I
nte
rna
t
io
na
l J
o
urna
l o
f
E
lect
rica
l a
nd
Co
m
pu
t
er
E
ng
ineering
(
I
J
E
CE
)
Vo
l.
1
6
,
No
.
1
,
Feb
r
u
ar
y
20
2
6
,
p
p
.
246
~
255
I
SS
N:
2088
-
8
7
0
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijece.
v
1
6
i
1
.
pp
2
4
6
-
2
5
5
246
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ec
e.
ia
esco
r
e.
co
m
An inf
o
rma
tion
r
etrie
v
a
l sy
stem
for India
n lega
l doc
uments
Ra
s
m
i R
a
ni Dha
la
1
,
A
V
S P
a
v
a
n K
um
a
r
1
,
So
um
y
a
P
riy
a
da
rsin
i P
a
nd
a
2
1
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
,
G
a
n
d
h
i
I
n
st
i
t
u
t
e
o
f
En
g
i
n
e
e
r
i
n
g
a
n
d
Te
c
h
n
o
l
o
g
y
U
n
i
v
e
r
si
t
y
,
G
u
n
u
p
u
r
,
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
i
l
i
c
o
n
U
n
i
v
e
r
s
i
t
y
,
O
d
i
sh
a
,
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
Ma
r
1
3
,
2
0
2
5
R
ev
is
ed
Sep
1
9
,
2
0
2
5
Acc
ep
ted
No
v
2
3
,
2
0
2
5
In
th
is
wo
r
k
,
a
leg
a
l
d
o
c
u
m
e
n
t
r
e
tri
e
v
a
l
sy
ste
m
is
p
re
se
n
ted
th
a
t
e
stim
a
tes
th
e
sig
n
ifi
c
a
n
c
e
o
f
th
e
u
se
r
q
u
e
ries
to
a
p
p
r
o
p
riate
leg
a
l
s
u
b
-
d
o
m
a
in
s
a
n
d
e
x
trac
ts t
h
e
k
e
y
d
o
c
u
m
e
n
ts co
n
tai
n
in
g
re
q
u
ire
d
in
fo
rm
a
ti
o
n
q
u
ick
l
y
.
In
o
rd
e
r
to
d
e
v
e
lo
p
su
c
h
a
s
y
ste
m
,
a
d
o
c
u
m
e
n
t
re
p
o
sit
o
ry
is
p
re
p
a
re
d
c
o
m
p
risin
g
th
e
d
o
c
u
m
e
n
ts
a
n
d
c
a
se
stu
d
y
re
p
o
r
ts
o
f
d
iffere
n
t
I
n
d
ia
n
leg
a
l
m
a
tt
e
rs
o
f
las
t
fiv
e
y
e
a
rs.
A
leg
a
l
su
b
-
d
o
m
a
in
c
las
sifica
ti
o
n
tec
h
n
iq
u
e
u
sin
g
d
e
e
p
n
e
u
ra
l
n
e
two
rk
(DN
N)
m
o
d
e
l
is
u
se
d
t
o
o
b
tai
n
th
e
re
lev
a
n
c
e
o
f
th
e
u
s
e
r
q
u
e
ries
with
re
sp
e
c
ti
v
e
leg
a
l
s
u
b
-
d
o
m
a
in
s
fo
r
q
u
ick
i
n
fo
rm
a
ti
o
n
re
tri
e
v
a
l.
A
q
u
e
ry
-
d
o
c
u
m
e
n
t
re
le
v
a
n
c
e
(QD
R)
sc
o
re
-
b
a
se
d
tec
h
n
iq
u
e
is
p
re
se
n
ted
t
o
ra
n
k
th
e
o
u
t
p
u
t
d
o
c
u
m
e
n
ts
i
n
re
latio
n
t
o
th
e
q
u
e
ry
term
s.
Th
e
p
re
se
n
ted
m
o
d
e
l
is
e
v
a
lu
a
ted
b
y
p
e
rf
o
rm
in
g
se
v
e
ra
l
e
x
p
e
rime
n
ts
u
n
d
e
r
d
iffere
n
t
c
o
n
tex
t
a
n
d
th
e
p
e
rfo
rm
a
n
c
e
o
f
th
e
p
re
se
n
ted
m
o
d
e
l
is
a
n
a
ly
z
e
d
.
