I
n
c
r
e
a
s
i
ng
a
c
c
ura
c
y
o
n
s
t
ra
t
e
g
y
4
M
a
c
h
i
n
e
M
o
n
o
l
i
n
g
u
a
l
c
o
r
p
u
s
In
c
re
a
s
i
n
g
(
%
)
4
.
45
3
2
.
4
2
4
.
4
6
3
5
.
4
8
9
.
4
4
4
.
4
7
3
7
.
1
9
4
.
8
2
4
.
4
8
3
7
.
8
2
1
.
6
9
4
.
4
9
3
8
.
5
5
1
.
9
3
4
.
5
0
3
9
.
5
2
2
.
5
2
4
.
5
1
4
0
.
6
3
2
.
8
1
3.
C
O
N
C
LU
S
I
O
N
T
h
e
ut
i
l
i
z
a
t
i
o
n
of
t
h
e
n
-
g
r
a
m
m
o
de
l
f
r
o
m
3
-
g
ra
m
t
o
7
-
gra
m
d
o
e
s
n
o
t
a
f
f
e
c
t
t
h
e
a
c
c
u
r
a
c
y
of
t
h
e
I
n
do
n
e
s
i
a
n
-
J
a
v
a
t
r
a
n
s
l
a
t
o
r
m
a
c
hi
n
e
.
I
t
i
s
r
e
c
o
m
m
e
nde
d
t
ha
t
SMT
us
i
n
g
a
s
m
a
l
l
c
o
r
pus
s
h
o
ul
d
ke
e
p
us
i
n
g
a
3
-
g
ra
m
l
a
ngua
ge
m
o
de
l
.
T
h
e
b
e
s
t
r
e
s
ul
t
f
o
r
i
m
p
r
o
v
i
n
g
t
he
l
a
n
gu
a
ge
m
o
de
l
r
o
l
e
i
s
t
o
us
e
t
h
e
t
h
e
p
a
r
a
l
l
e
l
c
o
r
pus
t
a
r
ge
t
l
a
ngua
ge
a
s
t
h
e
m
o
n
o
l
i
n
gu
a
l
c
o
r
p
us
,
t
h
e
n
a
dde
d
a
s
m
uc
h
a
s
po
s
s
i
b
l
e
w
i
t
h
o
t
h
e
r
s
e
nt
e
n
c
e
s
b
e
y
o
n
d
t
h
e
e
xi
s
t
i
ng
s
e
n
t
e
n
c
e
i
n
t
h
e
pa
ra
l
l
e
l
c
o
r
pus
.
R
EF
ER
EN
C
ES
[
1]
M
.
V
o
l
k
,
“
P
a
r
a
l
l
e
l
C
o
r
po
r
a
,
T
e
r
m
i
no
l
o
gy
E
xt
r
a
c
t
i
o
n
und
M
a
c
hi
ne
T
r
a
ns
l
a
t
i
o
n
,
”
I
n:
1
6.
D
T
T
Sy
m
pos
i
on
.
T
e
r
m
i
no
l
og
i
e
und
T
e
x
t
(
e
)
,
M
an
nhe
i
m
,
22
-
2
4
M
a
r
c
h
2
018
,
3
-
14.
2
018.
[
2]
E
.
Y
ı
l
dı
z
,
A
.
C
.
T
a
n
t
u˘
g
,
a
nd
B
.
D
i
r
i
.
“
T
he
e
f
f
e
c
t
o
f
pa
r
a
l
l
e
l
c
o
r
pus
qua
l
i
t
y
v
s
s
i
z
e
i
n
E
ng
l
i
s
h
-
to
-
T
ur
ki
s
h
S
M
T
,
”
I
n
P
r
oc
e
e
di
ngs
o
f
t
he
Si
x
t
h
I
n
t
e
r
nat
i
on
al
C
on
f
e
r
e
nc
e
on
W
e
b
s
e
r
v
i
c
e
s
and
Se
m
ant
i
c
T
e
c
hno
l
og
y
(
W
e
ST
2014)
,
201
4.
