I
AE
S In
t
er
na
t
io
na
l J
o
urna
l o
f
Art
if
icia
l In
t
ellig
ence
(
I
J
-
AI
)
Vo
l.
13
,
No
.
4
,
Dec
em
b
er
2
0
2
4
,
p
p
.
4
9
5
7
~
4
9
6
4
I
SS
N:
2
2
5
2
-
8
9
3
8
,
DOI
: 1
0
.
1
1
5
9
1
/
ijai.v
13
.i
4
.
p
p
4
9
5
7
-
4
9
6
4
4957
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
a
i
.
ia
esco
r
e.
co
m
Unsuperv
ised h
in
di word sens
e dis
a
mbig
ua
tion usin
g
gra
ph
-
ba
sed cent
ra
lity
mea
sures
P
ra
j
na
J
ha
1
,
Sh
re
y
a
Ag
a
rwa
l
1
,
Ali A
bb
a
s
1
,
Sa
t
y
endr
Si
ng
h
2
,
T
a
nv
ee
r
J
a
ha
n Sid
diq
ui
1
1
D
e
p
a
r
t
me
n
t
o
f
El
e
c
t
r
o
n
i
c
s a
n
d
C
o
m
mu
n
i
c
a
t
i
o
n
,
F
a
c
u
l
t
y
o
f
S
c
i
e
n
c
e
,
U
n
i
v
e
r
si
t
y
o
f
A
l
l
a
h
a
b
a
d
,
P
r
a
y
a
g
r
a
j
,
I
n
d
i
a
2
D
e
p
a
r
t
me
n
t
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
E
n
g
i
n
e
e
r
i
n
g
,
S
c
h
o
o
l
o
f
E
n
g
i
n
e
e
r
i
n
g
a
n
d
Te
c
h
n
o
l
o
g
y
,
B
M
L
M
u
n
j
a
l
U
n
i
v
e
r
si
t
y
,
K
a
p
r
i
w
a
s
,
I
n
d
i
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
an
2
7
,
2
0
2
4
R
ev
is
ed
Ma
r
2
7
,
2
0
2
4
Acc
ep
ted
Ap
r
1
7
,
2
0
2
4
Th
e
tas
k
o
f
w
o
rd
se
n
se
d
isa
m
b
ig
u
a
ti
o
n
(W
S
D)
p
la
y
s
a
k
e
y
ro
le
i
n
m
u
lt
ip
le
a
p
p
li
c
a
ti
o
n
s
o
f
n
a
tu
ra
l
lan
g
u
a
g
e
p
ro
c
e
ss
in
g
.
In
th
is
p
a
p
e
r,
we
p
ro
p
o
se
a
n
o
v
e
l
u
n
su
p
e
rv
ise
d
m
e
th
o
d
fo
r
t
a
rg
e
ted
Hin
d
i
WS
D
tas
k
.
F
irst,
we
c
re
a
te
a
we
ig
h
ted
g
ra
p
h
wh
e
re
th
e
n
o
d
e
s
c
o
rre
sp
o
n
d
to
v
a
ri
o
u
s
sy
n
se
ts
o
f
th
e
targ
e
t
wo
rd
a
n
d
t
h
e
n
e
i
g
h
b
o
ri
n
g
c
o
n
tex
t
wo
rd
s.
Th
e
e
d
g
e
s
i
n
t
h
e
g
ra
p
h
re
p
re
se
n
t
th
e
se
m
a
n
ti
c
re
latio
n
s
b
e
twe
e
n
th
e
se
sy
n
se
ts
in
th
e
Hin
d
i
Wo
rd
Ne
t
h
iera
rc
h
y
.
A
p
a
th
-
b
a
se
d
sim
il
a
rit
y
m
e
a
su
re
,
n
a
m
e
ly
Lea
c
o
c
k
-
Ch
o
d
o
ro
w
s
imilarity
m
e
a
su
re
,
is
u
se
d
t
o
a
ss
ig
n
we
ig
h
ts
t
o
e
d
g
e
s.
A
n
u
n
s
u
p
e
rv
ise
d
we
ig
h
ted
g
ra
p
h
-
b
a
se
d
c
e
n
trali
ty
a
lg
o
ri
th
m
is
u
se
d
t
o
i
d
e
n
t
ify
t
h
e
c
o
rre
c
t
se
n
se
o
f
a
targ
e
t
wo
rd
in
a
g
iv
e
n
c
o
n
tex
t
.
Th
e
p
e
rfo
rm
a
n
c
e
o
f
t
h
e
p
ro
p
o
se
d
a
lg
o
rit
h
m
is
m
e
a
su
re
d
o
n
2
0
a
m
b
ig
u
o
u
s
Hin
d
i
n
o
u
n
s
u
sin
g
fo
u
r
d
iffere
n
t
g
ra
p
h
-
b
a
se
d
c
e
n
tralit
y
m
e
a
su
re
s.
We
o
b
se
rv
e
d
a
m
a
x
imu
m
a
c
c
u
ra
c
y
o
f
6
6
.
9
2
%
u
sin
g
P
a
g
e
Ra
n
k
c
e
n
tralit
y
m
e
a
su
re
wh
ich
is
sig
n
ifi
c
a
n
tl
y
b
e
tt
e
r
th
a
n
e
a
rli
e
r
re
p
o
rted
g
ra
p
h
-
b
a
se
d
Hin
d
i
WS
D
a
lg
o
r
it
h
m
se
v
a
lu
a
ted
o
n
th
e
sa
m
e
d
a
tas
e
t.
K
ey
w
o
r
d
s
:
Hin
d
i Wo
r
d
Net
Natu
r
al
lan
g
u
ag
e
p
r
o
ce
s
s
in
g
Path
-
b
ased
s
im
ilar
ity
m
ea
s
u
r
e
W
eig
h
ted
g
r
ap
h
-
b
ased
ce
n
tr
ality
m
ea
s
u
r
es
W
o
r
d
s
en
s
e
d
is
am
b
ig
u
atio
n
T
h
is i
s
a
n
o
p
e
n
a
c
c
e
ss
a
rticle
u
n
d
e
r th
e
CC B
Y
-
SA
li
c
e
n
se
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
Pra
jn
a
J
h
a
Dep
ar
tm
en
t o
f
E
lectr
o
n
ics an
d
C
o
m
m
u
n
icatio
n
,
Facu
lty
o
f
S
cien
ce
,
Un
iv
er
s
ity
o
f
Allah
ab
a
d
Sen
ate
Ho
u
s
e,
Un
iv
er
s
ity
R
o
ad
,
Old
Katr
a,
Pra
y
a
g
r
aj,
Uttar
Pra
d
esh
2
1
1
0
0
2
,
I
n
d
ia
E
m
ail:
p
r
ag
y
a
.
j
h
a.
jk
@
g
m
ail.
c
o
m
1.
I
NT
RO
D
UCT
I
O
N
T
h
er
e
is
a
g
r
o
wi
n
g
d
em
a
n
d
f
o
r
d
e
v
el
o
p
in
g
t
o
o
ls
a
n
d
tec
h
n
o
l
o
g
ies
t
h
a
t
ca
n
ai
d
i
n
e
x
c
h
a
n
g
i
n
g
a
n
d
u
n
d
er
s
ta
n
d
i
n
g
i
d
ea
s
o
n
a
g
l
o
b
al
s
c
ale
.
Na
tu
r
al
la
n
g
u
a
g
e
p
r
o
ce
s
s
i
n
g
(
N
L
P
)
is
o
f
g
r
e
at
h
el
p
i
n
m
ee
t
in
g
t
h
ese
ch
all
en
g
es
b
y
e
n
ab
li
n
g
m
ac
h
i
n
es
t
o
u
n
d
er
s
ta
n
d
an
d
g
en
e
r
at
e
h
u
m
a
n
la
n
g
u
a
g
e
.
Ma
c
h
i
n
e
t
r
an
s
l
ati
o
n
,
s
e
n
t
im
en
t
an
al
y
s
is
,
t
e
x
t
s
u
m
m
ar
iz
ati
o
n
,
s
p
ee
ch
r
e
co
g
n
it
io
n
,
an
d
o
p
ti
ca
l
c
h
ar
ac
t
e
r
r
e
co
g
n
it
io
n
.
A
r
e
s
o
m
e
o
f
t
h
e
ap
p
li
ca
ti
o
n
s
o
f
NL
P
.
H
o
w
e
v
e
r
,
t
h
e
r
e
a
r
e
c
er
t
ai
n
ch
all
e
n
g
es
a
s
s
o
ci
at
ed
wit
h
th
ese
NL
P
a
p
p
l
icat
io
n
s
.
O
n
e
o
f
t
h
e
k
e
y
c
h
al
le
n
g
es
is
r
es
o
l
v
i
n
g
th
e
a
m
b
i
g
u
it
y
p
r
es
en
t
i
n
la
n
g
u
a
g
e
[
1
]
.
A
m
b
ig
u
it
y
is
a
n
i
n
h
er
en
t
p
r
o
b
l
em
t
o
all
h
u
m
an
l
an
g
u
a
g
es.
I
t
r
ef
er
s
t
o
t
h
e
s
it
u
a
ti
o
n
w
h
er
e
a
w
o
r
d
,
p
h
r
ase
,
s
e
n
te
n
c
e,
o
r
e
n
ti
r
e
d
is
co
u
r
s
e
c
a
n
b
e
in
t
er
p
r
et
e
d
i
n
m
o
r
e
th
a
n
o
n
e
way
.
A
m
b
i
g
u
it
y
i
n
a
la
n
g
u
a
g
e
o
c
cu
r
s
d
u
e
t
o
v
a
r
i
o
u
s
r
ea
s
o
n
s
s
u
c
h
as
h
o
m
o
n
y
m
s
(
w
o
r
d
s
wit
h
s
i
m
il
a
r
s
p
ell
in
g
a
n
d
p
r
o
n
u
n
cia
ti
o
n
,
b
u
t
h
a
v
e
d
if
f
e
r
e
n
t
m
e
a
n
i
n
g
s
)
,
p
o
ly
s
em
o
u
s
wo
r
d
s
(
w
o
r
d
s
w
it
h
m
u
lti
p
l
e
m
ea
n
i
n
g
s
)
,
o
r
f
i
g
u
r
at
iv
e
(
u
s
e
o
f
i
d
i
o
m
s
a
n
d
m
e
ta
p
h
o
r
s
)
i
n
t
ex
t
o
r
s
p
e
ec
h
.
T
h
e
p
r
o
b
le
m
o
f
am
b
i
g
u
it
y
ca
n
als
o
a
r
is
e
d
u
e
t
o
d
if
f
e
r
e
n
ce
s
i
n
p
e
r
s
p
ec
t
iv
e
k
n
o
w
le
d
g
e
o
f
c
o
n
te
x
t
u
al
in
f
o
r
m
a
ti
o
n
.
F
o
r
e
x
a
m
p
le
,
i
n
t
h
e
f
o
ll
o
wi
n
g
H
in
d
i se
n
te
n
c
es,
t
h
e
w
o
r
d
‘
क
ल
म
’
{
k
a
l
a
m
}
c
o
r
r
es
p
o
n
d
s
t
o
tw
o
d
i
f
f
e
r
e
n
t
m
ea
n
i
n
g
s
:
“
मा
ल
ी
ने
ग
ु
ल
ा
ब
की
कल
म
त
ै
य
ा
र
की।
{
M
a
a
li
n
e
g
u
l
a
b
ki
k
a
l
a
m
ta
i
yy
a
r
ki
}
E
n
g
l
is
h
t
r
a
n
s
l
ati
o
n
:
T
h
e
g
a
r
d
e
n
e
r
p
r
e
p
a
r
ed
t
h
e
r
o
s
e
p
e
n
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
13
,
No
.
4
,
Dec
em
b
er
2
0
2
4
:
4
9
5
7
-
4
9
6
4
4958
म
न
े
आज
एक
ल
ा
ल
कल
म
खर
ी
द
ी
।
{
M
a
i
n
e
a
a
j
e
k
la
a
l
k
a
l
a
m
k
h
a
r
ee
d
i
}
E
n
g
l
is
h
t
r
a
n
s
l
ati
o
n
:
I
b
o
u
g
h
t
a
r
e
d
p
en
t
o
d
a
y
.
H
e
r
e
a
n
d
h
e
n
c
e
f
o
r
t
h
,
w
e
w
i
l
l
p
r
o
v
i
d
e
t
r
a
n
s
l
i
t
e
r
a
t
i
o
n
(
i
n
c
u
r
l
y
b
r
a
c
e
s
)
a
n
d
t
r
a
n
s
l
a
t
i
o
n
i
n
E
n
g
l
i
s
h
o
f
H
i
n
d
i
t
e
x
t
w
h
e
r
e
v
e
r
i
t
i
s
n
e
e
d
e
d
f
o
r
c
o
m
p
r
e
h
e
n
d
i
n
g
t
h
e
m
e
a
n
i
n
g
o
f
t
h
e
c
o
n
t
e
n
t
.
A
s
i
t
i
s
e
v
i
d
e
n
t
f
r
o
m
t
h
e
c
o
n
t
e
x
t
,
i
n
t
h
e
s
e
c
o
n
d
s
e
n
t
e
n
c
e
,
t
h
e
w
o
r
d
‘
क
ल
म
’
i
s
u
s
e
d
i
n
t
h
e
s
e
n
s
e
o
f
‘
a
n
i
n
s
t
r
u
m
e
n
t
u
s
e
d
f
o
r
w
r
i
t
i
n
g
s
o
m
e
t
h
i
n
g
’
,
w
h
e
r
e
a
s
,
i
n
t
h
e
f
i
r
s
t
s
e
n
t
e
n
c
e
,
i
t
i
s
u
s
e
d
i
n
t
h
e
s
e
n
s
e
o
f
g
r
a
f
t
i
n
g
.
W
e
a
s
a
h
u
m
a
n
b
e
i
n
g
c
a
n
e
a
s
i
l
y
i
n
t
e
r
p
r
e
t
t
h
e
m
e
a
n
i
n
g
o
f
w
o
r
d
s
b
u
t
i
t
p
o
s
e
s
a
s
i
g
n
i
f
i
c
a
n
t
c
h
a
l
l
e
n
g
e
t
o
m
a
c
h
i
n
e
s
.
T
h
e
t
a
s
k
o
f
i
d
e
n
t
i
f
y
i
n
g
t
h
e
m
e
a
n
i
n
g
o
f
a
n
a
m
b
i
g
u
o
u
s
w
o
r
d
a
u
t
o
m
a
t
i
c
a
l
l
y
i
s
k
n
o
w
n
a
s
w
o
r
d
s
e
n
s
e
d
i
s
a
m
b
i
g
u
a
t
i
o
n
(
W
S
D
)
.
W
S
D
i
s
o
n
e
o
f
t
h
e
k
e
y
r
e
s
e
a
r
c
h
a
r
e
a
s
i
n
N
L
P
.
I
t
i
s
c
o
n
s
i
d
e
r
e
d
a
n
A
I
-
c
o
m
p
l
e
t
e
p
r
o
b
l
e
m
[
1
]
.
W
S
D
i
s
a
n
i
n
t
e
r
m
e
d
i
a
t
e
t
a
s
k
i
n
N
L
P
a
p
p
l
i
c
a
t
i
o
n
s
l
i
k
e
m
a
c
h
i
n
e
t
r
a
n
s
l
a
t
i
o
n
w
h
i
l
e
i
n
a
p
p
l
i
c
a
t
i
o
n
s
l
i
k
e
i
n
f
o
r
m
a
t
i
o
n
r
e
t
r
i
e
v
a
l
,
a
n
d
t
e
x
t
s
u
m
m
a
r
i
z
a
t
i
o
n
.
I
t
c
a
n
h
e
l
p
i
n
i
m
p
r
o
v
i
n
g
t
h
e
p
e
r
f
o
r
m
a
n
c
e
.