T
h
e
p
re
se
n
ted
m
o
d
e
l
a
c
h
iev
e
s
a
n
a
v
e
ra
g
e
p
re
c
isio
n
sc
o
re
o
f
0
.
9
8
a
n
d
re
c
a
ll
sc
o
re
o
f
0
.
9
7
i
n
t
h
e
e
x
p
e
rime
n
ts
p
e
rfo
rm
e
d
.
Th
e
re
tri
e
v
a
l
m
o
d
e
l
is
a
ss
e
ss
e
d
with
o
t
h
e
r
re
tri
e
v
a
l
m
o
d
e
ls
a
n
d
t
h
e
p
re
se
n
ted
m
o
d
e
l
a
c
h
iev
e
s
1
3
%
a
n
d
1
2
%
i
n
c
re
a
se
a
v
e
ra
g
e
a
c
c
u
ra
c
y
with
re
sp
e
c
t
to
p
re
c
isi
o
n
sc
o
re
s
a
n
d
re
c
a
ll
m
e
a
su
re
s
re
sp
e
c
ti
v
e
ly
c
o
m
p
a
re
d
to
th
e
tra
d
it
i
o
n
a
l
m
o
d
e
ls
sh
o
win
g
t
h
e
stre
n
g
th
o
f
t
h
e
p
re
se
n
ted
m
o
d
e
l.
K
ey
w
o
r
d
s
:
Dee
p
n
eu
r
al
n
etwo
r
k
Do
m
ain
class
if
icatio
n
L
eg
al
d
o
cu
m
en
t r
etr
ie
v
al
Natu
r
al
lan
g
u
ag
e
p
r
o
ce
s
s
in
g
Qu
er
y
p
r
o
ce
s
s
in
g
T
h
is i
s
a
n
o
p
e
n
a
c
c
e
ss
a
rticle
u
n
d
e
r th
e
CC B
Y
-
SA
li
c
e
n
se
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
So
u
m
y
a
Priy
ad
a
r
s
in
i Pan
d
a
Dep
ar
tm
en
t o
f
C
o
m
p
u
ter
Scie
n
ce
an
d
E
n
g
in
ee
r
in
g
,
Sil
ico
n
Un
iv
er
s
ity
Od
is
h
a,
I
n
d
ia
E
m
ail: so
u
m
y
a.
p
a
n
d
a@
s
ilico
n
.
ac
.
in
1.
I
NT
RO
D
UCT
I
O
N
T
h
e
f
ield
o
f
d
o
cu
m
en
t
in
f
o
r
m
atio
n
r
etr
iev
al
(
I
R
)
co
n
ce
r
n
s
o
n
r
etr
iev
in
g
r
elev
a
n
t
d
o
cu
m
e
n
ts
o
u
t
o
f
a
v
ar
ied
d
o
cu
m
en
t
co
llectio
n
b
ased
o
n
s
o
m
e
u
s
er
en
ter
ed
q
u
er
y
[
1
]
.
I
t
h
as
its
ap
p
licatio
n
s
in
d
esig
n
in
g
web
s
ea
r
ch
en
g
in
es
[
2
]
,
q
u
esti
o
n
an
s
wer
in
g
s
y
s
tem
s
[
3
]
,
d
ig
ital
lib
r
ar
ies
[
4
]
,
r
ec
o
m
m
en
d
atio
n
s
y
s
tem
s
[
5
]
,
o
r
g
an
izatio
n
al
d
ata
r
etr
iev
al
s
y
s
tem
s
[
6
]
.
T
h
e
u
s
er
s
in
n
ee
d
o
f
s
o
m
e
in
f
o
r
m
atio
n
m
ay
p
r
e
s
en
t
a
q
u
er
y
to
th
e
s
y
s
tem
co
m
p
r
is
in
g
r
elate
d
k
e
y
wo
r
d
s
,
an
d
th
e
r
etr
iev
al
m
o
d
el
r
etu
r
n
s
a
lis
t
o
f
o
u
tp
u
t
d
o
c
u
m
en
ts
as
p
er
th
eir
co
n
ten
t
m
atch
with
th
e
wo
r
d
s
in
th
e
q
u
er
y
[
7
]
.