[
3]
A
.
I
m
a
nkul
o
v
a
,
T
.
S
a
t
o
,
M
.
K
o
m
a
c
hi
,
“
I
m
pr
ov
i
ng
L
o
w
-
R
e
s
o
ur
c
e
N
e
ur
a
l
M
a
c
h
i
ne
T
r
a
ns
l
a
t
i
o
n
w
i
t
h
F
i
l
t
e
r
e
d
P
s
e
udo
-
pa
r
a
l
l
e
l
C
o
r
p
us
,
”
I
n
P
r
oc
e
e
di
ngs
of
t
he
4t
h
W
or
k
s
hop
on
A
s
i
an
T
r
ans
l
a
t
i
o
n
(
W
A
T
2017)
,
T
a
i
pe
i
,
2
017
[
4]
K
.
K
.
A
r
o
r
a
a
nd
S
.
S
.
A
g
r
a
w
a
,
“
P
r
e
-
P
r
o
c
e
s
s
i
ng
o
f
E
ng
l
i
s
h
-
H
i
n
di
C
o
r
pus
f
o
r
S
t
a
t
i
s
t
i
c
a
l
M
a
c
hi
n
e
T
r
a
ns
l
a
t
i
o
n
,
”
C
om
put
ac
i
ón
y
Si
s
t
e
m
as
,
V
o
l
.
21
,
N
o
.
4
,
2017
.
[
5]
H
.
T
r
a
n
,
Y
.
G
uo
,
P
.
J
i
a
n
,
S
.
S
h
i
,
a
n
d
H
.
H
ua
ng
,
“
I
m
pr
o
v
i
ng
P
a
r
a
l
l
e
l
C
o
r
pu
s
Q
ua
l
i
t
y
f
o
r
C
hi
ne
s
e
-
V
i
e
t
na
m
e
s
e
S
t
a
t
i
s
t
i
c
a
l
M
a
c
hi
n
e
T
r
a
n
s
l
a
t
i
o
n
,
”
J
our
nal
o
f
B
e
i
j
i
ng
I
ns
t
i
t
u
t
e
of
T
e
c
hnol
ogy
,
V
o
l
.
27
,
N
o
.
1
,
2
018
.
[
6]
M
.
G
.
A
s
pa
r
i
l
l
a
,
H
.
S
u
j
a
i
n
i
,
a
nd
R
.
D
.
N
y
o
t
o
,
“
C
o
r
p
us
Q
ua
l
i
t
y
I
m
pr
o
v
e
m
e
nt
t
o
I
m
pr
ov
e
t
he
Q
ua
l
i
t
y
of
S
t
a
t
i
s
t
i
c
a
l
T
r
a
n
s
l
a
t
o
r
M
a
c
hi
n
e
s
(
C
a
s
e
S
t
udy
of
I
ndo
ne
s
i
a
n
L
a
ng
ua
g
e
t
o
J
a
v
a
K
r
a
m
a
)
,
”
J
ur
nal
L
i
n
gu
i
s
t
i
k
K
om
pu
t
a
s
i
o
nal
,
V
o
l
.
1
,
N
o
.
2
,
2018
.
[
7]
J
.
S
u
,
H
.
W
u
,
H
.
W
a
ng
,
Y
.
C
h
e
n
,
X
.
S
h
i
,
H
.
D
o
ng
,
a
nd
Q
.
L
i
u,
“
T
r
a
n
s
l
a
t
i
o
n
M
o
de
l
A
da
p
t
a
t
i
o
n
f
o
r
S
t
a
t
i
s
t
i
c
a
l
M
a
c
hi
n
e
T
r
a
n
s
l
a
t
i
o
n
w
i
t
h
M
o
no
l
i
ng
ua
l
T
o
pi
c
I
nf
o
r
m
a
t
i
o
n,
”
i
n
P
r
oc
e
e
di
ngs
of
t
he
50
t
h
A
nnua
l
M
e
e
t
i
ng
of
t
he
A
s
s
o
c
i
a
t
i
on
f
o
r
C
om
pu
t
a
t
i
o
na
l
L
i
ng
ui
s
t
i
c
s
(
V
o
l
um
e
1
:
L
ong
P
ape
r
s
)
,
J
e
j
u
I
s
l
a
nd
,
201
2.