T
h
e
d
i
f
f
i
c
u
l
t
y
p
r
e
s
e
n
t
i
n
W
SD
o
r
i
g
i
n
a
t
e
s
f
r
o
m
m
u
lt
i
p
l
e
f
a
ct
o
r
s
s
u
c
h
as
t
h
e
es
ta
b
l
is
h
m
e
n
t
o
f
m
e
a
n
i
n
g
o
f
w
o
r
d
s
;
d
et
e
r
m
i
n
a
ti
o
n
o
f
t
h
e
g
r
a
n
u
l
a
r
i
t
y
o
f
s
e
n
s
e
i
n
v
e
n
t
o
r
y
,
n
a
t
u
r
e
o
f
w
o
r
d
s
(
d
o
m
a
i
n
-
s
p
e
ci
f
i
c
o
r
u
n
r
e
s
t
r
i
c
t
e
d
)
.
T
h
e
t
a
s
k
o
f
W
S
D
h
as
e
v
o
l
v
e
d
o
v
e
r
t
h
e
d
e
c
a
d
e
i
n
c
o
r
p
o
r
a
t
i
n
g
n
e
w
t
e
c
h
n
i
q
u
es
.
T
h
e
e
a
r
l
i
es
t
k
n
o
w
n
m
e
t
h
o
d
f
o
r
W
SD
t
as
k
i
s
t
h
e
d
i
c
ti
o
n
a
r
y
-
b
a
s
e
d
L
e
s
k
’
s
a
l
g
o
r
i
t
h
m
w
h
i
c
h
u
s
e
s
d
i
r
e
ct
o
v
e
r
l
a
p
b
e
t
w
e
e
n
t
h
e
c
o
n
t
e
x
t
a
n
d
s
e
n
s
e
d
e
f
i
n
i
t
i
o
n
s
t
o
d
is
a
m
b
i
g
u
a
te
an
a
m
b
i
g
u
o
u
s
w
o
r
d
.
T
h
e
m
e
th
o
d
w
a
s
l
a
t
e
r
m
o
d
i
f
i
e
d
t
o
u
s
e
s
t
a
n
d
a
r
d
le
x
i
c
al
r
e
s
o
u
r
c
e
s
s
u
c
h
a
s
W
o
r
d
N
et
[
2
]
a
n
d
o
t
h
e
r
s
i
m
i
la
r
i
t
y
m
e
as
u
r
e
s
b
e
s
i
d
es
d
i
r
e
c
t
o
v
e
r
la
p
s
i
m
i
l
a
r
it
y
m
e
a
s
u
r
e
s
[
3
]
.
F
o
r
t
h
e
E
n
g
l
i
s
h
l
a
n
g
u
a
g
e
,
m
a
n
y
s
u
p
e
r
v
i
s
e
d
a
l
g
o
r
i
t
h
m
s
h
a
v
e
b
e
e
n
e
x
p
l
o
r
e
d
a
n
d
p
r
o
p
o
s
e
d
b
y
s
c
i
e
n
t
i
s
t
s
w
o
r
l
d
w
i
d
e
.
M
o
s
t
o
f
t
h
e
s
e
a
l
g
o
r
i
t
h
m
s
u
t
i
l
i
z
e
l
e
x
i
c
a
l
a
n
d
c
o
n
t
e
x
t
u
a
l
k
n
o
w
l
e
d
g
e
f
o
r
d
i
s
a
m
b
i
g
u
a
t
i
o
n
[
1
]
a
n
d
h
a
v
e
b
e
e
n
s
u
c
c
e
s
s
f
u
l
i
n
a
c
h
i
e
v
i
n
g
g
o
o
d
a
c
c
u
r
a
c
y
.
H
o
w
e
v
e
r
,
t
h
e
s
e
m
e
t
h
o
d
s
r
e
q
u
i
r
e
a
s
e
n
s
e
-
t
a
g
g
e
d
c
o
r
p
u
s
f
o
r
t
r
a
i
n
i
n
g
.
T
h
e
c
r
e
a
t
i
o
n
o
f
s
u
c
h
a
c
o
r
p
u
s
i
s
a
l
a
b
o
r
a
n
d
t
i
m
e
-
c
o
n
s
u
m
i
n
g
t
a
s
k
.
T
h
i
s
p
o
s
e
s
a
p
r
o
b
l
e
m
i
n
a
p
p
l
i
c
a
t
i
o
n
s
o
f
s
u
p
e
r
v
i
s
e
d
a
p
p
r
o
a
c
h
e
s
f
o
r
r
e
s
o
u
r
c
e
-
c
o
n
s
t
r
a
i
n
t
l
a
n
g
u
a
g
e
s
l
i
k
e
H
i
n
d
i
a
n
d
o
t
h
e
r
I
n
d
i
a
n
l
a
n
g
u
a
g
e
s
.
T
h
i
s
m
o
t
i
v
a
t
e
s
r
e
s
e
a
r
c
h
e
r
s
t
o
e
x
p
l
o
r
e
u
n
s
u
p
e
r
v
i
s
e
d
m
e
t
h
o
d
s
f
o
r
W
S
D
.
T
h
e
u
n
s
u
p
e
r
v
i
s
e
d
a
p
p
r
o
a
c
h
f
o
r
d
i
s
a
m
b
i
g
u
a
t
i
n
g
w
o
r
d
s
e
n
s
e
w
a
s
f
i
r
s
t
i
n
t
r
o
d
u
c
e
d
b
y
Y
a
r
o
w
s
k
y
[
4
]
,
[
5
]
.
H
e
u
s
e
d
a
s
m
a
l
l
n
u
m
b
e
r
o
f
s
e
e
d
i
n
s
t
a
n
c
e
s
f
o
r
d
i
f
f
e
r
e
n
t
s
e
n
s
e
s
o
f
a
w
o
r
d
a
n
d
t
h
e
n
i
t
e
r
a
t
i
v
e
l
y
t
a
g
i
n
s
t
a
n
c
e
s
i
n
a
n
u
n
t
a
g
g
e
d
c
o
r
p
u
s
u
s
i
n
g
c
o
l
l
o
c
a
t
e
.
H
e
p
r
o
p
o
s
e
d
t
h
e
u
s
e
o
f
o
n
e
s
e
n
s
e
p
e
r
d
i
s
c
o
u
r
s
e
,
a
n
d
o
n
e
s
e
n
s
e
p
e
r
c
o
l
l
o
c
a
t
i
o
n
t
o
t
a
g
r
e
m
a
i
n
i
n
g
i
n
s
t
a
n
c
e
s
[
5
]
.
T
h
e
m
a
i
n
p
r
o
b
l
e
m
t
h
a
t
w
a
s
o
b
s
e
r
v
e
d
w
i
t
h
t
h
e
u
n
s
u
p
e
r
v
i
s
e
d
a
p
p
r
o
a
c
h
i
s
t
h
a
t
s
y
n
t
a
c
t
i
c
-
s
e
m
a
n
t
i
c
r
e
l
a
t
i
o
n
s
b
e
t
w
e
e
n
w
o
r
d
p
a
i
r
s
a
n
d
t
h
e
c
o
n
c
e
p
t
u
a
l
i
n
f
o
r
m
a
t
i
o
n
o
f
n
e
a
r
b
y
w
o
r
d
s
w
e
r
e
n
o
t
c
l
e
a
r
l
y
i
n
c
o
r
p
o
r
a
t
e
d
.
T
h
e
g
r
a
p
h
-
b
a
s
e
d
a
p
p
r
o
a
c
h
p
r
o
v
i
d
e
s
a
p
o
w
e
r
f
u
l
r
e
p
r
e
s
e
n
t
a
t
i
o
n
f
o
r
m
o
d
e
l
i
n
g
s
t
r
u
c
t
u
r
a
l
a
n
d
c
o
m
p
l
e
x
r
e
l
a
t
i
o
n
s
h
i
p
s
e
x
i
s
t
i
n
g
b
e
t
w
e
e
n
d
a
t
a
u
n
i
t
s
.
S
o
m
e
o
f
t
h
e
r
e
c
e
n
t
r
e
s
e
a
r
c
h
a
p
p
l
i
c
a
t
i
o
n
s
w
i
t
h
g
r
a
p
h
-
b
a
s
e
d
a
p
p
l
i
c
a
t
i
o
n
s
i
n
t
h
e
f
i
e
l
d
o
f
A
I
c
a
n
b
e
f
o
u
n
d
i
n
[
6
]
.
T
h
e
g
r
a
p
h
-
b
a
s
e
d
a
p
p
r
o
a
c
h
e
s
a
r
e
b
e
i
n
g
v
a
s
t
l
y
u
s
e
d
i
n
t
h
e
W
S
D
r
e
s
e
a
r
c
h
a
r
e
a
[
7
]
.
I
n
a
g
r
a
p
h
-
b
a
s
e
d
a
l
g
o
r
i
t
h
m
,
t
h
e
l
e
x
i
c
a
l
e
n
t
i
t
i
e
s
a
r
e
r
e
p
r
e
s
e
n
t
e
d
a
s
n
o
d
e
s
a
n
d
t
h
e
s
y
n
t
a
c
t
i
c
-
s
e
m
a
n
t
i
c
r
e
l
a
t
i
o
n
s
h
i
p
b
e
t
w
e
e
n
t
h
e
m
i
s
r
e
p
r
e
s
e
n
t
e
d
a
s
e
d
g
e
s
i
n
a
g
r
a
p
h
.
T
h
e
g
r
a
p
h
-
b
a
s
e
d
a
l
g
o
r
it
h
m
s
ar
e
q
u
i
t
e
u
s
e
f
u
l
f
o
r
l
o
w
-
r
e
s
o
u
r
c
e
l
a
n
g
u
a
g
e
s
a
s
i
t
d
o
e
s
n
o
t
r
eq
u
i
r
e
l
a
r
g
e
t
r
a
i
n
i
n
g
d
a
t
as
e
ts
.
O
wi
n
g
t
o
t
h
es
e
p
r
o
p
e
r
t
i
es
a
n
d
t
h
e
i
r
s
u
c
c
es
s
f
u
l
a
p
p
l
i
c
a
ti
o
n
s
i
n
E
n
g
l
is
h
W
SD
t
a
s
k
s
,
w
e
p
r
o
p
o
s
e
a
n
d
e
v
a
l
u
a
t
e
a
n
o
v
e
l
g
r
a
p
h
-
b
as
e
d
a
l
g
o
r
it
h
m
f
o
r
t
h
e
H
i
n
d
i
W
S
D
.
T
h
e
t
a
r
g
e
t
w
o
r
d
s
a
r
e
a
m
b
ig
u
o
u
s
H
i
n
d
i
n
o
u
n
s
.
W
e
u
s
e
t
h
e
L
e
ac
o
c
k
-
C
h
o
d
o
r
o
w
m
e
t
h
o
d
[
8
]
t
o
a
s
s
i
g
n
w
e
i
g
h
ts
t
o
e
d
g
e
s
a
n
d
d
i
s
a
m
b
i
g
u
a
t
e
a
w
o
r
d
b
y
s
e
l
e
c
t
i
n
g
a
s
e
n
s
e
n
o
d
e
t
h
a
t
r
e
c
ei
v
e
s
t
h
e
h
i
g
h
e
s
t
s
c
o
r
e
u
s
i
n
g
t
h
e
g
r
a
p
h
c
e
n
t
r
a
l
i
t
y
m
e
as
u
r
e
s
.
W
e
i
n
v
es
t
ig
a
t
e
f
o
u
r
d
i
f
f
e
r
e
n
t
g
r
a
p
h
-
b
a
s
e
d
c
e
n
t
r
a
l
it
y
m
e
as
u
r
e
s
:
cl
o
s
e
n
es
s
,
b
e
t
w
ee
n
n
e
s
s
,
e
ig
e
n
v
e
c
t
o
r
,
a
n
d
P
a
g
eR
a
n
k
.
E
a
r
l
i
e
r
w
o
r
k
s
i
n
v
o
l
v
i
n
g
g
r
a
p
h
-
b
a
s
e
d
H
i
n
d
i
W
S
D
u
s
e
m
i
n
i
m
u
m
c
o
s
t
s
p
a
n
n
i
n
g
t
r
e
e
[
9
]
o
r
p
e
r
f
o
r
m
a
r
a
n
d
o
m
w
al
k
f
o
r
d
i
s
a
m
b
i
g
u
at
i
o
n
[
1
0
]
,
w
h
e
r
e
a
s
t
h
is
s
t
u
d
y
u
s
e
s
:
i
)
L
e
a
c
o
c
k
C
h
o
d
o
r
o
w
m
et
h
o
d
,
a
p
a
t
h
-
b
as
e
d
s
i
m
il
a
r
it
y
m
e
as
u
r
e
,
t
o
c
o
m
p
u
t
e
t
h
e
e
d
g
e
w
e
i
g
h
t
,
a
n
d
i
i
)
u
ti
l
i
ze
s
s
co
r
e
s
a
s
s
i
g
n
e
d
t
o
n
o
d
e
s
u
s
i
n
g
g
r
a
p
h
c
e
n
t
r
a
l
i
t
y
m
e
as
u
r
es
i
n
d
i
s
am
b
i
g
u
a
t
i
o
n
.
W
e
ex
p
er
im
en
tally
ev
alu
ate
th
e
p
er
f
o
r
m
an
ce
o
f
th
e
p
r
o
p
o
s
ed
alg
o
r
ith
m
u
s
in
g
f
o
u
r
d
if
f
er
e
n
t
ce
n
tr
ality
m
ea
s
u
r
es
an
d
co
m
p
ar
e
th
eir
p
er
f
o
r
m
an
ce
o
n
2
0
p
o
ly
s
em
o
u
s
Hin
d
i
n
o
u
n
s
u
s
ed
i
n
[
1
1
]
.
T
h
e
d
ataset
is
a
p
ar
t
o
f
th
e
s
en
s
e
an
n
o
tate
d
d
ataset
a
v
ailab
le
o
n
t
h
e
tec
h
n
o
lo
g
y
d
e
v
elo
p
m
en
t
f
o
r
I
n
d
ia
n
lan
g
u
ag
es
(
T
DI
L
)
web
s
ite
[
1
2
]
.
Sin
g
h
et
a
l.
[
1
1
]
u
s
es
th
e
L
ea
c
o
ck
-
C
h
o
d
o
r
o
w
s
im
ilar
ity
s
co
r
e
in
a
L
esk
-
lik
e
s
ettin
g
.
T
h
e
ch
o
ice
o
f
th
e
d
ataset
m
ak
es
it
p
o
s
s
ib
le
to
co
m
p
a
r
e
th
e
p
e
r
f
o
r
m
an
ce
o
f
th
e
p
r
o
p
o
s
ed
alg
o
r
ith
m
.
W
e
o
b
tain
an
o
v
er
all
av
er
ag
e
ac
cu
r
ac
y
o
f
6
6
.
9
2
% u
s
in
g
th
e
Pag
eRan
k
alg
o
r
ith
m
,
f
o
llo
wed
b
y
6
6
.
4
9
% o
b
tain
ed
u
s
in
g
th
e
c
lo
s
en
ess
ce
n
tr
ality
alg
o
r
ith
m
wh
ich
is
b
etter
th
an
th
e
ac
c
u
r
ac
y
r
ep
o
r
te
d
in
[
1
0
]
,
[
1
1
]
.
T
h
e
p
ap
e
r
is
d
iv
id
ed
in
to
th
e
f
o
llo
win
g
s
ec
tio
n
s
.