W
ith
th
e
av
ailab
ilit
y
o
f
m
ass
iv
e
n
u
m
b
er
o
f
d
ig
ital
r
ep
o
s
ito
r
ies
av
ailab
le
o
n
lin
e
a
n
d
t
h
eir
r
a
p
id
g
r
o
wth
[
8
]
,
it
is
ch
allen
g
in
g
to
f
etc
h
th
e
r
eq
u
ir
e
d
in
f
o
r
m
atio
n
q
u
ic
k
ly
[
9
]
,
[
1
0
]
.
Als
o
,
u
s
er
q
u
er
ies
m
ay
b
e
th
e
p
ar
tial
s
p
ec
if
icatio
n
o
f
th
eir
n
ee
d
s
,
h
an
d
lin
g
d
if
f
er
en
t
am
b
ig
u
ities
in
th
e
q
u
er
y
wo
r
d
s
a
n
d
p
r
o
ce
s
s
in
g
th
e
ac
tu
al
in
te
n
t
o
f
th
e
u
s
er
s
in
d
if
f
er
e
n
t
d
o
m
ain
s
is
s
till
a
ch
allen
g
in
g
task
[
1
1
]
.
T
h
is
m
ak
es
th
e
I
R
tech
n
o
lo
g
y
an
ac
tiv
e
ar
ea
o
f
r
esear
ch
wi
th
p
len
ty
o
f
f
u
tu
r
e
r
esear
ch
o
p
p
o
r
tu
n
ities
f
o
r
th
e
r
esear
ch
er
s
to
d
esig
n
s
p
ec
ializ
ed
m
eth
o
d
s
th
at
m
ay
ad
d
r
ess
th
e
co
n
tex
t
lev
el
p
r
o
ce
s
s
in
g
in
d
if
f
er
en
t
d
o
m
ain
s
[
1
2
]
.
T
h
er
e
ar
e
a
n
u
m
b
er
o
f
d
o
m
ai
n
s
p
ec
if
ic
r
etr
iev
al
m
o
d
els
h
a
v
e
b
ee
n
d
o
c
u
m
en
ted
in
t
h
e
d
o
m
ain
s
o
f
ag
r
icu
ltu
r
e,
m
ed
ical,
d
ig
ital
li
b
r
ar
ies,
leg
al
in
f
o
r
m
atio
n
r
etr
iev
al,
an
d
d
if
f
er
en
t
o
r
g
an
izati
o
n
al
d
ata
r
etr
iev
al
[
1
3
]
,
[
1
4
]
.
Ov
er
th
e
p
ast f
ew
y
ea
r
s
,
th
e
f
ield
o
f
leg
al
i
n
f
o
r
m
a
tio
n
r
etr
ie
v
al
h
as
r
ec
eiv
ed
s
ig
n
if
ican
t
im
p
o
r
tan
ce
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
A
n
in
fo
r
ma
tio
n
r
etri
ev
a
l sys
t
em
fo
r
I
n
d
ia
n
le
g
a
l d
o
cu
men
ts
(
R
a
s
mi
R
a
n
i D
h
a
l
a
)
247
am
o
n
g
leg
al
p
r
ac
titi
o
n
er
s
an
d
tech
n
o
lo
g
is
ts
d
u
e
to
its
p
o
ten
tiality
to
b
r
in
g
s
ig
n
if
ican
t
in
n
o
v
atio
n
to
th
e
leg
al
in
d
u
s
tr
y
[
1
5
]
,
[
1
6
]
.
Als
o
,
r
ec
en
tly
,
th
e
I
R
tech
n
o
lo
g
y
h
as
u
n
d
er
g
o
n
e
s
ig
n
if
ican
t
ad
v
an
c
em
en
ts
d
u
e
to
t
h
e
ad
ap
tatio
n
o
f
d
i
f
f
er
en
t
m
ac
h
i
n
e
lear
n
in
g
m
o
d
els
to
ac
h
ie
v
e
b
etter
p
e
r
f
o
r
m
an
ce
[
1
1
]
.