[
8]
G
.
N
e
ub
i
g
,
T
.
W
a
t
a
na
b
e
,
"
O
p
t
i
m
i
z
a
t
i
o
n
f
o
r
S
t
a
t
i
s
t
i
c
a
l
M
a
c
hi
ne
T
r
a
ns
l
a
t
i
o
n:
A
S
ur
v
e
y
,
"
C
om
put
at
i
ona
l
L
i
ngu
i
s
t
i
c
s
,
V
o
l
.
4
2,
N
o
.
1
,
201
6.
[
9]
K
.
N
.
D
e
w
,
A
.
M
.
T
ur
n
e
r
,
Y
.
K
.
C
ho
i
,
A
.
B
o
s
o
l
d,
a
nd
K
.
K
i
r
c
h
ho
f
f
e
,
"
D
e
v
e
l
o
pm
e
nt
o
f
M
a
c
hi
ne
T
r
a
n
s
l
a
t
i
o
n
T
e
c
hno
l
o
gy
f
o
r
A
s
s
i
s
t
i
ng
H
e
a
l
t
h
C
o
m
m
uni
c
a
t
i
o
n:
A
S
y
s
t
e
m
a
t
i
c
R
e
v
i
e
w
,
"
J
o
ur
n
al
o
f
B
i
om
e
di
c
al
I
n
f
or
m
at
i
c
s
,
V
o
l
.
8
5,
20
18
[
10]
P
.
J
.
A
nt
o
ny
a
nd
K
.
P
.
S
o
m
a
n
,
“
K
e
r
ne
l
B
a
s
e
d
P
a
r
t
o
f
S
pe
e
c
h
T
a
g
ge
r
f
o
r
K
a
nnda
,
”
i
n
I
n
t
e
r
nat
i
on
al
C
on
f
e
r
e
nc
e
on
M
ac
hi
ne
L
e
ar
ni
ng
and
C
y
be
r
ne
t
i
c
s
,
I
C
M
L
C
2010
,
Q
i
ng
da
o
,
S
ha
n
d
o
ng
,
201
0.
[
11]
M
.
M
o
ha
g
he
g
h,
A
.
S
a
r
r
a
f
xa
d
e
h
,
a
nd
T
.
M
o
i
r
,
"
I
m
pr
o
v
e
d
L
a
ngua
g
e
M
o
de
l
i
ng
f
o
r
E
ng
l
i
s
h
-
P
e
r
s
i
a
n
S
t
a
t
i
s
t
i
c
a
l
M
a
c
hi
n
e
T
r
a
n
s
l
a
t
i
o
n
,
"
i
n
P
r
oc
e
e
di
ngs
o
f
SSS
T
-
4
,
F
our
t
h
W
or
k
s
ho
p
on
Sy
n
t
a
x
and
S
t
r
u
c
t
u
r
e
i
n
St
at
i
s
t
i
c
al
T
r
ans
l
a
t
i
on
,
C
O
L
I
N
G
2010
,
B
e
i
j
i
ng
,
2010
.
[
12]
J
.
S
a
ng
e
e
t
ha
,
S
.
J
o
t
hi
l
a
ks
hm
i
,
a
nd
R
.
N
.
D
.
K
um
a
r
,
"
A
n
E
f
f
i
c
i
e
nt
M
a
c
hi
ne
T
r
a
ns
l
a
t
i
o
n
S
y
s
t
e
m
f
o
r
E
ng
l
i
s
h
t
o
I
ndi
a
n
L
a
ng
ua
g
e
s
U
s
i
ng
H
y
br
i
d
M
e
c
ha
n
i
s
m
,
"
I
nt
e
r
n
at
i
ona
l
J
ou
r
na
l
of
E
ng
i
ne
e
r
i
ng
and
T
e
c
hno
l
og
y
(
I
J
E
T
)
,
V
o
l
.