I
n
s
ec
tio
n
1
,
th
e
p
r
o
b
lem
o
f
w
o
r
d
a
m
b
ig
u
ity
in
th
e
Hin
d
i
lan
g
u
ag
e
an
d
o
u
r
a
p
p
r
o
ac
h
to
r
eso
lv
e
it
is
b
r
ie
f
ly
in
t
r
o
d
u
ce
d
;
s
ec
tio
n
2
d
is
cu
s
s
es
ex
is
tin
g
g
r
a
p
h
-
b
ased
alg
o
r
ith
m
s
ap
p
lied
f
o
r
W
SD
in
E
n
g
lis
h
a
n
d
Hin
d
i
lan
g
u
a
g
es.
I
n
s
ec
tio
n
3
,
we
in
tr
o
d
u
ce
th
e
g
r
a
p
h
-
b
ased
ce
n
tr
ality
m
ea
s
u
r
es
b
ein
g
u
s
ed
in
th
is
wo
r
k
.
Sectio
n
4
p
r
o
v
i
d
es
th
e
d
etails
o
f
th
e
p
r
o
p
o
s
ed
m
eth
o
d
o
lo
g
y
.
T
h
e
ex
p
er
im
en
t,
e
v
alu
atio
n
,
an
d
co
m
p
ar
ativ
e
r
esu
lts
f
o
llo
wed
b
y
a
d
etailed
d
is
cu
s
s
io
n
o
f
o
u
r
ex
p
e
r
im
en
tal
o
b
s
er
v
atio
n
s
in
s
ec
tio
n
5
.
I
n
s
ec
tio
n
6
,
we
c
o
n
clu
d
e
o
u
r
p
ap
er
an
d
s
u
g
g
est f
u
tu
r
e
d
ir
ec
tio
n
s
.
2.
RE
L
AT
E
D
WO
RK
S
T
h
is
s
ec
tio
n
b
r
ief
ly
r
ev
iews
s
o
m
e
o
f
th
e
ea
r
lier
g
r
ap
h
-
b
ase
d
W
SD
m
eth
o
d
s
.
On
e
o
f
th
e
e
ar
ly
wo
r
k
s
in
v
o
lv
in
g
W
o
r
d
Net
g
r
a
p
h
f
o
r
W
SD
task
i
s
r
ep
o
r
ted
in
[
1
3
]
.
I
n
th
is
p
a
p
er
,
t
h
e
m
in
im
u
m
s
em
an
tic
d
is
tan
ce
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
Un
s
u
p
ervis
ed
h
in
d
i wo
r
d
s
en
s
e
d
is
a
mb
ig
u
a
tio
n
u
s
in
g
g
r
a
p
h
-
b
a
s
ed
ce
n
tr
a
lity m
ea
s
u
r
es
(
P
r
a
jn
a
Jh
a
)
4959
b
etwe
en
p
air
wis
e
s
y
n
s
ets
th
as
b
ee
n
u
s
ed
to
d
is
am
b
i
g
u
ate
a
m
b
ig
u
o
u
s
n
o
u
n
s
ap
p
ea
r
in
g
in
a
co
n
tex
t
win
d
o
w.
T
h
e
W
o
r
d
Net
tax
o
n
o
m
y
a
n
d
th
e
n
o
tio
n
o
f
co
n
ce
p
tu
al
d
is
tan
ce
is
u
s
ed
f
o
r
r
eso
lv
in
g
lex
ical
am
b
ig
u
ities
o
f
n
o
u
n
s
in
[
1
4
]
.
An
u
n
s
u
p
er
v
is
ed
k
n
o
wled
g
e
-
b
ased
W
SD
alg
o
r
ith
m
p
r
o
p
o
s
ed
i
n
[
1
5
]
u
s
es
Pag
eRan
k
o
n
t
h
e
g
r
ap
h
ex
tr
ac
te
d
f
r
o
m
th
e
d
o
cu
m
en
t
f
o
r
o
p
e
n
-
tex
t
W
SD.
T
h
e
v
er
tices
o
f
th
e
g
r
ap
h
wer
e
d
e
r
iv
ed
f
r
o
m
s
y
n
s
ets,
an
d
th
e
ed
g
es we
r
e
d
er
iv
e
d
u
s
in
g
s
em
an
tic
r
elatio
n
s
am
o
n
g
W
o
r
d
Net
s
y
n
s
ets.
Nav
ig
li
[
1
6
]
in
tr
o
d
u
ce
d
th
e
u
s
e
o
f
lex
ical
ch
ain
s
an
d
s
tr
u
ctu
r
a
l
s
em
an
tic
in
ter
co
n
n
ec
tio
n
s
f
o
r
d
is
am
b
ig
u
atio
n
.
He
p
r
o
p
o
s
ed
a
n
o
v
el
m
eth
o
d
o
f
in
ter
lin
k
in
g
s
en
s
es a
s
a
g
r
ap
h
-
b
ased
lex
ico
n
s
tr
u
ctu
r
e
a
n
d
ass
ig
n
in
g
th
em
to
co
n
tex
t w
o
r
d
s
,
an
d
co
n
s
ec
u
tiv
el
y
r
an
k
in
g
th
em
u
s
in
g
th
e
h
y
p
er
l
in
k
-
i
n
d
u
ce
d
to
p
ic
s
ea
r
ch
(
HI
T
S
)
alg
o
r
ith
m
.
T
s
atsar
o
n
is
et
a
l.
[
1
7
]
im
p
lem
en
ts
f
o
u
r
s
em
an
tic
g
r
ap
h
r
ep
r
esen
tatio
n
s
o
n
s
en
s
ev
al
-
2
an
d
s
en
s
ev
al
-
3
d
atasets
v
iz.
s
p
r
ea
d
in
g
ac
tiv
atio
n
f
o
r
n
etwo
r
k
p
r
o
ce
s
s
in
g
(
SAN
)
,
Pa
g
e
R
an
k
,
HI
T
S,
an
d
p
r
im
itiv
e
r
an
k
(
P
-
R
an
k
)
.
An
o
t
h
e
r
w
o
r
k
i
n
v
o
lv
in
g
E
n
g
li
s
h
W
SD
u
s
es
a
c
o
-
o
cc
u
r
r
e
n
ce
g
r
a
p
h
i
n
w
h
i
ch
v
er
tic
es
co
n
s
is
t
o
f
w
o
r
d
s
th
a
t
o
cc
u
r
t
o
g
e
th
er
w
it
h
th
e
ta
r
g
et
w
o
r
d
,
a
n
d
ed
g
es
r
e
p
r
es
en
t
t
h
e
ir
f
r
e
q
u
e
n
c
y
a
n
d
i
d
en
ti
f
y
s
en
s
e
b
y
it
er
ati
v
e
ly
s
ele
cti
n
g
h
i
g
h
l
y
c
o
n
n
ec
t
ed
h
u
b
s
[
1
8
]
.
T
h
ese
h
u
b
s
ar
e
tr
e
ate
d
as
a
d
e
p
i
cti
o
n
o
f
th
e
s
e
n
s
es
i
n
d
u
ce
d
b
y
t
h
e
alg
o
r
it
h
m
,
t
h
e
s
am
e
w
ay
as
cl
u
s
ter
s
o
f
ex
am
p
l
es i
n
[
1
9
]
.
A
g
i
r
r
e
a
n
d
So
r
o
a
[
2
0
]
h
av
e
s
h
o
wn
u
n
s
u
p
e
r
v
is
e
d
wo
r
d
s
en
s
e
i
n
d
u
cti
o
n
(
W
SI
)
g
i
v
es
b
et
te
r
r
es
u
lts
c
o
m
p
a
r
ed
t
o
s
u
p
e
r
v
is
e
d
W
S
I
i
n
t
er
m
s
o
f
F
-
s
co
r
e
o
n
S
en
s
E
v
al
-
3
d
at
ase
t
[
2
1
]
.
A
n
o
t
h
e
r
w
ay
o
f
ap
p
l
y
i
n
g
t
h
e
g
r
a
p
h
-
b
ase
d
al
g
o
r
it
h
m
i
n
u
n
s
u
p
e
r
v
is
e
d
W
SD
i
s
b
y
e
x
p
l
o
iti
n
g
t
h
e
h
ie
r
ar
ch
ica
l
p
r
o
p
e
r
t
y
o
f
t
h
e
g
r
ap
h
i
n
th
e
h
i
er
ar
c
h
ic
al
r
a
n
d
o
m
g
r
ap
h
(
HR
G
)
al
g
o
r
i
t
h
m
[
2
2
]
.
T
h
is
wo
r
k
u
s
es
a
s
en
s
e
-
t
a
g
g
e
d
co
r
p
u
s
s
im
i
la
r
t
o
[
2
0
]
a
n
d
c
o
m
p
u
t
es
co
ll
o
c
at
io
n
al
w
ei
g
h
t
b
y
a
p
p
l
y
i
n
g
t
h
e
J
a
cc
a
r
d
c
o
e
f
f
ici
e
n
t
s
im
il
ar
it
y
o
n
t
h
e
ta
r
g
et
w
o
r
d
a
n
d
its
co
n
t
ex
t
w
o
r
d
s
.
T
h
e
r
es
u
lt
s
h
o
ws
t
h
a
t
HR
Gs
o
u
t
p
er
f
o
r
m
t
h
e
C
h
i
n
ese
wh
is
p
e
r
u
n
we
ig
h
t
e
d
(
C
W
U
)
b
aseli
n
e
b
y
9
.
4
%
.
A
m
e
th
o
d
o
f
i
n
d
u
ci
n
g
s
e
n
s
e
u
s
i
n
g
c
o
l
lo
c
ati
o
n
s
i
n
a
g
r
a
p
h
is
p
r
ese
n
t
ed
i
n
[
2
3
]
.
T
h
e
a
u
t
h
o
r
s
u
s
e
d
C
h
i
n
ese
W
h
is
p
e
r
s
a
n
d
J
a
cc
a
r
d
s
im
i
la
r
it
y
t
o
p
o
p
u
l
at
e
t
h
e
g
r
a
p
h
.
Nar
ay
a
n
a
n
an
d
B
h
a
tta
c
h
a
r
a
y
y
a
[
2
4
]
f
o
r
m
e
d
a
s
e
m
a
n
ti
c
d
i
r
e
cte
d
-
ac
y
cli
c
-
g
r
a
p
h
(
DAG
)
w
h
er
e
v
e
r
ti
ce
s
ar
e
t
h
e
te
x
t
u
a
l
w
o
r
d
s
y
n
s
e
ts
,
a
n
d
f
o
r
e
ac
h
s
y
n
s
et
o
f
th
e
w
o
r
d
,
t
h
e
l
in
k
d
is
ta
n
c
e
f
r
o
m
t
h
e
s
y
n
s
et
to
t
h
e
cu
r
r
e
n
t
v
e
r
t
ex
o
f
th
e
DA
G
a
n
d
t
h
e
c
u
r
r
e
n
t
wo
r
d
f
r
o
m
t
h
e
te
x
t
a
r
e
d
et
er
m
i
n
e
d
u
s
i
n
g
W
o
r
d
Ne
t
o
n
Se
m
C
o
r
-
c
o
r
p
u
s
[
2
5
]
.
An
u
n
s
u
p
e
r
v
is
ed
E
n
g
lis
h
W
S
D
alg
o
r
ith
m
p
r
o
p
o
s
ed
in
[
2
6
]
u
s
es
th
e
ce
n
tr
ality
alg
o
r
ith
m
s
to
th
e
weig
h
ted
g
r
ap
h
an
d
f
in
d
s
th
e
m
o
s
t
ap
p
r
o
p
r
iate
s
en
s
e
u
s
in
g
th
e
v
o
tin
g
m
eth
o
d
f
r
o
m
s
ix
d
if
f
er
en
t
c
en
tr
ality
m
ea
s
u
r
es.
So
m
e
o
th
er
n
o
tab
le
wo
r
k
s
in
v
o
lv
in
g
m
u
ltil
in
g
u
al
r
eso
u
r
ce
s
f
o
r
d
is
am
b
ig
u
atio
n
in
cl
u
d
e
[
2
7
]
,
[
2
8
]
.
I
n
r
ec
en
t
y
ea
r
s
,
ef
f
o
r
ts
h
av
e
b
ee
n
m
ad
e
b
y
I
n
d
ian
r
esear
ch
er
s
to
ex
p
lo
r
e
th
e
g
r
ap
h
f
ea
tu
r
es,
an
d
g
r
ap
h
m
ea
s
u
r
es
f
o
r
s
o
lv
in
g
ce
r
tain
o
p
e
n
-
class
r
esear
ch
p
r
o
b
lem
s
,
W
SD
b
ein
g
o
n
e
o
f
th
em
.
T
h
e
wo
r
k
in
v
o
lv
in
g
Hin
d
i
W
SD
in
clu
d
es
[
9
]
,
[
2
9
]
–
[
3
2
]
.
Acc
o
r
d
in
g
to
J
ain
an
d
L
o
b
iy
al
[
9
]
,
g
r
ap
h
-
b
ased
co
n
n
ec
tiv
ity
m
ea
s
u
r
es
ar
e
u
s
ed
f
o
r
Hin
d
i
W
SD
,
th
e
lin
k
s
b
etwe
en
th
e
s
y
n
s
et
n
o
d
es
ar
e
cr
ea
ted
u
s
in
g
v
ar
io
u
s
r
elatio
n
s
h
ip
s
d
ef
in
ed
in
W
o
r
d
Net.
Ho
wev
er
,
n
o
weig
h
ts
ar
e
ass
ig
n
ed
t
o
th
ese
lin
k
s
an
d
ea
ch
lin
k
i
s
ass
u
m
ed
to
tak
e
“u
n
ity
”
weig
h
t.
T
h
e
u
s
e
o
f
lo
c
al
an
d
g
lo
b
al
g
r
a
p
h
co
n
n
ec
tiv
i
ty
m
ea
s
u
r
es
was
in
v
o
lv
e
d
in
[
2
9
]
.
A
g
r
ap
h
-
b
ased
alg
o
r
ith
m
to
d
is
am
b
ig
u
ate
o
p
en
-
class
wo
r
d
s
was
p
r
o
p
o
s
ed
in
[
3
0
]
wh
ich
u
s
es
n
o
d
e
n
eig
h
b
o
r
h
o
o
d
co
n
n
ec
tiv
ity
m
ea
s
u
r
es
f
o
r
d
is
am
b
ig
u
atio
n
.
A
n
o
v
el
id
e
a
th
a
t
th
e
ass
o
ciatio
n
b
etwe
en
wo
r
d
s
is
g
o
v
er
n
ed
b
y
a
g
r
ad
u
al
tr
an
s
itio
n
f
r
o
m
b
ein
g
r
elate
d
to
n
o
t
r
elate
d
,
i.e
.
,
th
er
e
is
a
d
eg
r
ee
o
f
f
u
zz
in
ess
,
was
p
r
o
p
o
s
ed
b
y
J
ain
an
d
L
o
b
iy
al
[
3
1
]
.
T
h
e
a
u
th
o
r
s
d
e
v
elo
p
e
d
a
f
u
zz
y
Hin
d
i
W
o
r
d
Net
an
d
u
s
ed
it
t
o
p
e
r
f
o
r
m
Hin
d
i
W
SD
u
s
in
g
f
u
zz
y
c
o
n
n
ec
tiv
ity
m
ea
s
u
r
es.
T
h
e
co
n
ce
p
t
o
f
co
o
p
er
a
tiv
e
g
am
e
th
eo
r
y
an
d
f
u
zz
y
H
in
d
i
W
o
r
d
Net
was
u
s
ed
d
is
am
b
ig
u
atio
n
in
[
3
2
]
.
R
esear
ch
f
o
cu
s
in
g
o
n
g
r
ap
h
-
b
ased
W
SD
is
also
ap
p
lied
i
n
I
n
d
ian
lan
g
u
ag
es
s
u
ch
as T
elu
g
u
[
3
3
]
.