T
h
e
u
s
e
o
f
d
o
cu
m
en
ts
r
elate
d
to
d
if
f
er
e
n
t
leg
al
m
att
er
s
h
as
th
e
ca
p
ac
ity
t
o
ex
p
an
d
ac
ce
s
s
to
ju
s
tice
b
y
p
r
o
v
id
i
n
g
ac
ce
s
s
ib
le
an
d
h
ig
h
-
q
u
ality
leg
al
s
u
p
p
o
r
t
at
r
ed
u
ce
d
co
s
t
to
th
e
u
s
er
s
[
1
7
]
.
T
h
e
I
R
s
y
s
tem
s
o
n
leg
al
d
o
m
ain
m
a
y
allo
w
ex
tr
ac
tin
g
u
s
ef
u
l
i
n
f
o
r
m
atio
n
f
r
o
m
p
r
ev
io
u
s
ca
s
es
to
s
u
p
p
o
r
t
cu
r
r
en
t
a
n
aly
s
is
an
d
q
u
ick
d
ec
is
io
n
m
ak
in
g
in
s
im
ilar
leg
al
m
atter
s
[
1
8
]
.
Als
o
,
ac
cu
r
ate
r
etr
iev
al
o
f
leg
al
i
n
f
o
r
m
atio
n
is
v
ital
to
p
r
o
v
id
e
ac
ce
s
s
to
th
e
law
to
lay
m
en
a
n
d
leg
al
p
r
o
f
ess
io
n
als.
Du
e
to
th
e
r
ap
i
d
in
c
r
ea
s
e
in
th
e
leg
al
d
o
cu
m
e
n
ts
av
ailab
le
in
elec
tr
o
n
ic
f
o
r
m
,
leg
al
I
R
s
y
s
tem
s
ar
e
b
ec
o
m
in
g
im
p
o
r
tan
t
th
ese
d
ay
s
with
a
h
u
g
e
d
em
an
d
f
r
o
m
v
a
r
ied
u
s
e
r
co
m
m
u
n
ities
[
1
9
]
.
T
h
is
wo
r
k
f
o
cu
s
es
o
n
u
s
in
g
th
e
I
R
tech
n
o
lo
g
y
in
th
e
leg
al
d
o
m
ain
to
d
esig
n
an
I
R
s
y
s
tem
f
o
r
th
e
I
n
d
ia
n
leg
al
d
o
cu
m
e
n
ts
.
A
leg
al
d
o
cu
m
e
n
t
r
etr
iev
al
(
L
DR
)
s
y
s
tem
is
a
v
ar
ian
t
o
f
th
e
I
R
tech
n
o
lo
g
y
th
at
f
o
cu
s
es
o
n
ef
f
icien
tly
lo
ca
tin
g
r
ele
v
an
t
le
g
al
d
o
c
u
m
en
ts
f
r
o
m
co
llectio
n
o
f
d
o
cu
m
en
ts
a
n
d
ca
s
e
s
tu
d
y
r
ep
o
r
ts
r
elate
d
to
d
if
f
er
en
t
ca
s
e
m
atter
s
[
2
0
]
.
T
h
e
L
DR
s
y
s
tem
s
ar
e
v
er
y
h
el
p
f
u
l
f
o
r
t
h
e
leg
al
p
r
o
f
ess
io
n
als
an
d
o
t
h
er
u
s
er
s
in
n
ee
d
o
f
s
o
m
e
leg
al
in
f
o
r
m
ati
o
n
to
f
etch
th
e
r
e
q
u
ir
ed
i
n
f
o
r
m
atio
n
r
elate
d
to
s
o
m
e
leg
al
m
a
t
t
er
q
u
ick
ly
f
r
o
m
a
v
ast
lan
d
s
ca
p
e
o
f
leg
al
d
o
cu
m
en
ts
.
As
d
ig
ital
in
f
o
r
m
atio
n
s
o
u
r
ce
s
o
n
d
if
f
e
r
en
t
leg
al
m
atter
s
ar
e
in
cr
ea
s
in
g
d
ay
b
y
d
ay
,
it
i
s
b
ec
o
m
in
g
d
if
f
icu
lt
f
o
r
t
h
e
leg
al
p
r
ac
titi
o
n
er
s
to
f
etch
th
e
r
eq
u
ir
e
d
in
f
o
r
m
a
tio
n
q
u
ick
l
y
.