6
,
N
o
.
4,
20
14
.
[
13]
H
.
S
u
j
a
i
n
i
,
K
us
pr
i
y
a
nt
o
,
A
.
A
.
A
r
m
a
n
,
a
n
d
A
.
P
u
r
w
a
r
i
a
n
t
i
,
“
E
x
t
e
nd
e
d
W
o
r
d
S
i
m
i
l
a
r
i
t
y
B
a
s
e
d
C
l
us
t
e
r
i
ng
o
n
U
ns
upe
r
v
i
s
e
d
P
o
S
I
nduc
t
i
o
n
t
o
I
m
pr
ov
e
E
ng
l
i
s
h
-
I
nd
o
ne
s
i
a
n
S
t
a
t
i
s
t
i
c
a
l
M
a
c
hi
n
e
T
r
a
ns
l
a
t
i
o
n
,
”
i
n
16
t
h
O
R
I
E
N
T
A
L
C
O
C
O
SD
A
/
C
A
SL
R
E
-
20
13
,
G
u
r
g
a
o
n,
I
ndi
a
,
2013
.
[
14]
H
.
Y
u
,
J
.
S
u
,
Y
.
L
v
,
a
nd
Q
.
L
i
u,
“
A
T
o
pi
c
-
T
r
i
g
g
e
r
e
d
L
a
ng
ua
g
e
M
o
de
l
f
o
r
S
t
a
t
i
s
t
i
c
a
l
M
a
c
hi
ne
T
r
a
n
s
l
a
t
i
o
n
,
”
i
n
P
r
oc
e
e
di
ngs
o
f
t
he
Si
x
t
h
I
n
t
e
r
nat
i
on
al
J
oi
n
t
C
on
f
e
r
e
nc
e
on
N
at
ur
a
l
L
angua
ge
P
r
oc
e
s
s
i
ng
,
N
a
g
oy
a
,
2013
.
[
15]
Y
.
Z
ha
ng
,
A
.
N
i
e
,
A
.
Z
e
h
nde
r
,
L
.
R
o
dne
y
,
a
nd
J
.
Z
o
u,
“
V
e
t
T
ag
:
i
m
pr
ov
i
ng
au
t
om
a
t
e
d
v
e
t
e
r
i
na
r
y
di
a
gno
s
i
s
c
o
di
n
g
v
i
a
l
ar
ge
-
s
c
a
l
e
l
angu
age
m
ode
l
i
ng
,
”
D
i
g
i
t
a
l
M
e
di
c
i
n
e
,
2
019
.
[
16]
M
.
M
o
ha
g
he
g
h,
A
.
S
a
r
r
a
f
z
a
de
h,
a
nd
T
.
M
o
i
r
,
“
I
m
pr
o
v
e
d
L
a
n
gua
g
e
M
o
de
l
i
ng
f
o
r
E
ng
l
i
s
h
-
P
e
r
s
i
a
n
S
t
a
t
i
s
t
i
c
a
l
M
a
c
hi
n
e
,
”
in
SS
ST
-
4,
F
our
t
h
W
or
k
s
hop
on
S
y
nt
ax
and
S
t
r
uc
t
ur
e
i
n
St
a
t
i
s
t
i
c
a
l
T
r
a
ns
l
a
t
i
o
n
,
B
e
i
j
i
ng
,
201
0.
[
17]
C
.
M
o
nz
,
“
S
t
a
t
i
s
t
i
c
a
l
M
a
c
h
i
ne
T
r
a
n
s
l
a
t
i
o
n
w
i
t
h
L
o
c
a
l
L
a
ng
ua
g
e
M
o
de
l
s
,
”
in
C
o
nf
e
r
e
nc
e
on
E
m
pi
r
i
c
al
M
e
t
hod
s
i
n
N
at
ur
al
L
a
ngua
ge
P
r
oc
e
s
s
i
ng
,
E
di
n
bur
g
h
,
2
011
.
[
18]
S
.