T
h
e
p
r
o
p
o
s
ed
wo
r
k
d
if
f
er
s
f
r
o
m
all
th
e
s
e
ea
r
lier
r
ep
o
r
ted
wo
r
k
as sp
ec
if
ied
in
s
ec
tio
n
1
.
3.
SE
M
AN
T
I
C
S
I
M
I
L
ARI
T
Y
AND
G
RAP
H
-
B
AS
E
D
C
E
N
T
RA
L
I
T
Y
M
E
AS
URE
S
T
h
is
s
ec
tio
n
in
tr
o
d
u
ce
s
th
e
s
em
an
tic
s
im
ilar
ity
an
d
g
r
ap
h
ce
n
tr
ality
m
ea
s
u
r
es
u
s
ed
i
n
th
is
s
tu
d
y
.
Sem
an
tic
s
im
ilar
ity
d
eter
m
in
es
th
e
lik
elih
o
o
d
esti
m
atio
n
o
f
th
e
s
em
an
tic
ass
o
ciatio
n
th
at
ex
is
ts
b
etwe
en
two
s
em
an
tic
en
titi
es.
I
t
is
u
s
u
ally
o
b
tain
ed
u
tili
zin
g
th
e
in
f
o
r
m
at
io
n
co
n
ten
t o
f
th
e
m
a
n
u
ally
a
n
n
o
tated
c
o
r
p
o
r
a
o
r
s
tr
u
ctu
r
ed
r
eso
u
r
ce
s
s
u
ch
as
W
o
r
d
Net.
A
n
u
m
b
er
o
f
W
o
r
d
Net
-
b
ased
s
em
an
tic
s
im
ilar
ity
m
ea
s
u
r
es
h
av
e
b
ee
n
p
r
o
p
o
s
ed
to
co
m
p
u
te
s
em
an
ti
c
s
im
ilar
ity
b
etwe
en
th
e
two
s
y
n
s
ets
[
8
]
.
W
e
u
s
e
L
ea
co
ck
-
C
h
o
d
o
r
o
w
s
em
an
tic
s
im
ilar
ity
m
ea
s
u
r
e
to
d
eter
m
in
e
th
e
s
em
an
tic
ass
o
ciatio
n
b
etwe
en
s
y
n
s
et
p
air
s
.
T
h
e
L
ea
co
ck
-
C
h
o
d
o
r
o
w
m
eth
o
d
co
n
s
id
er
s
th
e
co
n
c
ep
t
u
al
d
is
tan
ce
b
etwe
en
th
e
two
co
n
ce
p
ts
in
th
e
h
ie
r
ar
ch
y
/tax
o
n
o
m
y
o
f
th
e
lex
ical
d
atab
ase
s
u
ch
as
W
o
r
d
Net.
T
h
e
s
im
ilar
ity
s
co
r
e
b
etwe
en
th
e
two
co
n
ce
p
ts
is
ca
lcu
lated
b
y
d
eter
m
in
i
n
g
th
e
s
h
o
r
test
p
ath
co
n
tain
in
g
th
e
l
ea
s
t
co
m
m
o
n
s
u
b
s
u
m
er
o
f
two
co
n
ce
p
ts
,
an
d
its
d
ep
th
.
Ma
th
em
atica
lly
,
th
e
L
ea
co
ck
-
C
h
o
d
o
r
o
w
s
im
ilar
ity
m
ea
s
u
r
e
ca
n
b
e
ex
p
r
ess
ed
as
(
1
)
:
=
−
l
o
g
(
+
1
)
2
∗
(
1
)
W
h
er
e
+
1
ar
e
th
e
two
c
o
n
ce
p
ts
,
an
d
D
is
th
e
m
ax
im
u
m
d
e
p
th
o
f
th
e
tax
o
n
o
m
y
.
Her
e,
f
o
r
n
o
u
n
s
,
D
is
12
[
1
1
]
in
th
e
W
o
r
d
Net
h
ie
r
a
r
ch
y
.
T
h
e
g
r
ap
h
-
b
ased
ce
n
tr
al
ity
alg
o
r
ith
m
is
ap
p
lied
to
a
g
r
ap
h
o
r
n
etwo
r
k
to
d
eter
m
in
e
t
h
e
s
ig
n
if
ican
c
e
o
f
ea
ch
n
o
d
e
r
elativ
e
to
o
th
er
n
o
d
es
in
th
e
g
r
a
p
h
.
I
t
ca
lcu
la
tes
th
e
ce
n
tr
ality
o
r
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
13
,
No
.
4
,
Dec
em
b
er
2
0
2
4
:
4
9
5
7
-
4
9
6
4
4960
im
p
o
r
tan
ce
o
f
ea
c
h
n
o
d
e
c
o
n
s
id
er
in
g
th
e
l
o
ca
tio
n
o
f
th
e
n
o
d
e
in
t
h
e
g
r
ap
h
,
an
d
its
co
n
n
ec
tiv
ity
with
th
e
ad
jo
in
in
g
n
o
d
es.
I
n
o
u
r
wo
r
k
,
we
h
av
e
ap
p
lied
f
o
u
r
ce
n
tr
alit
y
alg
o
r
ith
m
s
as
f
o
llo
win
g
.
3
.
1
.
Clo
s
eness
c
ent
ra
lity
Fo
r
a
n
o
d
e
,
clo
s
en
ess
is
d
ef
in
ed
as
th
e
r
ec
i
p
r
o
ca
l o
f
th
e
s
u
m
o
f
s
h
o
r
test
d
is
tan
ce
b
etwe
en
0
to
all
th
e
o
th
er
n
o
d
es
o
v
er
all
th
e
r
e
ac
h
ab
le
n
o
d
es.
Fo
r
th
e
weig
h
t
ed
g
r
ap
h
,
th
e
weig
h
t
o
f
th
e
e
d
g
es
is
co
n
s
id
er
ed
in
ca
lcu
latin
g
th
e
s
h
o
r
test
p
ath
f
o
r
a
s
p
ec
if
ic
n
o
d
e
.
I
t c
an
b
e
ex
p
r
ess
ed
u
s
in
g
(
2
)
.
(
)
=
−
1
∑
(
ℎ
ℎ
ℎ
(
,
,
ℎ
)
−
1
=
1
(
2
)
3
.
2
.
B
et
wee
nn
ess
ce
ntr
a
lity
Fo
r
a
n
o
d
e
,
b
etwe
en
n
ess
is
d
e
f
in
ed
in
ter
m
s
o
f
th
e
to
tal
n
u
m
b
er
o
f
s
h
o
r
test
p
ath
s
ex
is
tin
g
b
etwe
en
two
n
o
d
e
p
air
s
an
d
,
an
d
th
e
n
u
m
b
er
o
f
s
u
ch
p
ath
s
th
at
p
ass
es
th
r
o
u
g
h
th
e
in
ter
m
e
d
iate
n
o
d
e
.
T
h
e
p
r
o
ce
s
s
is
r
ep
ea
ted
f
o
r
all
th
e
ad
jo
in
in
g
p
air
s
o
f
n
o
d
es
a
n
d
n
o
d
e
in
t
h
e
g
r
ap
h
.
Fo
r
weig
h
ted
b
etwe
en
n
ess
ce
n
tr
ality
,
th
e
ed
g
e
weig
h
ts
ar
e
co
n
s
id
er
ed
wh
ile
c
o
m
p
u
tin
g
th
e
to
tal
weig
h
t
o
f
s
h
o
r
test
p
a
th
s
b
etwe
en
an
d
,
an
d
th
e
f
r
ac
tio
n
o
f
s
u
ch
weig
h
ted
s
h
o
r
test
p
ath
s
th
at
p
ass
th
r
o
u
g
h
t
h
e
n
o
d
e
as in
(
3
)
.
B
e
tw
e
e
n
n
e
s
s
(
v
i
)
=
∑
σ
(
v
x
,
v
y
|
v
i
)
σ
(
v
x
,
v
y
)
v
x
,
v
y
∈
V
(
3
)
w
h
er
e
σ
(
v
x
,
v
y
)
d
en
o
tes th
e
weig
h
ted
s
h
o
r
test
p
ath
ex
is
tin
g
b
etwe
en
v
x
,
v
y
.
3
.
3
.
E
ig
env
ec
t
o
r
ce
ntr
a
lity
Fo
r
a
n
o
d
e
,
its
im
p
o
r
ta
n
ce
i
n
th
e
g
r
a
p
h
is
d
ep
e
n
d
en
t
u
p
o
n
th
e
im
p
o
r
tan
ce
o
f
th
e
n
eig
h
b
o
r
in
g
n
o
d
es.
T
h
u
s
,
in
eig
e
n
v
alu
e
ce
n
tr
ality
o
f
a
n
o
d
e
is
d
ir
ec
tly
p
r
o
p
o
r
tio
n
al
to
th
e
s
u
m
o
f
th
e
c
en
tr
ality
s
co
r
e
o
f
its
n
eig
h
b
o
r
in
g
n
o
d
es.
I
t
is
m
ea
s
u
r
ed
b
y
ca
lcu
latin
g
th
e
p
r
in
cip
al
eig
en
v
ec
t
o
r
o
f
th
e
a
d
ja
ce
n
cy
m
at
r
ix
.
T
h
e
p
r
o
ce
s
s
is
iter
ated
till
co
n
v
er
g
en
ce
u
n
til
th
e
eig
en
v
ec
t
o
r
ce
n
tr
ality
s
co
r
e
f
o
r
all
th
e
n
o
d
es
is
d
eter
m
in
ed
.
T
h
e
n
o
d
e
o
f
th
e
g
r
a
p
h
f
o
r
m
s
th
e
v
ec
to
r
.
Ma
th
em
atica
lly
,
eig
en
v
ec
to
r
ce
n
tr
ality
f
o
r
a
n
o
d
e
wh
ich
is
th
e
i
th
en
tity
o
f
th
e
v
ec
t
o
r
,
ca
n
b
e
ex
p
r
ess
ed
as in
(
4
)
.
(
)
:
(
)
=
(
4
)
w
h
er
e
(
)
is
th
e
ad
jace
n
cy
m
atr
ix
o
f
th
e
g
r
ap
h
(
,
)
,
an
d
is
th
e
eig
en
v
alu
e
co
m
p
u
ted
o
v
e
r
th
e
ad
jace
n
cy
m
atr
i
x
.
T
h
e
la
r
g
est v
alu
e
o
f
t
h
e
s
o
lu
tio
n
is
s
elec
ted
f
o
r
t
h
e
eig
en
v
alu
e.
3
.
4
.
P
a
g
eRa
n
k
Pag
eRan
k
is
u
s
ed
to
ass
ig
n
s
co
r
es
o
r
r
a
n
k
s
to
th
e
n
o
d
es
ac
c
o
r
d
in
g
to
th
eir
r
ele
v
an
ce
in
t
h
e
g
r
ap
h
.
I
t
tak
es
in
to
ac
co
u
n
t
th
e
lin
k
ed
s
tr
u
ctu
r
e
o
f
th
e
g
r
ap
h
.
I
n
th
e
Pag
eRan
k
alg
o
r
ith
m
,
ea
ch
n
o
d
e
lin
k
ed
to
a
g
iv
en
n
o
d
e
ca
s
ts
its
v
o
te
f
o
r
t
h
at
p
ar
ticu
lar
n
o
d
e.
I
n
itially
,
ea
ch
n
o
d
e
is
g
iv
en
an
eq
u
al
s
co
r
e
in
t
h
e
alg
o
r
ith
m
.
T
h
e
n
th
e
alg
o
r
ith
m
iter
ativ
ely
u
p
d
a
tes
th
e
s
co
r
e
o
f
th
e
n
o
d
es
u
n
ti
l
co
n
v
er
g
e
n
ce
is
ac
h
iev
ed
.
T
h
e
n
o
d
es
ar
e
r
an
k
e
d
ac
co
r
d
in
g
to
t
h
eir
s
co
r
e.
Giv
e
n
th
at
b
e
th
e
weig
h
t
ass
o
ciate
d
with
th
e
li
n
k
c
o
n
n
ec
tin
g
v
e
r
tices
,
,
b
e
th
e
weig
h
t f
o
r
th
e
lin
k
co
n
n
ec
tin
g
,
,
Pag
eRan
k
is
d
ef
in
ed
a
s
(
5
)
.
(
)
=
(
1
−
)
+
∗
∑
∑
(
,
)
∈
(
,
)
∈
(
)
(
5
)
4.
P
RO
P
O
SE
D
G
RAP
H
-
B
AS
E
D
M
E
T
H
O
D
F
O
R
H
I
NDI
WO
RD
SE
N
SE
D
I
SA
M
B
I
G
UATI
O
N
T
h
e
p
r
o
p
o
s
ed
alg
o
r
ith
m
wo
r
k
s
b
y
cr
ea
tin
g
a
weig
h
ted
g
r
a
p
h
u
s
in
g
th
e
s
en
s
es
o
f
tar
g
et
wo
r
d
s
an
d
co
n
tex
t
wo
r
d
s
as
v
er
tices.
T
h
e
e
d
g
es
i
n
th
e
g
r
a
p
h
a
r
e
cr
ea
t
ed
b
y
j
o
i
n
i
n
g
a
p
ai
r
o
f
v
er
tic
es
u
s
in
g
th
e
s
y
n
s
et
h
ie
r
ar
ch
y
o
f
Hi
n
d
i
W
o
r
d
N
et
.
T
h
e
wei
g
h
t
t
o
an
e
d
g
e
is
ass
i
g
n
e
d
b
y
c
o
m
p
u
ti
n
g
s
em
an
tic
s
im
ilar
ity
b
etwe
en
th
e
p
air
o
f
v
er
tices.
W
e
u
s
e
th
e
L
ea
co
ck
-
C
h
o
d
o
r
o
w
s
im
ilar
ity
m
ea
s
u
r
e
f
o
r
co
m
p
u
tin
g
s
em
an
tic
s
im
ilar
ity
b
etwe
en
th
e
two
co
n
ce
p
ts
.
T
h
e
alg
o
r
ith
m
ic
s
tep
s
ar
e
d
etaile
d
:
−
Pre
-
p
r
o
c
ess
i
n
g
:
T
h
e
d
atas
et
is
p
r
e
-
p
r
o
ce
s
s
e
d
t
o
r
e
m
o
v
e
s
to
p
w
o
r
d
s
,
t
o
r
ed
u
ce
m
o
r
p
h
o
l
o
g
i
ca
l
v
ar
ia
n
ts
t
o
th
e
ir
li
n
g
u
is
ti
c
r
o
o
ts
,
a
n
d
t
o
as
s
ig
n
p
a
r
t
-
of
-
s
p
e
ec
h
ta
g
s
t
o
ea
c
h
wo
r
d
.
−
E
x
tr
ac
t
io
n
o
f
co
n
t
e
x
t
wi
n
d
o
w
:
T
h
e
p
r
e
-
p
r
o
ce
s
s
ed
d
ata
is
u
s
ed
t
o
e
x
t
r
ac
t
a
c
o
n
te
x
t
w
in
d
o
w
o
f
s
i
ze
±
n
wo
r
d
s
k
ee
p
i
n
g
t
h
e
ta
r
g
e
t
w
o
r
d
i
n
th
e
m
i
d
d
le
.
I
n
t
h
is
w
o
r
k
,
a
c
o
n
t
ex
t
wi
n
d
o
w
co
m
p
r
is
i
n
g
o
f
±
2
n
o
u
n
s
wit
h
t
h
e
t
ar
g
et
wo
r
d
in
t
h
e
m
i
d
d
le
is
u
s
e
d
.