Als
o
,
m
an
u
al
s
ea
r
ch
in
g
o
f
leg
al
in
f
o
r
m
atio
n
f
r
o
m
v
ast an
d
s
u
b
s
tan
tial le
n
g
th
o
f
leg
al
d
o
c
u
m
en
ts
wh
ich
in
clu
d
es th
e
r
ep
o
r
ts
o
n
d
i
f
f
er
en
t
leg
al
ca
s
e
s
tu
d
ies,
s
tatu
tes,
d
o
cu
m
en
ts
o
r
tex
t
r
elate
d
to
leg
al
m
atter
s
,
co
n
tr
ac
ts
,
r
u
les
an
d
r
eg
u
latio
n
s
,
leg
al
o
p
in
io
n
s
,
is
a
ted
io
u
s
task
[
2
1
]
.
I
t is cr
u
cia
l in
f
ac
ilit
atin
g
leg
al
r
esear
ch
e
r
s
an
d
p
r
ac
titi
o
n
er
s
to
q
u
ick
ly
p
r
o
v
id
e
ac
ce
s
s
to
r
elev
an
t
in
f
o
r
m
atio
n
f
r
o
m
lar
g
e
co
llectio
n
o
f
d
ig
ital
leg
al
in
f
o
r
m
atio
n
s
o
u
r
ce
s
[
2
2
]
.
T
h
er
e
f
o
r
e,
th
er
e
is
a
n
e
ed
f
o
r
th
e
d
ev
elo
p
m
en
t
o
f
e
f
f
ec
tiv
e
m
eth
o
d
s
t
o
wo
r
k
o
n
th
e
v
ar
ied
leg
al
d
ata
s
o
u
r
ce
s
an
d
m
ay
p
r
o
ce
s
s
th
e
v
ast
co
llectio
n
o
f
leg
al
d
o
cu
m
en
ts
an
d
p
r
o
v
id
e
th
e
n
ee
d
e
d
in
f
o
r
m
atio
n
q
u
ick
ly
to
th
e
leg
al
p
r
ac
titi
o
n
e
r
to
r
ef
er
to
s
im
ilar
ca
s
e
s
tu
d
ies
in
t
h
e
p
r
e
v
io
u
s
ly
r
ep
o
r
te
d
ca
s
es
to
b
e
c
o
n
s
id
er
ed
to
r
ea
ch
to
s
o
m
e
c
o
n
clu
s
io
n
s
.
L
eg
al
d
o
c
u
m
en
t
r
etr
iev
al
(
L
DR
)
is
a
ch
allen
g
in
g
task
an
d
h
as
r
ec
eiv
ed
in
ter
est
f
r
o
m
b
o
th
r
esear
ch
er
s
an
d
i
n
d
u
s
tr
y
r
ec
e
n
tly
to
s
u
p
p
o
r
t
th
e
law
p
r
ac
tit
io
n
er
s
to
m
in
im
ize
t
h
e
h
ea
v
y
m
an
u
al
wo
r
k
th
e
y
ca
r
r
ied
o
u
t
to
p
e
r
f
o
r
m
d
if
f
er
e
n
t
ca
s
e
s
tu
d
ies
[
2
3
]
.
Als
o
,
an
L
DR
s
y
s
tem
m
ay
also
b
e
u
s
ef
u
l
f
o
r
t
h
e
co
m
m
o
n
p
eo
p
le
in
n
ee
d
o
f
s
o
m
e
b
asic
leg
al
in
f
o
r
m
atio
n
to
r
etr
iev
e
th
e
ap
p
r
o
p
r
iate
leg
al
in
f
o
r
m
at
io
n
q
u
ick
l
y
as
p
er
th
eir
n
ee
d
s
.
Ho
wev
er
,
th
e
m
aj
o
r
ch
allen
g
e
in
d
esig
n
in
g
a
le
g
al
I
R
s
y
s
tem
is
d
u
e
to
th
e
v
a
r
iety
o
f
leg
al
ca
s
es
an
d
th
e
v
ast
co
llectio
n
o
f
d
ig
ital
s
o
u
r
ce
s
,
wh
ich
r
eq
u
ir
es
ex
p
er
tis
e
in
u
n
d
er
s
tan
d
i
n
g
b
o
t
h
th
e
ca
s
e
an
d
th
e
ass
o
ciate
d
law
r
elate
d
to
th
at
[
2
4
]
.