B
a
ne
r
j
e
e
,
J
.
M
o
s
t
o
w
,
J
.
B
e
c
k,
a
n
d
W
.
T
a
m
,
"
I
m
pr
ov
i
ng
L
a
ng
ua
ge
M
o
de
l
s
by
L
e
a
r
ni
ng
f
r
o
m
S
pe
e
c
h
R
e
c
o
g
ni
t
i
o
n
E
r
r
o
r
s
i
n
a
R
e
a
d
i
ng
T
ut
o
r
t
h
a
t
L
i
s
t
e
ns
,
"
i
n
Se
c
ond
I
n
t
e
r
na
t
i
ona
l
C
onf
e
r
e
nc
e
on
A
pp
l
i
e
d
A
r
t
i
f
i
c
i
a
l
I
nt
e
l
l
i
ge
nc
e
,
2003
.
Evaluation Warning : The document was created with Spire.PDF for Python.
Int
J
E
l
e
c
&
Co
m
p
E
n
g
IS
S
N
:
2088
-
8708
Im
pr
ov
i
ng
t
he
r
ol
e
o
f
l
angu
age
m
od
e
l
i
n
s
t
a
t
i
s
t
i
c
a
l
m
ac
h
i
ne
t
r
ans
l
at
i
on
…
(
H
e
r
r
y
Su
j
ai
ni
)
2109
[
19]
H
.
S
u
j
a
i
n
i
,
K
us
pr
i
y
a
nt
o
,
A
.
A
.
A
r
m
a
n,
a
n
d
A
.
P
u
r
w
a
r
i
a
n
t
i
,
“
A
N
ov
e
l
P
a
r
t
-
of
-
S
pe
e
c
h
S
e
t
D
e
v
e
l
o
pi
ng
M
e
t
ho
d
f
o
r
S
t
a
t
i
s
t
i
c
a
l
M
a
c
hi
ne
T
r
a
n
s
l
a
t
i
o
n
,
”
T
E
L
K
O
M
N
I
K
A
(
T
e
l
e
c
om
m
un
i
c
a
t
i
on
C
om
put
.
E
l
e
c
t
r
on
.
C
on
t
r
ol
.
)
,
v
o
l
.
12
,
no
.
3,
2014
.
[
20]
K
.
J
a
y
a
a
nd
D
.
G
up
t
a
,
“
E
xp
l
o
r
a
t
i
o
n
o
f
C
o
r
pus
A
ug
m
e
nt
a
t
i
o
n
A
ppr
o
a
c
h
f
o
r
E
ng
l
i
s
h
-
H
i
n
di
B
i
d
i
r
e
c
t
i
o
na
l
S
t
a
t
i
s
t
i
c
a
l
M
a
c
hi
n
e
T
r
a
n
s
l
a
t
i
o
n
S
y
s
t
e
m
,
”
I
n
t
e
r
na
t
i
ona
l
J
o
ur
n
al
of
E
l
e
c
t
r
i
c
a
l
an
d
C
om
p
ut
e
r
E
ngi
ne
e
r
i
ng
(
I
J
E
C
E
)
,
v
o
l
.
6
,
no
.
3
,
2016
.
[
21]
[
z
]
C
.
S
h
a
o
ul
,
C
.
F
.
W
e
s
t
bu
r
y
,
a
nd
R
.
H
.
B
a
a
y
e
n,
"
T
he
Subj
e
c
t
i
v
e
F
r
e
que
nc
y
of
W
or
d
n
-
gr
am
s
,
"
P
S
I
H
O
L
O
G
I
J
A
,
V
o
l
.
4
6,
N
o
.
4
,
201
3.
[
22]
A
.
S
t
o
l
c
ke
,
J
.
Z
he
n
g
,
W
.
W
a
ng
,
a
nd
V
.