CW
=
{
w
−
n
,
w
−
n
−
1
,
…
,
w
−
1
,
t
w
,
w
1
…
,
w
n
−
1
,
w
n
}
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
Un
s
u
p
ervis
ed
h
in
d
i wo
r
d
s
en
s
e
d
is
a
mb
ig
u
a
tio
n
u
s
in
g
g
r
a
p
h
-
b
a
s
ed
ce
n
tr
a
lity m
ea
s
u
r
es
(
P
r
a
jn
a
Jh
a
)
4961
−
Gr
a
p
h
c
r
ea
ti
o
n
:
E
x
t
r
a
ct
a
s
et
o
f
v
e
r
t
ices
,
V,
b
y
e
x
t
r
ac
ti
n
g
a
ll
th
e
s
e
n
s
es
o
f
t
h
e
t
ar
g
et
w
o
r
d
a
n
d
all
o
t
h
e
r
wo
r
d
s
ap
p
e
a
r
i
n
g
i
n
t
h
e
c
o
n
te
x
t
wi
n
d
o
w
f
r
o
m
Hi
n
d
i
W
o
r
d
Net
.
C
r
e
ate
a
n
u
n
d
i
r
e
ct
ed
w
e
ig
h
te
d
g
r
ap
h
,
G
=
(
V
,
E
)
.
T
h
e
w
ei
g
h
t
to
a
n
e
d
g
e,
e
=(
v
i
,
v
j
)
is
ass
ig
n
ed
b
y
c
o
m
p
u
t
in
g
s
em
an
tic
s
im
ilar
ity
b
etw
ee
n
v
er
tex
v
i
a
n
d
v
j
u
s
in
g
th
e
L
ea
c
o
ck
-
C
h
o
d
o
r
o
w
s
im
ilar
ity
m
ea
s
u
r
e.
−
C
o
m
p
u
tatio
n
o
f
v
er
tex
s
co
r
e
:
T
h
e
g
r
ap
h
is
tr
av
er
s
ed
s
tar
tin
g
f
r
o
m
t
h
e
s
en
s
es
o
f
th
e
f
ir
s
t
wo
r
d
a
n
d
ea
ch
v
er
tex
is
ass
ig
n
ed
a
s
co
r
e
u
s
in
g
a
g
r
a
p
h
-
ce
n
t
r
ality
m
ea
s
u
r
e
as
d
is
cu
s
s
ed
in
s
ec
t
io
n
3
.
W
e
ex
p
er
im
en
t
with
f
o
u
r
d
if
f
er
e
n
t m
ea
s
u
r
es
–
i
)
clo
s
en
ess
,
ii
)
b
etwe
en
n
ess
,
iii
)
eig
en
v
ec
to
r
ce
n
tr
ality
,
a
n
d
iv
)
Pag
eRan
k
.
−
Sen
s
e
id
en
tific
atio
n
:
T
h
e
s
co
r
e
o
f
n
o
d
es
r
ep
r
esen
tin
g
th
e
s
en
s
es
o
f
th
e
tar
g
et
wo
r
d
is
ex
tr
ac
ted
.
T
h
e
win
n
er
s
en
s
e
co
r
r
esp
o
n
d
s
to
t
h
e
n
o
d
e
with
th
e
h
i
g
h
est s
co
r
e
An
illu
s
tr
ativ
e
ex
am
p
le
o
f
g
r
ap
h
cr
ea
tio
n
f
o
r
th
e
wo
r
d
‘
उ
र
’
{
u
tta
r
}
is
s
h
o
wn
in
Fig
u
r
e
1
.
I
n
th
e
d
iag
r
am
,
th
e
v
er
tices
in
th
e
g
r
ap
h
c
o
m
p
r
is
e
o
f
s
y
n
s
ets
o
f
th
e
tar
g
et
wo
r
d
an
d
wo
r
d
s
ap
p
e
ar
in
g
i
n
±
2
c
o
n
te
x
t
ex
cl
u
d
in
g
s
t
o
p
w
o
r
d
s
.
T
h
es
e
s
y
n
s
ets
ar
e
co
n
n
ec
ted
u
s
in
g
W
o
r
d
Net
-
s
y
n
s
et
h
ier
a
r
ch
y
.
T
h
e
weig
h
t
o
f
an
ed
g
e
is
eq
u
al
to
th
e
s
im
ilar
ity
s
co
r
e
b
etwe
en
its
v
er
tices
o
b
tain
e
d
u
s
in
g
th
e
L
ea
c
o
ck
-
C
h
o
d
o
r
o
w
s
em
an
tic
s
im
ilar
ity
m
ea
s
u
r
e.
T
h
e
g
r
ap
h
ca
p
tu
r
es
th
e
s
y
n
tactic
-
s
em
an
tic
r
elatio
n
s
h
ip
b
etwe
en
th
e
n
o
d
es,
a
n
d
th
u
s
,
p
r
o
v
id
es
a
p
o
wer
f
u
l to
o
l to
p
er
f
o
r
m
W
SD.
Fig
u
r
e
1
.
W
eig
h
ted
g
r
ap
h
f
o
r
t
h
e
tar
g
et
wo
r
d
‘
उ
र
’
an
d
c
o
n
t
ex
t w
o
r
d
s
5.
E
XP
E
R
I
M
E
N
T
AND
R
E
SU
L
T
W
e
h
av
e
p
er
f
o
r
m
e
d
o
u
r
ex
p
e
r
im
en
t
o
n
2
0
am
b
ig
u
o
u
s
Hin
d
i
wo
r
d
s
tak
en
f
r
o
m
th
e
s
en
s
e
-
an
n
o
tated
Hin
d
i
d
ataset
[
1
2
]
.
All
th
ese
2
0
am
b
ig
u
o
u
s
wo
r
d
s
ar
e
n
o
u
n
s
.
T
h
e
lis
t
o
f
ta
r
g
et
wo
r
d
s
u
s
ed
f
o
r
th
e
ex
p
e
r
im
en
t
an
d
th
eir
co
r
r
esp
o
n
d
in
g
s
en
s
e
co
u
n
ts
ar
e
s
h
o
wn
in
T
ab
le
1
.
T
h
e
d
ataset
co
n
s
is
ts
o
f
s
am
p
le
in
s
tan
ce
s
f
o
r
ea
ch
s
en
s
e
o
f
a
p
o
ly
s
em
o
u
s
wo
r
d
.
T
h
e
n
u
m
b
er
o
f
in
s
tan
ce
s
in
th
e
d
ataset
is
9
6
5
.
T
ab
le
1
.
Data
s
et
d
escr
ip
tio
n
#
S
e
n
ses
Ta
r
g
e
t
w
o
r
d
s
(
N
o
u
n
s)
2
को
ट
ा
(
Q
u
o
t
a
/
K
o
t
a
)
,
ह
ा
र
(
H
a
a
r
)
,
हल
(
H
a
l
)
,
स
ो
न
ा
(
G
o
l
d
)
,
विवि
(
Vi
d
h
i
)
,
मा
ग
(
Ma
a
n
g
)
,
द
ा
म
(
D
a
a
m
)
,
ती
र
(
T
e
e
r
)
,
ता
न
(
T
a
a
n
)
,
डा
क
(
D
a
a
k
)
,
ज
े
ठ
(
J
e
t
h
)
,
च
ं
द
ा
(
C
h
a
n
d
a
)
,
ग
ु
(
G
u
r
u
)
3
उर
(
U
t
t
a
r
)
,
क
ुं
भ
(
k
u
m
b
h
)
,
स
ं
ब
ं
ि
(
sa
m
b
a
n
d
h
)
,
फल
(
f
a
l
)
,
स
ं
म
ण
(
sa
n
k
r
a
m
a
n
)
,
ि
च
न
(
v
a
c
h
a
n
)
4
म
ू
ल
(
M
o
o
l
)
F
o
r
d
i
s
a
m
b
i
g
u
a
t
i
o
n
,
a
w
e
i
g
h
t
e
d
-
g
r
a
p
h
g
r
a
p
h
i
s
c
r
e
a
t
e
d
f
o
r
e
a
c
h
i
n
s
t
a
n
c
e
o
f
t
h
e
t
a
r
g
e
t
w
o
r
d
.
E
a
c
h
n
o
d
e
i
n
t
h
e
g
r
a
p
h
i
s
t
h
e
n
a
s
s
i
g
n
e
d
a
s
c
o
r
e
u
s
i
n
g
c
l
o
s
e
n
e
s
s
,
b
e
t
w
e
e
n
n
e
s
s
,
e
i
g
e
n
v
e
c
t
o
r
c
e
n
t
r
a
l
i
t
y
a
l
g
o
r
i
t
h
m
s
,
a
n
d
P
a
g
e
R
a
n
k
.
T
h
e
p
r
o
c
e
s
s
i
s
r
e
p
e
a
t
e
d
f
o
r
e
a
c
h
i
n
s
t
a
n
c
e
o
f
a
l
l
t
h
e
2
0
w
o
r
d
s
.
T
h
e
a
c
c
u
r
a
c
y
o
f
p
r
e
d
i
c
t
i
o
n
f
o
r
a
p
a
r
t
i
c
u
l
a
r
w
o
r
d
i
s
o
b
t
a
i
n
e
d
b
y
a
v
e
r
a
g
i
n
g
t
h
e
a
c
c
u
r
a
c
y
o
f
a
l
l
t
h
e
s
e
n
s
e
s
.
T
h
e
p
r
e
d
i
c
t
i
o
n
a
c
c
u
r
a
c
y
o
f
e
a
c
h
o
f
t
h
e
t
a
r
g
e
t
w
o
r
d
s
i
n
t
h
e
d
a
t
a
s
e
t
u
s
i
n
g
c
l
o
s
e
n
e
s
s
,
b
e
t
w
e
e
n
n
e
s
s
,
e
i
g
e
n
v
e
c
t
o
r
,
a
n
d
P
a
g
e
R
a
n
k
m
e
a
s
u
r
e
i
s
l
i
s
t
e
d
i
n
T
a
b
l
e
2
.
Fro
m
T
ab
le
2
,
it
ca
n
b
e
cle
ar
ly
o
b
s
er
v
ed
t
h
at
th
e
Pag
e
R
an
k
an
d
clo
s
en
ess
m
ea
s
u
r
es
p
er
f
o
r
m
s
ig
n
if
ican
tly
b
etter
th
an
b
etw
ee
n
n
ess
.
T
h
e
m
ax
im
u
m
ac
cu
r
ac
y
o
f
0
.
6
6
9
2
(
a
v
er
ag
e
d
o
v
er
all
th
e
in
s
tan
ce
s
)
is
o
b
tain
ed
u
s
in
g
Pag
eRan
k
,
w
h
ich
is
clo
s
ely
f
o
llo
wed
b
y
clo
s
en
ess
ce
n
tr
ality
(
0
.
6
6
4
9
)
.
T
h
e
eig
en
v
ec
to
r
ce
n
tr
ality
m
ea
s
u
r
e
r
esu
lts
in
an
o
v
e
r
all
ac
cu
r
ac
y
o
f
0
.
6
2
3
8
.
T
h
e
wo
r
s
t
p
er
f
o
r
m
i
n
g
ca
s
e
co
r
r
esp
o
n
d
s
to
th
e
b
etwe
en
n
ess
m
ea
s
u
r
e.
T
h
e
clo
s
en
ess
ce
n
tr
ality
f
o
r
th
e
weig
h
ted
g
r
ap
h
co
n
s
id
er
s
th
e
weig
h
t
o
f
lin
k
s
ass
o
ciate
d
with
th
e
n
o
d
es
to
ca
lcu
late
th
e
s
h
o
r
test
p
ath
f
o
r
ea
ch
n
o
d
e
p
air
.
I
n
ce
r
tain
ca
s
es,
lik
e
s
en
s
e
-
2
o
f
‘
क
ुं
भ
’
(
‘
ku
mb
h
’
)
,
o
u
t
o
f
2
2
in
s
tan
ce
s
,
clo
s
en
ess
ce
n
tr
ality
a
cc
u
r
ately
p
r
ed
icted
th
e
ap
p
r
o
p
r
iate
s
en
s
e
f
o
r
2
1
in
s
tan
ce
s
,
f
o
llo
wed
b
y
Pag
eRan
k
wh
ich
p
r
ed
icted
co
r
r
ec
tly
2
0
tim
es.
T
h
e
r
ea
s
o
n
f
o
r
th
e
p
o
o
r
p
er
f
o
r
m
a
n
ce
o
f
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
13
,
No
.
4
,
Dec
em
b
er
2
0
2
4
:
4
9
5
7
-
4
9
6
4
4962
b
etwe
en
n
ess
is
th
at
i
t
as
s
ig
n
s
a
s
co
r
e
to
ea
ch
n
o
d
e
b
y
c
o
m
p
u
tin
g
th
e
m
ax
im
u
m
o
f
th
e
f
r
a
ctio
n
o
f
th
e
s
h
o
r
test
p
ath
s
th
at
p
ass
es
th
r
o
u
g
h
it.
F
o
r
d
is
am
b
ig
u
atio
n
,
we
u
s
e
th
e
m
ax
im
u
m
s
co
r
in
g
n
o
d
e
am
o
n
g
th
e
s
en
s
es
o
f
th
e
tar
g
et
wo
r
d
.
Du
e
t
o
th
e
lim
i
ted
co
n
tex
t
two
o
r
m
o
r
e
s
en
s
es
ar
e
ass
ig
n
ed
s
am
e
s
co
r
e
in
wh
ich
ca
s
e
th
e
alg
o
r
ith
m
s
im
p
ly
r
etu
r
n
s
th
e
s
en
s
e
lis
ted
f
ir
s
t in
th
e
in
v
en
to
r
y
.
T
ab
le
2
.
Pre
d
ictio
n
ac
cu
r
ac
y
o
b
tain
ed
u
s
in
g
g
r
ap
h
-
b
ased
ce
n
tr
ality
m
ea
s
u
r
es
Ta
r
g
e
t
w
o
r
d
(
n
o
u
n
s
)
C
l
o
se
n
e
ss
B
e
t
w
e
e
n
n
e
ss
Ei
g
e
n
v
e
c
t
o
r
P
a
g
e
R
a
n
k
को
ट
ा
(
Q
u
o
t
a
/
K
o
t
a
)
0
.
7
1
8
1
0
.
0
6
5
4
0
.
6
2
7
8
0
.
6
9
8
1
ह
ा
र
(
H
a
a
r
)
0
.
7
9
4
4
0
.
5
5
5
6
0
.
5
8
3
3
0
.
7
4
1
7
हल
(
H
a
l
)
0
.
5
9
5
2
0
.
4
5
3
6
0
.
5
5
9
5
0
.
5
9
5
2
स
ो
न
ा
(
G
o
l
d
)
0
.
6
4
4
4
0
.
5
9
8
9
0
.
5
4
8
9
0
.
6
7
2
2
विवि
(
Vi
d
h
i
)
0
.
6
5
2
8
0
.
5
2
9
8
0
.
5
6
5
1
0
.
6
3
1
7
मा
ग
(
Ma
a
n
g
)
0
.
6
4
0
1
0
.
5
7
9
5
0
.
6
4
3
9
0
.
6
4
2
0
द
ा
म
(
D
a
a
m
)
0
.
7
9
5
8
0
.
2
0
4
1
0
.
7
3
3
4
0
.
7
8
7
5
ती
र
(
T
e
e
r
)
0
.
6
8
9
1
0
.
3
3
0
9
0
.
6
0
3
6
0
.
6
9
4
5
ता
न
(
T
a
a
n
)
0
.
7
9
8
0
0
.
3
1
0
1
0
.
6
2
0
1
0
.
7
9
8
0
डा
क
(
D
a
a
k
)
0
.
6
7
8
5
0
.
4
9
6
7
0
.
5
5
1
9
0
.
6
3
3
1
ज
े
ठ
(
J
e
t
h
)
0
.
5
5
0
.
6
0
.
4
5
0
.
6
5
च
ं
द
ा
(
C
h
a
n
d
a
)
0
.
8
1
3
2
0
.
3
2
6
4
0
.
6
5
4
4
0
.
7
2
3
5
ग
ु
(
G
u
r
u
)
0
.