Als
o
,
th
e
f
r
eq
u
e
n
t
leg
is
lativ
e
ch
an
g
es
m
a
y
r
e
n
d
er
p
r
io
r
ca
s
e
law
o
b
s
o
let
e
o
r
in
ap
p
licab
le
in
d
r
af
ti
n
g
leg
al
ac
ts
[
2
5
]
.
L
eg
al
tex
ts
m
ay
also
in
clu
d
e
s
tatu
tes,
ca
s
e
l
aw,
r
eg
u
latio
n
s
,
an
d
leg
al
o
p
in
io
n
s
,
d
if
f
er
e
n
t
q
u
o
t
atio
n
s
f
r
o
m
o
th
er
ju
d
g
m
en
ts
,
an
d
leg
is
lativ
e
r
ef
er
en
ce
s
th
at
r
eq
u
ir
e
ad
v
an
ce
d
tex
t
an
aly
s
is
tech
n
iq
u
es
to
b
e
in
co
r
p
o
r
ated
to
id
en
tify
th
e
e
x
ac
t
in
ten
t
as
p
er
th
e
n
ee
d
[
1
9
]
.
T
h
e
p
r
esen
ce
o
f
co
m
m
o
n
ter
m
in
o
l
o
g
ies
with
d
o
m
ain
-
s
p
ec
if
ic
te
r
m
s
ad
d
e
d
m
o
r
e
c
h
allen
g
es
to
t
h
e
d
ev
elo
p
m
en
t
o
f
s
u
ch
s
y
s
tem
.
L
eg
al
d
o
c
u
m
en
ts
m
a
y
co
n
tain
i
n
f
o
r
m
atio
n
i
n
th
e
f
o
r
m
s
o
f
ab
s
tr
ac
t,
f
o
r
m
al
o
r
a
ju
d
icial
lan
g
u
ag
e
th
at
m
ay
c
o
n
tain
lar
g
e
n
ar
r
ativ
e
p
ar
ts
wh
ich
ar
e
d
if
f
icu
lt
to
an
aly
ze
b
y
s
im
p
le
wo
r
d
le
v
el
tex
t
p
r
o
ce
s
s
in
g
m
eth
o
d
s
.
T
h
er
ef
o
r
e,
r
etr
iev
al
o
f
leg
al
m
atter
s
f
r
o
m
lar
g
e
co
llectio
n
o
f
d
o
cu
m
en
ts
i
s
s
till
a
m
atter
o
f
co
n
s
id
er
ab
le
d
if
f
icu
lty
an
d
s
p
ec
ialized
m
eth
o
d
s
an
d
ap
p
r
o
ac
h
es
ar
e
n
ee
d
ed
d
u
e
to
th
e
d
is
tin
ctiv
e
ch
ar
ac
ter
is
tics
o
f
leg
al
d
o
c
u
m
en
ts
[
2
3
]
.
T
h
er
e
is
f
ewe
r
r
esear
ch
d
o
c
u
m
en
ted
i
n
th
e
L
DR
d
o
m
ain
.
T
h
e
ea
r
lier
L
DR
r
esear
ch
f
o
cu
s
es
o
n
ex
tr
ac
tin
g
r
ele
v
an
t
leg
al
i
n
f
o
r
m
atio
n
u
s
in
g
k
ey
wo
r
d
-
b
ased
m
atch
s
co
r
e
tech
n
iq
u
es
[
1
7
]
.
T
h
o
s
e
m
eth
o
d
s
ar
e
f
o
u
n
d
to
b
e
less
ef
f
ec
tiv
e
i
n
te
r
m
s
o
f
f
etch
in
g
th
e
r
ele
v
an
t
in
f
o
r
m
atio
n
q
u
ic
k
ly
f
r
o
m
h
u
g
e
co
llectio
n
s
o
f
leg
al
d
o
cu
m
e
n
ts
with
th
e
co
m
p
le
x
leg
al
tex
t
f
o
r
m
ats
[
1
8
]
.
W
ith
th
e
s
h
if
t
in
r
esear
ch
f
o
cu
s
to
war
d
s
d
ee
p
lear
n
i
n
g
ar
ch
itectu
r
es,
atten
tio
n
-
b
ased
m
o
d
els
em
er
g
ed
as
a
m
ea
n
s
t
o
o
b
tai
n
im
p
r
o
v
e
d
d
ata
r
ep
r
e
s
en
tatio
n
s
in
leg
al
d
o
m
ain
s
[
1
9
]
.