A
br
a
s
h
,
“
S
R
I
L
M
a
t
s
i
x
t
e
e
n:
U
pda
t
e
a
nd
o
ut
l
o
o
k,
”
in
A
u
t
om
a
t
i
c
Spe
e
c
h
R
e
c
ogni
t
i
on
and
U
nde
r
s
t
a
ndi
ng
(
A
SR
U
)
,
2
011
I
E
E
E
W
o
r
ks
ho
p,
W
a
i
ko
l
o
a
,
20
11
.
[
23]
F
.
J
.
O
c
h
a
n
d
H
.
N
e
y
,
“
A
S
y
s
t
e
m
a
t
i
c
C
o
m
pa
r
i
s
o
n
o
f
V
a
r
i
o
us
S
t
a
t
i
s
t
i
c
a
l
A
l
i
g
nm
e
n
t
M
o
de
l
s
,
”
C
om
pu
t
a
t
i
ona
l
L
i
ngu
i
s
t
i
c
s
,
v
o
l
.
1
,
no
.
29,
p
p.
19
-
51
,
200
3.
[
24]
W
.
X
u
a
nd
P
.
K
o
e
hn,
“
E
xt
e
nd
i
ng
H
i
e
r
o
D
e
c
o
di
ng
i
n
M
o
s
e
s
w
i
t
h
C
u
be
G
r
o
w
i
ng
,
”
T
h
e
P
r
a
g
ue
B
u
l
l
e
t
i
n
o
f
M
a
t
he
m
a
t
i
c
a
l
L
i
ng
ui
s
t
i
c
s
,
8
(
1
)
,
20
12
[
25]
K
.
P
a
p
i
n
e
ni
,
S
.
R
o
uko
s
,
T
.
W
a
r
d
a
nd
W
.
-
J
.
Z
hu
,
“
B
L
E
U
:
A
M
e
t
ho
d
F
o
r
A
ut
o
m
a
t
i
c
E
v
a
l
ua
t
i
o
n
o
f
M
a
c
hi
n
e
T
r
a
n
s
l
a
t
i
o
n,
”
in
P
r
oc
e
e
di
ngs
o
f
t
he
40t
h
A
nnua
l
M
e
e
t
i
ng
o
f
t
he
A
s
s
oc
i
a
t
i
on
o
f
C
om
pu
t
a
t
i
o
na
l
L
i
n
gui
s
t
i
c
s
(
A
C
L
)
,
P
e
nns
y
l
v
an
i
a
,
2002
.
BI
O
G
R
A
P
H
Y
O
F
A
U
T
H
O
R
H
e
r
r
y
S
u
j
a
i
n
i
g
r
a
dua
t
e
d
f
r
o
m
a
ba
c
he
l
o
r
's
de
g
r
e
e
in
t
he
E
l
e
c
t
r
i
c
a
l
E
ng
i
ne
e
r
i
ng
D
e
pa
r
t
m
e
n
t
,
U
ni
v
e
r
s
i
t
y
of
T
a
nj
ung
pu
r
a
.
H
e
g
o
t
hi
s
m
a
s
t
e
r
a
nd
a
do
c
t
o
r
a
l
de
g
r
e
e
f
r
o
m
S
T
E
I
,
B
a
ndung
I
ns
t
i
t
u
t
e
o
f
T
e
c
hno
l
o
gy
.
S
i
nc
e
1997
,
h
e
h
a
s
be
c
o
m
e
a
l
e
c
t
ur
e
r
a
t
I
nf
o
r
m
a
t
i
c
s
D
e
pa
r
t
m
e
n
t
,
E
ng
i
n
e
e
r
i
ng
F
a
c
ul
t
y
,
U
ni
v
e
r
s
i
t
y
o
f
T
a
nj
ung
pur
a
.
H
e
r
r
e
s
e
a
r
c
h
i
n
t
e
r
e
s
t
i
s
o
n
c
o
m
put
a
t
i
o
na
l
l
i
ng
ui
s
t
i
c
s
,
m
a
i
n
l
y
o
n
m
a
c
hi
ne
t
r
a
ns
l
a
t
i
o
n
a
nd
m
a
c
hi
n
e
l
e
a
r
ni
ng
Evaluation Warning : The document was created with Spire.PDF for Python.