6
6
4
5
0
.
4
1
0
2
0
.
6
5
3
8
0
.
6
7
3
0
उर
(
U
t
t
a
r
)
0
.
6
3
5
4
0
.
5
1
1
5
0
.
5
9
2
6
0
.
6
2
9
7
क
ुं
भ
(
k
u
m
b
h
)
0
.
7
1
7
4
0
.
4
8
7
5
0
.
6
0
0
8
0
.
7
5
8
7
स
ं
ब
ं
ि
(
sa
m
b
a
n
d
h
)
0
.
7
2
3
9
0
.
4
2
5
7
0
.
6
2
3
6
0
.
7
फल
(
f
a
l
)
0
.
6
1
0
2
0
.
4
0
3
1
0
.
6
0
1
7
0
.
6
9
7
3
स
ं
मण
(
s
a
n
k
r
a
m
a
n
)
0
.
6
9
9
1
0
.
4
3
2
9
0
.
5
2
5
3
0
.
5
6
3
6
ि
च
न
(
v
a
c
h
a
n
)
0
.
7
8
7
8
0
.
4
8
7
3
0
.
6
2
3
7
0
.
6
7
2
1
म
ू
ल
(
M
o
o
l
)
0
.
5
7
2
5
0
.
4
7
4
2
0
.
5
5
7
0
0
.
6
0
6
7
A
v
e
r
a
g
e
a
c
c
u
r
a
c
y
0
.
6
6
4
9
0
.
4
8
5
1
0
.
6
2
3
8
0
.
6
6
9
2
T
ab
le
3
co
m
p
ar
es
th
e
p
er
f
o
r
m
an
ce
o
f
th
e
p
r
o
p
o
s
ed
m
eth
o
d
with
th
e
b
aselin
e
w
o
r
k
r
ep
o
r
ted
in
[
1
1
]
wh
ich
u
s
es
L
ea
co
k
-
C
h
o
d
o
r
o
w
s
em
an
tic
s
im
ilar
ity
-
b
ased
s
co
r
e
in
d
is
am
b
ig
u
atio
n
a
n
d
a
n
o
th
er
m
o
r
e
r
ec
e
n
t
g
r
ap
h
-
b
ased
m
eth
o
d
r
ep
o
r
ted
in
[
1
0
]
t
h
at
u
s
es
th
e
s
am
e
d
ataset.
J
h
a
et
a
l.
[
1
0
]
u
s
es
s
em
an
tic
s
im
ilar
ity
to
ass
ig
n
weig
h
ts
to
ed
g
es
a
n
d
p
er
f
o
r
m
s
a
r
an
d
o
m
walk
to
ac
h
iev
e
d
is
am
b
ig
u
atio
n
.
As
ev
id
en
t
f
r
o
m
th
e
tab
le,
all
ex
ce
p
t
th
e
b
etwe
en
n
ess
ce
n
tr
ality
m
ea
s
u
r
e
p
e
r
f
o
r
m
ed
b
etter
th
an
th
e
b
aselin
e
[
1
1
]
.
B
o
th
Pag
eRan
k
a
n
d
clo
s
en
ess
m
ea
s
u
r
es
p
er
f
o
r
m
ed
b
etter
th
an
t
h
e
g
r
ap
h
-
b
a
s
ed
W
SD
m
eth
o
d
r
e
p
o
r
ted
in
[
1
0
]
wh
ile
t
h
e
p
er
f
o
r
m
an
ce
o
f
E
ig
en
v
ec
to
r
c
en
tr
ality
m
ea
s
u
r
e
is
co
m
p
ar
ab
le
to
it.
W
e
ac
h
iev
ed
a
s
ig
n
if
i
ca
n
t
im
p
r
o
v
em
e
n
t
o
f
1
0
.
3
3
%
o
v
er
[
1
1
]
an
d
5
.
5
7
%
o
v
er
[
1
0
]
u
s
in
g
th
e
Pag
e
R
an
k
m
ea
s
u
r
e.
I
t
s
h
o
u
ld
b
e
n
o
ted
th
at
in
[
1
1
]
p
r
ec
is
io
n
an
d
r
ec
all
m
ea
s
u
r
e
s
ar
e
u
s
ed
f
o
r
p
er
f
o
r
m
an
ce
ev
alu
atio
n
.
T
h
e
p
r
o
p
o
s
ed
alg
o
r
ith
m
p
r
o
v
i
d
es
an
an
s
wer
f
o
r
ea
ch
in
s
tan
ce
h
en
c
e
p
r
ec
is
io
n
an
d
r
ec
all
ar
e
s
am
e
as a
cc
u
r
ac
y
.
T
ab
le
3
.
C
o
m
p
a
r
ativ
e
an
aly
s
is
o
f
p
r
o
p
o
s
ed
m
eth
o
d
o
v
e
r
b
as
elin
e
M
e
t
h
o
d
A
c
c
u
r
a
c
y
P
r
o
p
o
se
d
m
e
t
h
o
d
C
l
o
se
n
e
ss
B
e
t
w
e
e
n
n
e
ss
Ei
g
e
n
V
e
c
t
o
r
P
a
g
e
R
a
n
k
0
.
6
6
4
9
0
.
4
8
5
1
0
.
6
2
3
8
0
.
6
6
9
2
S
i
n
g
h
e
t
a
l
.
[
1
1
]
0
.
6
0
6
5
Jh
a
e
t
a
l
.
[
1
0
]
0
.
6
3
3
9
6.
CO
NCLU
SI
O
N
AND
F
U
T
U
RE
WO
RK
I
n
t
h
i
s
p
a
p
e
r
,
w
e
p
r
o
p
o
s
e
a
n
d
e
v
a
l
u
a
t
e
a
n
u
n
s
u
p
e
r
v
i
s
e
d
g
r
ap
h
-
b
a
s
e
d
a
l
g
o
r
i
t
h
m
f
o
r
t
h
e
H
in
d
i
W
SD
t
a
s
k
.
W
e
u
s
e
t
h
e
W
o
r
d
N
e
t
-
b
ase
d
s
e
m
a
n
t
i
c
s
i
m
il
a
r
i
t
y
m
e
t
h
o
d
t
o
a
s
s
i
g
n
w
ei
g
h
t
t
o
e
d
g
e
s
.
T
h
e
d
i
s
a
m
b
i
g
u
a
t
i
o
n
is
d
o
n
e
u
s
i
n
g
s
c
o
r
e
s
a
s
s
i
g
n
e
d
t
o
t
h
e
s
e
n
s
e
n
o
d
e
.
W
e
e
x
p
e
r
i
m
e
n
t
w
it
h
f
o
u
r
d
i
f
f
e
r
e
n
t
c
e
n
t
r
al
i
t
y
m
e
a
s
u
r
e
s
f
o
r
n
o
d
e
s
c
o
r
i
n
g
.
T
h
e
P
a
g
eR
a
n
k
m
e
as
u
r
e
w
i
t
h
a
n
o
v
e
r
a
ll
a
c
c
u
r
a
c
y
o
f
6
6
.
9
2
%
p
e
r
f
o
r
m
s
b
et
t
e
r
t
h
a
n
a
l
l
o
t
h
e
r
m
e
as
u
r
e
s
.
T
h
e
c
l
o
s
e
n
es
s
c
e
n
t
r
a
li
t
y
m
e
as
u
r
e
p
e
r
f
o
r
m
e
d
q
u
i
t
e
c
l
o
s
e
t
o
P
a
g
e
R
a
n
k
w
it
h
a
n
o
b
s
e
r
v
e
d
a
cc
u
r
a
c
y
o
f
6
6
.
4
9
%
o
v
e
r
t
h
e
e
n
t
i
r
e
d
a
t
as
et
.
T
h
e
t
w
o
b
e
s
t
-
p
e
r
f
o
r
m
i
n
g
c
as
es
o
f
t
h
e
p
r
o
p
o
s
e
d
a
l
g
o
r
i
t
h
m
p
e
r
f
o
r
m
e
d
b
e
t
t
e
r
t
h
a
n
e
x
is
t
i
n
g
w
o
r
k
s
o
n
t
h
e
s
a
m
e
d
a
ta
s
et
.
T
h
e
i
m
p
r
o
v
e
m
e
n
t
i
s
q
u
i
t
e
s
ig
n
i
f
i
c
a
n
t
.
T
h
e
p
r
o
p
o
s
e
d
m
et
h
o
d
u
s
i
n
g
P
a
g
eR
a
n
k
o
u
t
p
e
r
f
o
r
m
e
d
t
w
o
o
f
t
h
e
ea
r
l
i
er
m
e
t
h
o
d
s
e
v
al
u
a
t
e
d
o
n
t
h
e
s
am
e
d
a
t
as
e
t
b
y
a
s
i
g
n
i
f
i
c
a
n
t
m
ar
g
i
n
o
f
1
0
.
3
3
%
a
n
d
5
.
5
7
%
.
T
h
e
p
r
o
m
i
s
i
n
g
r
e
s
u
l
ts
o
b
t
a
i
n
e
d
i
n
t
h
i
s
s
t
u
d
y
d
e
m
o
n
s
t
r
a
t
e
t
h
a
t
u
n
s
u
p
e
r
v
is
e
d
a
p
p
r
o
a
c
h
e
s
c
a
n
b
e
e
f
f
e
c
t
i
v
e
l
y
u
s
e
d
f
o
r
W
S
D
ta
s
k
s
i
n
t
h
e
a
b
s
e
n
c
e
o
f
t
a
g
g
e
d
co
r
p
u
s
a
n
d
t
h
e
i
r
p
e
r
f
o
r
m
a
n
c
e
c
a
n
b
e
s
i
g
n
i
f
ic
a
n
t
l
y
i
m
p
r
o
v
e
d
b
y
e
n
r
i
c
h
i
n
g
t
h
e
s
e
a
p
p
r
o
a
c
h
e
s
u
s
i
n
g
k
n
o
w
l
e
d
g
e
f
r
o
m
t
h
e
e
x
i
s
t
i
n
g
l
e
x
i
c
a
l
r
e
s
o
u
r
c
e
s
.
F
u
r
t
h
er
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
Un
s
u
p
ervis
ed
h
in
d
i wo
r
d
s
en
s
e
d
is
a
mb
ig
u
a
tio
n
u
s
in
g
g
r
a
p
h
-
b
a
s
ed
ce
n
tr
a
lity m
ea
s
u
r
es
(
P
r
a
jn
a
Jh
a
)
4963
i
n
v
e
s
t
i
g
at
i
o
n
s
o
n
la
r
g
e
r
d
a
t
as
et
s
a
n
d
i
n
v
o
l
v
i
n
g
o
t
h
e
r
l
a
n
g
u
a
g
e
s
m
a
y
b
e
n
e
e
d
e
d
t
o
c
o
n
f
i
r
m
th
e
s
e
f
i
n
d
i
n
g
s
.
T
h
i
s
w
o
r
k
f
o
c
u
s
e
s
o
n
t
a
r
g
e
t
e
d
W
S
D
;
h
o
w
e
v
e
r
,
i
t
c
a
n
b
e
ea
s
il
y
e
x
t
en
d
e
d
f
o
r
a
l
l
W
S
D
.
F
u
t
u
r
e
s
t
u
d
ie
s
m
a
y
e
x
p
l
o
r
e
t
h
is
a
p
p
r
o
a
c
h
f
o
r
o
t
h
e
r
p
a
r
t
o
f
s
p
e
e
c
h
c
a
t
e
g
o
r
i
e
s
a
n
d
f
o
r
a
l
l
W
S
D
t
a
s
k
s
i
n
v
o
l
v
i
n
g
H
i
n
d
i
,
a
n
d
o
t
h
er
I
n
d
i
a
n
l
a
n
g
u
a
g
e
s
.
ACK
NO
WL
E
DG
E
M
E
NT
W
e
ex
p
r
ess
o
u
r
g
r
atitu
d
e
to
C
FIL
T
,
I
I
T
-
B
o
m
b
ay
f
o
r
p
r
o
v
id
i
n
g
Hin
d
i
W
o
r
d
Net
API
as
o
p
en
s
o
u
r
ce
.
W
e
u
s
ed
th
is
API
f
o
r
im
p
lem
e
n
tin
g
p
ar
ts
o
f
th
e
p
r
o
p
o
s
ed
alg
o
r
ith
m
.
RE
F
E
R
E
NC
E
S
[
1
]
R
.
N
a
v
i
g
l
i
,
“
W
o
r
d
se
n
se
d
i
s
a
m
b
i
g
u
a
t
i
o
n
:
A
su
r
v
e
y
,
”
AC
M
C
o
m
p
u
t
i
n
g
S
u
rv
e
y
s
,
v
o
l
.
4
1
,
n
o
.
2
,
2
0
0
9
,
d
o
i
:
1
0
.
1
1
4
5
/
1
4
5
9
3
5
2
.
1
4
5
9
3
5
5
.
[
2
]
S
.
B
a
n
e
r
j
e
e
a
n
d
T.
P
e
d
e
r
se
n
,
“
A
n
a
d
a
p
t
e
d
l
e
s
k
a
l
g
o
r
i
t
h
m
f
o
r
w
o
r
d
se
n
se
d
i
sam
b
i
g
u
a
t
i
o
n
u
si
n
g
w
o
r
d
n
e
t
,
”
C
o
m
p
u
t
a
t
i
o
n
a
l
L
i
n
g
u
i
st
i
c
s
a
n
d
I
n
t
e
l
l
i
g
e
n
t
T
e
x
t
Pr
o
c
e
ssi
n
g
,
v
o
l
.
2
2
7
6
,
p
p
.
1
3
6
–
1
4
5
,
2
0
0
2
,
d
o
i
:
1
0
.
1
0
0
7
/
3
-
5
4
0
-
4
5
7
1
5
-
1
_
1
1
.
[
3
]
S
.
P
a
t
w
a
r
d
h
a
n
,
S
.
B
a
n
e
r
j
e
e
,
a
n
d
T
.
P
e
d
e
r
se
n
,
“
U
si
n
g
m
e
a
s
u
r
e
s
o
f
se
man
t
i
c
r
e
l
a
t
e
d
n
e
ss
f
o
r
w
o
r
d
se
n
s
e
d
i
s
a
mb
i
g
u
a
t
i
o
n
,
”
C
o
m
p
u
t
a
t
i
o
n
a
l
L
i
n
g
u
i
s
t
i
c
s
a
n
d
I
n
t
e
l
l
i
g
e
n
t
T
e
x
t
Pr
o
c
e
ssi
n
g
,
v
o
l
.
2
5
8
8
,
p
p
.
2
4
1
–
2
5
7
,
2
0
0
3
,
d
o
i
:
1
0
.
1
0
0
7
/
3
-
5
4
0
-
3
6
4
5
6
-
0
_
2
4
.
[
4
]
D
.
Y
a
r
o
w
s
k
y
,
“
O
n
e
s
e
n
se
p
e
r
c
o
l
l
o
c
a
t
i
o
n
,
”
H
u
m
a
n
L
a
n
g
u
a
g
e
T
e
c
h
n
o
l
o
g
y
:
Pro
c
e
e
d
i
n
g
s
o
f
a
W
o
rks
h
o
p
H
e
l
d
,
P
l
a
i
n
s
b
o
r
o
,
N
e
w
Jersey
,
p
p
.
2
6
6
-
271
,
1
9
9
3
,
d
o
i
:
1
0
.
3
1
1
5
/
1
0
7
5
6
7
1
.
1
0
7
5
7
3
1
.
[
5
]
D
.