I
n
leg
al
d
o
cu
m
en
t
r
etr
iev
al
p
r
o
ce
s
s
,
r
elev
an
t
in
f
o
r
m
atio
n
g
o
es
b
ey
o
n
d
s
im
p
le
k
ey
wo
r
d
m
atch
in
g
to
p
r
o
ce
s
s
th
e
co
n
tex
t
an
d
m
ea
n
in
g
o
f
leg
al
te
r
m
in
o
lo
g
ies
an
d
co
n
ce
p
ts
.
[
2
0
]
d
is
cu
s
s
es
ab
o
u
t
a
leg
al
k
n
o
wled
g
e
g
r
ap
h
s
tech
n
iq
u
e
wh
er
e,
leg
al
n
o
tio
n
s
,
ca
s
es,
s
ta
tu
tes,
an
d
th
eir
lin
k
ag
es
ar
e
r
ep
r
esen
ted
g
r
ap
h
-
wis
e,
allo
win
g
s
em
an
ti
c
s
ea
r
ch
es
th
at
tak
e
in
to
ac
c
o
u
n
t
th
e
lin
k
s
b
etwe
en
d
if
f
e
r
en
t
en
titi
es
to
b
e
p
er
f
o
r
m
ed
m
o
r
e
ea
s
ily
.
I
n
th
e
p
ast
d
ec
ad
e,
L
DR
tech
n
o
lo
g
y
h
as
b
ee
n
in
v
esti
g
ated
b
y
u
s
in
g
d
if
f
er
e
n
t
in
f
o
r
m
atio
n
p
r
o
ce
s
s
in
g
tech
n
o
lo
g
ies.
Ho
wev
er
,
as
leg
al
d
o
cu
m
e
n
ts
f
r
eq
u
en
tl
y
em
p
lo
y
r
itu
alis
tic
lan
g
u
ag
e
an
d
r
h
eto
r
ical
s
tr
u
ctu
r
es,
citatio
n
s
f
r
o
m
o
th
e
r
n
o
r
m
s
[
2
1
]
,
p
r
o
ce
s
s
in
g
th
o
s
e
d
e
p
en
d
e
n
c
ies
an
d
i
d
en
tify
in
g
th
e
ex
ac
t
i
n
f
o
r
m
atio
n
n
ee
d
b
y
f
o
cu
s
in
g
o
n
s
im
p
le
k
ey
wo
r
d
m
atch
-
b
ased
tech
n
iq
u
es
ar
e
n
o
t
f
o
u
n
d
to
b
e
ef
f
ec
ti
v
e
in
leg
al
s
ce
n
ar
io
s
[
2
2
]
.
I
n
s
tead
,
th
e
s
em
an
tic
asp
ec
t
o
f
tex
t
p
r
o
ce
s
s
in
g
p
lay
s
v
ital
r
o
le
in
an
aly
s
is
an
d
r
etr
iev
al
o
f
leg
al
d
o
cu
m
e
n
ts
.
I
n
th
is
r
eg
ar
d
,
ap
p
l
y
in
g
d
ee
p
le
ar
n
in
g
m
o
d
els
m
ay
b
e
m
o
r
e
b
en
ef
icial
o
v
er
o
th
er
tr
ad
iti
o
n
al
m
o
d
els
[
2
3
]
.
Desig
n
in
g
ef
f
icien
t
m
o
d
els
t
o
p
r
o
ce
s
s
th
e
co
m
p
lex
leg
al
tex
t
an
d
ex
tr
ac
tin
g
th
e
a
p
p
r
o
p
r
iate
in
f
o
r
m
atio
n
q
u
ick
ly
f
r
o
m
th
em
is
s
till
an
in
tr
icate
task
.
I
n
th
is
r
eg
ar
d
,
r
etr
iev
al
m
o
d
els
o
r
d
atab
ases
ar
e
av
ailab
le
f
o
r
r
etr
iev
al
o
f
E
u
r
o
p
ea
n
,
New
Z
ea
lan
d
,
UK/US
laws
an
d
c
ase
s
tu
d
ies.