Y
a
r
o
w
s
k
y
,
“
U
n
s
u
p
e
r
v
i
se
d
w
o
r
d
se
n
se
d
i
sam
b
i
g
u
a
t
i
o
n
r
i
v
a
l
i
n
g
su
p
e
r
v
i
se
d
m
e
t
h
o
d
s,
”
P
ro
c
e
e
d
i
n
g
s o
f
t
h
e
A
n
n
u
a
l
Me
e
t
i
n
g
o
f
t
h
e
Asso
c
i
a
t
i
o
n
f
o
r
C
o
m
p
u
t
a
t
i
o
n
a
l
L
i
n
g
u
i
st
i
c
s
,
v
o
l
.
1
9
9
5
,
p
p
.
1
8
9
–
1
9
6
,
1
9
9
5
,
d
o
i
:
1
0
.
3
1
1
5
/
9
8
1
6
5
8
.
9
8
1
6
8
4
.
[
6
]
N
.
K
h
a
n
,
Z.
M
a
,
A
.
U
l
l
a
h
,
a
n
d
K
.
P
o
l
a
t
,
“
C
a
t
e
g
o
r
i
z
a
t
i
o
n
o
f
k
n
o
w
l
e
d
g
e
g
r
a
p
h
b
a
s
e
d
r
e
c
o
mm
e
n
d
a
t
i
o
n
m
e
t
h
o
d
s
a
n
d
b
e
n
c
h
m
a
r
k
d
a
t
a
se
t
s
f
r
o
m
t
h
e
p
e
r
s
p
e
c
t
i
v
e
s
o
f
a
p
p
l
i
c
a
t
i
o
n
sce
n
a
r
i
o
s
:
A
c
o
mp
r
e
h
e
n
s
i
v
e
s
u
r
v
e
y
,
”
E
x
p
e
rt
S
y
s
t
e
m
s
w
i
t
h
A
p
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
2
0
6
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
sw
a
.
2
0
2
2
.
1
1
7
7
3
7
.
[
7
]
R
.
M
i
h
a
l
c
e
a
,
“
U
n
s
u
p
e
r
v
i
se
d
l
a
r
g
e
-
v
o
c
a
b
u
l
a
r
y
w
o
r
d
s
e
n
se
d
i
sam
b
i
g
u
a
t
i
o
n
w
i
t
h
g
r
a
p
h
-
b
a
se
d
a
l
g
o
r
i
t
h
ms
f
o
r
se
q
u
e
n
c
e
d
a
t
a
l
a
b
e
l
i
n
g
,
”
H
L
T
/
EM
N
L
P
2
0
0
5
-
H
u
m
a
n
L
a
n
g
u
a
g
e
T
e
c
h
n
o
l
o
g
y
C
o
n
f
e
r
e
n
c
e
a
n
d
C
o
n
f
e
r
e
n
c
e
o
n
Em
p
i
r
i
c
a
l
M
e
t
h
o
d
s
i
n
N
a
t
u
ra
l
L
a
n
g
u
a
g
e
Pr
o
c
e
ssi
n
g
,
Pr
o
c
e
e
d
i
n
g
s
o
f
t
h
e
C
o
n
f
e
re
n
c
e
,
p
p
.
4
1
1
–
4
1
8
,
2
0
0
5
,
d
o
i
:
1
0
.
3
1
1
5
/
1
2
2
0
5
7
5
.
1
2
2
0
6
2
7
.
[
8
]
S
.
B
h
i
n
g
a
r
d
i
v
e
,
H
.
R
e
d
k
a
r
,
P
.
S
a
p
p
a
d
l
a
,
D
.
S
i
n
g
h
,
a
n
d
P
.
B
h
a
t
t
a
c
h
a
r
y
y
a
,
“
I
n
d
o
W
o
r
d
N
e
t
:
S
i
m
i
l
a
r
i
t
y
c
o
m
p
u
t
i
n
g
s
e
ma
n
t
i
c
s
i
m
i
l
a
r
i
t
y
a
n
d
r
e
l
a
t
e
d
n
e
ss
u
s
i
n
g
I
n
d
o
W
o
r
d
N
e
t
,
”
Pr
o
c
e
e
d
i
n
g
s
o
f
t
h
e
8
t
h
G
l
o
b
a
l
W
o
r
d
N
e
t
C
o
n
f
e
r
e
n
c
e
,
G
W
C
2
0
1
6
,
p
p
.
3
9
–
4
3
,
2
0
1
6
.
[
9
]
A
.
J
a
i
n
a
n
d
D
.
K
.
L
o
b
i
y
a
l
,
“
A
n
e
w
a
p
p
r
o
a
c
h
f
o
r
u
n
s
u
p
e
r
v
i
s
e
d
w
o
r
d
s
e
n
s
e
d
i
s
a
m
b
i
g
u
a
t
i
o
n
i
n
H
i
n
d
i
l
a
n
g
u
a
g
e
u
s
i
n
g
g
r
a
p
h
c
o
n
n
e
c
t
i
v
i
t
y
m
e
a
s
u
r
e
s
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
A
r
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
a
n
d
S
o
f
t
C
o
m
p
u
t
i
n
g
,
v
o
l
.
4
,
n
o
.
4
,
2
0
1
4
,
d
o
i
:
1
0
.
1
5
0
4
/
i
j
a
i
s
c
.
2
0
1
4
.
0
6
5
8
0
0
.
[
1
0
]
P
.
Jh
a
,
S
.
A
g
a
r
w
a
l
,
A
.
A
b
b
a
s,
a
n
d
T
.
J.
S
i
d
d
i
q
u
i
,
“
A
n
o
v
e
l
u
n
s
u
p
e
r
v
ı
se
d
g
r
a
p
h
-
b
a
s
e
d
a
l
g
o
r
ı
t
h
m
f
o
r
H
i
n
d
i
w
o
r
d
se
n
se
d
i
s
a
mb
i
g
u
a
t
i
o
n
,
”
S
N
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
v
o
l
.
4
,
n
o
.
5
,
2
0
2
3
,
d
o
i
:
1
0
.
1
0
0
7
/
s
4
2
9
7
9
-
0
2
3
-
0
2
1
1
6
-
1.
[
1
1
]
S
.
S
i
n
g
h
,
V
.
K
.
S
i
n
g
h
,
a
n
d
T.
J.
S
i
d
d
i
q
u
i
,
“
H
i
n
d
i
w
o
r
d
s
e
n
s
e
d
i
sam
b
i
g
u
a
t
i
o
n
u
si
n
g
s
e
ma
n
t
i
c
r
e
l
a
t
e
d
n
e
ss
mea
s
u
r
e
,
”
M
u
l
t
i
-
d
i
s
c
i
p
l
i
n
a
ry
T
r
e
n
d
s
i
n
Art
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
:
7
t
h
I
n
t
e
rn
a
t
i
o
n
a
l
Wo
r
k
sh
o
p
,
MIWAI
2
0
1
3
,
K
r
a
b
i
,
T
h
a
i
l
a
n
d
,
v
o
l
.
8
2
7
1
,
p
p
.
2
4
7
–
2
5
6
,
2
0
1
3
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
3
-
6
4
2
-
4
4
9
4
9
-
9
_
2
3
.
[
1
2
]
“
S
e
n
s
e
a
n
n
o
t
a
t
e
d
H
i
n
d
i
c
o
r
p
u
s
:
I
n
d
i
a
n
l
a
n
g
u
a
g
e
t
e
c
h
n
o
l
o
g
y
p
r
o
l
i
f
e
r
a
t
i
o
n
a
n
d
d
e
p
l
o
y
me
n
t
c
e
n
t
r
e
,”
T
D
I
L
.
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
s
:
/
/
t
d
i
l
-
d
c
.
i
n
/
i
n
d
e
x
.
p
h
p
.
[
1
3
]
M
.
S
u
ssn
a
,
“
W
o
r
d
se
n
se
d
i
sam
b
i
g
u
a
t
i
o
n
f
o
r
f
r
e
e
-
t
e
x
t
i
n
d
e
x
i
n
g
u
s
i
n
g
a
m
a
ssi
v
e
s
e
ma
n
t
i
c
n
e
t
w
o
r
k
,
”
Pr
o
c
e
e
d
i
n
g
s
o
f
t
h
e
S
e
c
o
n
d
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
I
n
f
o
rm
a
t
i
o
n
a
n
d
K
n
o
w
l
e
d
g
e
M
a
n
a
g
e
m
e
n
t
,
p
p
.
6
7
–
7
4
,
1
9
9
3
,
d
o
i
:
1
0
.
1
1
4
5
/
1
7
0
0
8
8
.
1
7
0
1
0
6
.
[
1
4
]
E.
A
g
i
r
r
e
a
n
d
G
.
R
i
g
a
u
,
“
W
o
r
d
s
e
n
se
d
i
s
a
mb
i
g
u
a
t
i
o
n
u
s
i
n
g
c
o
n
c
e
p
t
u
a
l
d
e
n
s
i
t
y
,
”
Pro
c
e
e
d
i
n
g
s
o
f
t
h
e
1
6
t
h
c
o
n
f
e
r
e
n
c
e
o
n
C
o
m
p
u
t
a
t
i
o
n
a
l
l
i
n
g
u
i
st
i
c
s
,
p
p
.
1
6
-
22
,
1
9
9
6
,
d
o
i
:
1
0
.
3
1
1
5
/
9
9
2
6
2
8
.
9
9
2
6
3
5
.
[
1
5
]
R
.
M
i
h
a
l
c
e
a
,
P
.
Ta
r
a
u
,
a
n
d
E
.
F
i
g
a
,
“
P
a
g
e
R
a
n
k
o
n
s
e
ma
n
t
i
c
n
e
t
w
o
r
k
s
,
w
i
t
h
a
p
p
l
i
c
a
t
i
o
n
t
o
w
o
r
d
s
e
n
s
e
d
i
s
a
m
b
i
g
u
a
t
i
o
n
,
”
C
O
L
I
N
G
2
0
0
4
-
Pr
o
c
e
e
d
i
n
g
s
o
f
t
h
e
2
0
t
h
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
C
o
m
p
u
t
a
t
i
o
n
a
l
L
i
n
g
u
i
s
t
i
c
s
,
2
0
0
4
,
d
o
i
:
1
0
.
3
1
1
5
/
1
2
2
0
3
5
5
.
1
2
2
0
5
1
7
.
[
1
6
]
R
.
N
a
v
i
g
l
i
,
“
A
s
t
r
u
c
t
u
r
a
l
a
p
p
r
o
a
c
h
t
o
t
h
e
a
u
t
o
ma
t
i
c
a
d
j
u
d
i
c
a
t
i
o
n
o
f
w
o
r
d
s
e
n
s
e
d
i
s
a
g
r
e
e
me
n
t
s,”
N
a
t
u
r
a
l
L
a
n
g
u
a
g
e
E
n
g
i
n
e
e
r
i
n
g
,
v
o
l
.
1
4
,
n
o
.
4
,
p
p
.
5
4
7
–
5
7
3
,
2
0
0
8
,
d
o
i
:
1
0
.
1
0
1
7
/
S
1
3
5
1
3
2
4
9
0
8
0
0
4
7
4
9
.
[
1
7
]
G
.
Ts
a
t
s
a
r
o
n
i
s
,
I
.
V
a
r
l
a
m
i
s,
a
n
d
K
.
N
ø
r
v
å
g
,
“
A
n
e
x
p
e
r
i
m
e
n
t
a
l
s
t
u
d
y
o
n
u
n
s
u
p
e
r
v
i
s
e
d
g
r
a
p
h
-
b
a
se
d
w
o
r
d
s
e
n
s
e
d
i
s
a
mb
i
g
u
a
t
i
o
n
,
”
C
o
m
p
u
t
a
t
i
o
n
a
l
L
i
n
g
u
i
s
t
i
c
s
a
n
d
I
n
t
e
l
l
i
g
e
n
t
T
e
x
t
Pr
o
c
e
ssi
n
g
,
v
o
l
.
6
0
0
8
,
p
p
.
1
8
4
–
1
9
8
,
2
0
1
0
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
3
-
642
-
1
2
1
1
6
-
6
_
1
6
.
[
1
8
]
J.
V
é
r
o
n
i
s,
“
H
y
p
e
r
L
e
x
:
Le
x
i
c
a
l
c
a
r
t
o
g
r
a
p
h
y
f
o
r
i
n
f
o
r
m
a
t
i
o
n
r
e
t
r
i
e
v
a
l
,
”
C
o
m
p
u
t
e
r
S
p
e
e
c
h
a
n
d
L
a
n
g
u
a
g
e
,
v
o
l
.
1
8
,
n
o
.
3
,
p
p
.
2
2
3
–
2
5
2
,
2
0
0
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
c
sl
.
2
0
0
4
.
0
5
.
0
0
2
.
[
1
9
]
A
.
P
u
r
a
n
d
a
r
e
a
n
d
T
.
P
e
d
e
r
s
e
n
,
“
W
o
r
d
s
e
n
s
e
d
i
s
c
r
i
m
i
n
a
t
i
o
n
b
y
c
l
u
s
t
e
r
i
n
g
c
o
n
t
e
x
t
s
i
n
v
e
c
t
o
r
a
n
d
s
i
m
i
l
a
r
i
t
y
s
p
a
c
e
s
,
”
T
h
e
8
t
h
C
o
n
f
e
r
e
n
c
e
o
n
C
o
m
p
u
t
a
t
i
o
n
a
l
N
a
t
u
r
a
l
L
a
n
g
u
a
g
e
L
e
a
r
n
i
n
g
,
C
o
N
L
L
2
0
0
4
-
H
e
l
d
i
n
c
o
o
p
e
r
a
t
i
o
n
w
i
t
h
H
L
T
-
N
A
A
C
L
2
0
0
4
,
p
p
.
4
1
–
4
8
,
2
0
0
4
.
[
2
0
]
E.
A
g
i
r
r
e
a
n
d
A
.
S
o
r
o
a
,
“
S
e
me
v
a
l
-
2
0
0
7
t
a
s
k
0
2
:
E
v
a
l
u
a
t
i
n
g
w
o
r
d
s
e
n
s
e
i
n
d
u
c
t
i
o
n
a
n
d
d
i
s
c
r
i
m
i
n
a
t
i
o
n
s
y
s
t
e
ms,”
A
C
L
2
0
0
7
-
S
e
m
E
v
a
l
2
0
0
7
-
P
ro
c
e
e
d
i
n
g
s
o
f
t
h
e
4
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
W
o
rks
h
o
p
o
n
S
e
m
a
n
t
i
c
Ev
a
l
u
a
t
i
o
n
s
,
v
o
l
.
2
0
0
7
,
p
p
.
7
–
1
2
,
2
0
0
7
.
[
2
1
]
B
.
S
y
n
d
e
r
a
n
d
M
.
P
a
l
m
e
r
,
“
T
h
e
E
n
g
l
i
sh
a
l
l
-
w
o
r
d
s
t
a
sk
,
”
Pr
o
c
e
e
d
i
n
g
s
o
f
S
EN
S
EVAL
-
3
,
t
h
e
T
h
i
r
d
I
n
t
e
rn
a
t
i
o
n
a
l
Wo
r
k
sh
o
p
o
n
t
h
e
Ev
a
l
u
a
t
i
o
n
o
f
S
y
s
t
e
m
s
f
o
r t
h
e
S
e
m
a
n
t
i
c
A
n
a
l
y
s
i
s
o
f
T
e
x
t
,
p
p
.
4
1
–
4
3
,
2
0
0
4
.
[
2
2
]
I
.
P
.
K
l
a
p
a
f
t
i
s
a
n
d
S
.
M
a
n
a
n
d
h
a
r
,
“
W
o
r
d
se
n
se
i
n
d
u
c
t
i
o
n
a
n
d
d
i
sam
b
i
g
u
a
t
i
o
n
u
si
n
g
h
i
e
r
a
r
c
h
i
c
a
l
r
a
n
d
o
m
g
r
a
p
h
s,
”
E
MN
L
P
2
0
1
0
-
C
o
n
f
e
re
n
c
e
o
n
Em
p
i
ri
c
a
l
Me
t
h
o
d
s
i
n
N
a
t
u
r
a
l
L
a
n
g
u
a
g
e
Pro
c
e
ss
i
n
g
,
Pr
o
c
e
e
d
i
n
g
s
o
f
t
h
e
C
o
n
f
e
r
e
n
c
e
,
p
p
.
7
4
5
–
7
5
5
,
2
0
1
0
.
[
2
3
]
I
.
P
.
K
l
a
p
a
f
t
i
s
a
n
d
S
.
M
a
n
a
n
d
h
a
r
,
“
W
o
r
d
se
n
s
e
i
n
d
u
c
t
i
o
n
u
s
i
n
g
g
r
a
p
h
s
o
f
c
o
l
l
o
c
a
t
i
o
n
s
,
”
Fr
o
n
t
i
e
rs
i
n
Ar
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
a
n
d
Ap
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
1
7
8
,
p
p
.
2
9
8
–
3
0
2
,
2
0
0
8
,
d
o
i
:
1
0
.
3
2
3
3
/
9
7
8
-
1
-
5
8
6
0
3
-
8
9
1
-
5
-
2
9
8
.
[
2
4
]
U
.
E.
N
a
r
a
y
a
n
a
n
a
n
d
P
.
B
h
a
t
t
a
c
h
a
r
a
y
y
a
,
“
W
o
r
d
s
e
n
s
e
d
i
s
a
m
b
i
g
u
a
t
i
o
n
u
s
i
n
g
s
e
ma
n
t
i
c
g
r
a
p
h
,
”
P
ro
c
e
e
d
i
n
g
s o
f
t
h
e
1
s
t
I
n
t
e
rn
a
t
i
o
n
a
l
G
l
o
b
a
l
Wo
r
d
N
e
t
C
o
n
f
e
re
n
c
e
,
2
0
0
2
.
[
2
5
]
G
.
A
.
M
i
l
l
e
r
,
C
.
Le
a
c
o
c
k
,
R
.
Te
n
g
i
,
a
n
d
R
.
T
.
B
u
n
k
e
r
,
“
A
sem
a
n
t
i
c
c
o
n
c
o
r
d
a
n
c
e
,
”
Pr
o
c
e
e
d
i
n
g
s
o
f
t
h
e
Wo
r
k
sh
o
p
o
n
H
u
m
a
n
L
a
n
g
u
g
e
T
e
c
h
n
o
l
o
g
y
,
1
9
9
3
,
d
o
i
:
1
0
.
3
1
1
5
/
1
0
7
5
6
7
1
.
1
0
7
5
7
4
2
.
[
2
6
]
R
.
S
i
n
h
a
a
n
d
R
.
M
i
h
a
l
c
e
a
,
“
U
n
s
u
p
e
r
v
i
s
e
d
g
r
a
p
h
-
b
a
se
d
w
o
r
d
s
e
n
s
e
d
i
s
a
m
b
i
g
u
a
t
i
o
n
u
s
i
n
g
me
a
su
r
e
s
o
f
w
o
r
d
sem
a
n
t
i
c
si
m
i
l
a
r
i
t
y
,
”
I
C
S
C
2
0
0
7
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
S
e
m
a
n
t
i
c
C
o
m
p
u
t
i
n
g
,
p
p
.
3
6
3
–
3
6
9
,
2
0
0
7
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
S
C
.
2
0
0
7
.
8
7
.
[
2
7
]
E.
A
g
i
r
r
e
a
n
d
A
.
S
o
r
o
a
,
“
U
si
n
g
t
h
e
mu
l
t
i
l
i
n
g
u
a
l
c
e
n
t
r
a
l
r
e
p
o
s
i
t
o
r
y
f
o
r
g
r
a
p
h
-
b
a
se
d
w
o
r
d
se
n
se
d
i
sam
b
i
g
u
a
t
i
o
n
,
”
Pr
o
c
e
e
d
i
n
g
s
o
f
t
h
e
6
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
L
a
n
g
u
a
g
e
Re
s
o
u
rc
e
s
a
n
d
Ev
a
l
u
a
t
i
o
n
,
L
REC
2
0
0
8
,
p
p
.
1
3
8
8
–
1
3
9
2
,
2
0
0
8
.
[
2
8
]
C
.
S
i
l
b
e
r
e
r
a
n
d
S
.
P
.
P
o
n
z
e
t
t
o
,
“
U
H
D
:
C
r
o
ss
-
l
i
n
g
u
a
l
w
o
r
d
s
e
n
s
e
d
i
sam
b
i
g
u
a
t
i
o
n
u
s
i
n
g
mu
l
t
i
l
i
n
g
u
a
l
C
o
-
o
c
c
u
r
r
e
n
c
e
g
r
a
p
h
s,”
A
C
L
2
0
1
0
-
S
e
m
E
v
a
l
2
0
1
0
-
5
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
Wo
r
k
sh
o
p
o
n
S
e
m
a
n
t
i
c
Ev
a
l
u
a
t
i
o
n
,
Pro
c
e
e
d
i
n
g
s
,
p
p
.
1
3
4
–
1
3
7
,
2
0
1
0
.
[
2
9
]
S
.
K
.
V
i
s
h
w
a
k
a
r
ma
a
n
d
C
.
K
.
V
i
s
h
w
a
k
a
r
m
a
,
“
A
g
r
a
p
h
-
b
a
se
d
a
p
p
r
o
a
c
h
t
o
w
o
r
d
se
n
se
d
i
s
a
m
b
i
g
u
a
t
i
o
n
f
o
r
H
i
n
d
i
l
a
n
g
u
a
g
e
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
S
c
i
e
n
t
i
f
i
c
R
e
s
e
a
r
c
h
En
g
i
n
e
e
r
i
n
g
&
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
1
,
p
p
.
3
1
3
–
3
1
8
,
2
0
1
2
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
13
,
No
.
4
,
Dec
em
b
er
2
0
2
4
:
4
9
5
7
-
4
9
6
4
4964
[
3
0
]
A
.
Jai
n
,
S
.
Y
a
d
a
v
,
a
n
d
D
.
T
a
y
a
l
,
“
M
e
a
s
u
r
i
n
g
c
o
n
t
e
x
t
-
me
a
n
i
n
g
f
o
r
o
p
e
n
c
l
a
ss
w
o
r
d
s
i
n
H
i
n
d
i
l
a
n
g
u
a
g
e
,
”
2
0
1
3
6
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
C
o
n
t
e
m
p
o
ra
r
y
C
o
m
p
u
t
i
n
g
,
I
C
3
2
0
1
3
,
p
p
.
1
1
8
–
1
2
3
,
2
0
1
3
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
3
.
2
0
1
3
.
6
6
1
2
1
7
4
.
[
3
1
]
A
.
Jai
n
a
n
d
D
.
K
.
L
o
b
i
y
a
l
,
“
F
u
z
z
y
H
i
n
d
i
w
o
r
d
n
e
t
a
n
d
w
o
r
d
se
n
s
e
d
i
sa
mb
i
g
u
a
t
i
o
n
u
s
i
n
g
f
u
z
z
y
g
r
a
p
h
c
o
n
n
e
c
t
i
v
i
t
y
mea
s
u
r
e
s
,
”
A
C
M
T
ra
n
s
a
c
t
i
o
n
s
o
n
As
i
a
n
a
n
d
L
o
w
-
Re
s
o
u
rc
e
L
a
n
g
u
a
g
e
I
n
f
o
rm
a
t
i
o
n
Pro
c
e
ss
i
n
g
,
v
o
l
.
1
5
,
n
o
.
2
,
2
0
1
5
,
d
o
i
:
1
0
.
1
1
4
5
/
2
7
9
0
0
7
9
.
[
3
2
]
G
.
J
a
i
n
a
n
d
D
.
K
.
L
o
b
i
y
a
l
,
“
W
o
r
d
s
e
n
s
e
d
i
s
a
m
b
i
g
u
a
t
i
o
n
u
s
i
n
g
c
o
o
p
e
r
a
t
i
v
e
g
a
m
e
t
h
e
o
r
y
a
n
d
f
u
z
z
y
h
i
n
d
i
w
o
r
d
n
e
t
b
a
s
e
d
o
n
C
o
n
c
e
p
t
N
e
t
,
”
A
C
M
T
r
a
n
s
a
c
t
i
o
n
s
o
n
A
s
i
a
n
a
n
d
L
o
w
-
R
e
s
o
u
r
c
e
L
a
n
g
u
a
g
e
I
n
f
o
r
m
a
t
i
o
n
P
r
o
c
e
s
s
i
n
g
,
v
o
l
.
2
1
,
n
o
.
4
,
2
0
2
2
,
d
o
i
:
1
0
.
1
1
4
5
/
3
5
0
2
7
3
9
.
[
3
3
]
N
.
K
o
p
p
u
l
a
,
B
.
P
.
R
a
n
i
,
a
n
d
K
.
S
.
R
a
o
,
“
W
o
r
d
s
e
n
s
e
d
i
sam
b
i
g
u
a
t
i
o
n
i
n
t
e
l
u
g
u
l
a
n
g
u
a
g
e
u
si
n
g
k
n
o
w
l
e
d
g
e
-
b
a
s
e
d
a
p
p
r
o
a
c
h
,
”
Ad
v
a
n
c
e
s i
n
I
n
t
e
l
l
i
g
e
n
t
S
y
st
e
m
s
a
n
d
C
o
m
p
u
t
i
n
g
,
v
o
l
.
1
0
9
0
,
p
p
.
1
5
3
–
1
6
1
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
9
8
1
-
15
-
1
4
8
0
-
7
_
1
3
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Pra
jn
a
J
h
a
is
a
re
se
a
rc
h
sc
h
o
lar
i
n
th
e
field
o
f
n
a
t
u
ra
l
lan
g
u
a
g
e
p
r
o
c
e
ss
in
g
a
n
d
a
rti
ficia
l
in
tell
ig
e
n
c
e
in
th
e
De
p
a
rtme
n
t
o
f
E
lec
tro
n
ics
a
n
d
C
o
m
m
u
n
ica
ti
o
n
,
Un
i
v
e
rsity
o
f
Allah
a
b
a
d
.
S
h
e
h
a
s
c
o
m
p
lete
d
M
a
ste
r
o
f
Tec
h
n
o
lo
g
y
(M
.
Tec
h
.
)
in
Co
m
p
u
ter
S
c
ien
c
e
fr
o
m
Ba
n
a
sth
a
li
Vid
y
a
p
it
h
,
T
o
n
k
,
Ra
jas
th
a
n
.
S
h
e
h
a
s
a
ls
o
w
o
rk
e
d
a
t
III
T
-
Hy
d
e
ra
b
a
d
o
n
th
e
M
a
c
h
in
e
Tran
sla
ti
o
n
T
o
o
l
-
A
n
u
sa
a
ra
k
a
.
S
h
e
h
a
s
p
u
b
li
sh
e
d
re
n
o
wn
e
d
a
rti
c
les
in
we
ll
-
re
p
u
te
d
c
o
n
fe
re
n
c
e
,
a
n
d
jo
u
rn
a
l
o
n
t
h
e
to
p
ic
o
f
re
o
r
d
e
rin
g
,
a
n
d
wo
r
d
se
n
se
d
isa
m
b
ig
u
a
ti
o
n
i
n
Hin
d
i
Lan
g
u
a
g
e
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
p
ra
g
y
a
.
jh
a
.
jk
@
g
m
a
il
.
c
o
m
o
r
p
ra
jn
a
_
jh
a
@a
ll
d
u
n
iv
.
a
c
.
i
n
.
S
h
r
e
y
a
Ag
a
r
wa
l
is
a
re
se
a
rc
h
sc
h
o
lar
in
t
h
e
De
p
a
rtme
n
t
o
f
El
e
c
tro
n
ics
a
n
d
Co
m
m
u
n
ica
ti
o
n
s
in
t
h
e
field
o
f
NLP
,
in
U
n
iv
e
rsit
y
o
f
Allah
a
b
a
d
.
S
h
e
d
i
d
h
e
r
m
a
ste
rs
in
Co
m
p
u
ter
S
c
ie
n
c
e
a
n
d
wa
s
a
wa
rd
e
d
a
G
o
ld
M
e
d
a
l
f
ro
m
Un
i
v
e
rsi
ty
o
f
Allah
a
b
a
d
.
He
r
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
d
isc
o
u
rse
a
n
a
ly
sis,
n
a
tu
ra
l
lan
g
u
a
g
e
p
ro
c
e
ss
in
g
,
g
e
n
e
ra
ti
v
e
AI,
i
n
fo
rm
a
ti
o
n
e
x
trac
ti
o
n
,
a
n
d
m
a
c
h
in
e
lea
rn
in
g
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
a
g
a
rwa
l.
sh
re
y
a
1
9
9
4
@
g
m
a
il
.
c
o
m
.
Ali
Abb
a
s
h
a
s
fin
ish
e
d
M
a
ste
r
o
f
Tec
h
n
o
l
o
g
y
(M
.
Tec
h
.
)
d
e
g
re
e
in
Co
m
p
u
ter
Tec
h
n
o
l
o
g
y
,
sp
e
c
ializin
g
in
n
a
t
u
r
a
l
lan
g
u
a
g
e
p
r
o
c
e
ss
in
g
.
His
re
se
a
rc
h
b
a
c
k
g
r
o
u
n
d
e
n
c
o
m
p
a
ss
e
s
o
v
e
r
six
y
e
a
rs
o
f
e
x
p
e
rien
c
e
in
th
e
field
o
f
d
o
c
u
m
e
n
t
c
las
sifica
ti
o
n
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
a
li
a
b
b
a
s3
6
7
@g
m
a
il
.
c
o
m
.
Dr
.
S
a
ty
e
n
d
r
S
in
g
h
is
wo
rk
in
g
i
n
t
h
e
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
En
g
i
n
e
e
rin
g
a
t
B
M
L
M
u
n
jal
U
n
iv
e
rsity
,
G
u
ru
g
ra
m
.
He
o
b
tain
e
d
P
h
.
D
.
i
n
Co
m
p
u
ter
S
c
ien
c
e
fro
m
th
e
Un
i
v
e
rsity
o
f
Al
lah
a
b
a
d
,
P
ra
y
a
g
ra
j,
In
d
ia i
n
2
0
1
5
.
His res
e
a
rc
h
in
tere
sts in
c
lu
d
e
n
a
t
u
ra
l
lan
g
u
a
g
e
p
ro
c
e
ss
in
g
,
m
a
c
h
in
e
lea
rn
in
g
,
a
n
d
c
o
m
p
u
tati
o
n
a
l
sta
ti
st
ics
.
H
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
sa
ty
e
n
d
r@g
m
a
il
.
c
o
m
.
Pro
f.
T
a
n
v
e
e
r
J
a
h
a
n
S
id
d
iq
u
i
is
P
ro
fe
ss
o
r
i
n
c
o
m
p
u
ter
sc
ie
n
c
e
,
De
p
a
rtme
n
t
o
f
El
e
c
tro
n
ics
a
n
d
Co
m
m
u
n
ica
ti
o
n
with
m
o
re
t
h
a
n
2
5
y
e
a
rs
o
f
e
x
p
e
ri
e
n
c
e
in
tea
c
h
in
g
a
n
d
re
se
a
rc
h
.
S
h
e
p
u
b
li
s
h
e
d
m
o
re
t
h
a
n
4
0
re
se
a
rc
h
a
rti
c
les
in
jo
u
rn
a
ls
a
n
d
c
o
n
f
e
re
n
c
e
p
ro
c
e
e
d
in
g
,
e
d
it
e
d
/au
t
h
o
re
d
b
o
o
k
s.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
sid
d
iq
u
i.
ta
n
v
e
e
r@g
m
a
il
.
c
o
m
.
Evaluation Warning : The document was created with Spire.PDF for Python.