Ho
wev
er
,
th
e
r
e
tr
iev
al
o
f
r
elev
a
n
t
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
1
6
,
No
.
1
,
Feb
r
u
ar
y
20
2
6
:
2
4
6
-
255
248
in
f
o
r
m
atio
n
f
r
o
m
leg
al
d
o
c
u
m
en
ts
an
d
ca
s
e
s
tu
d
ies
r
elate
d
to
d
if
f
e
r
en
t
I
n
d
ian
ca
s
e
m
atter
s
is
n
o
t
y
et
s
u
p
p
o
r
ted
b
y
s
ig
n
if
ica
n
t r
esea
r
ch
f
in
d
in
g
s
[
2
5
]
an
d
is
th
e
f
o
cu
s
o
f
th
e
wo
r
k
p
r
esen
ted
in
t
h
is
p
ap
er
.
T
h
e
m
ajo
r
c
o
n
tr
ib
u
tio
n
s
o
f
th
i
s
wo
r
k
in
clu
d
e
d
esig
n
o
f
a
d
o
cu
m
en
t
r
ep
o
s
ito
r
y
co
n
s
id
er
in
g
th
e
leg
al
ca
s
e
r
ep
o
r
ts
an
d
r
elate
d
d
o
cu
m
en
ts
b
elo
n
g
in
g
to
d
if
f
e
r
en
t
I
n
d
ian
leg
al
m
atter
s
.
W
e
p
r
esen
t
leg
al
d
o
cu
m
e
n
t
in
f
o
r
m
atio
n
r
etr
iev
al
s
y
s
tem
f
o
r
th
e
I
n
d
ian
leg
al
m
atter
s
th
a
t
d
eter
m
in
es
th
e
s
ig
n
if
ican
ce
o
f
th
e
u
s
er
en
ter
e
d
q
u
er
ies
with
r
esp
ec
tiv
e
leg
al
s
u
b
-
d
o
m
ain
s
an
d
ex
tr
ac
ts
th
e
m
o
s
t
s
u
itab
le
d
o
cu
m
en
ts
q
u
ic
k
ly
.
T
h
e
n
o
v
elty
o
f
th
e
wo
r
k
is
ap
p
ly
in
g
a
le
g
al
s
u
b
-
d
o
m
ain
class
if
icatio
n
tec
h
n
iq
u
e
to
ca
te
g
o
r
ize
th
e
q
u
er
ies
in
to
r
esp
ec
tiv
e
g
r
o
u
p
s
wh
ich
m
in
im
izes
th
e
s
ea
r
ch
s
p
ac
e
a
n
d
p
r
o
v
id
es
th
e
r
eq
u
ir
ed
r
esu
lts
q
u
ick
ly
.
T
o
s
tar
t
with
th
e
d
ev
elo
p
m
e
n
t
o
f
s
u
ch
a
m
o
d
el,
th
e
d
o
cu
m
en
t
r
e
p
o
s
ito
r
y
is
p
r
ep
ar
ed
f
ir
s
t
b
y
co
llectin
g
th
e
d
o
cu
m
en
ts
an
d
ca
s
e
s
tu
d
y
r
ep
o
r
ts
o
f
I
n
d
ian
leg
al
m
atter
s
o
f
last
f
iv
e
y
ea
r
s
.
A
s
t
h
e
leg
al
d
o
cu
m
en
ts
m
ay
b
e
ca
teg
o
r
ized
in
to
s
o
m
e
b
r
o
ad
e
r
leg
al
s
u
b
d
o
m
ain
s
,
th
e
tr
ad
itio
n
al
I
R
m
o
d
els
m
a
y
n
o
t
p
r
o
v
id
e
t
h
e
r
e
q
u
ir
ed
p
er
f
o
r
m
an
ce
.
I
n
s
tead
,
th
e
d
o
m
ain
-
b
ased
m
eth
o
d
s
m
a
y
b
e
m
o
r
e
s
u
itab
le
to
f
u
lf
ill
th
e
u
s
er
’
s
n
ee
d
s
with
r
esp
ec
t
to
t
h
e
d
o
m
ain
-
s
p
ec
if
ic
r
eq
u
ir
em
e
n
ts
.
T
h
is
m
a
y
r
ed
u
c
e
th
e
s
ea
r
c
h
s
p
ac
e
s
ig
n
if
ican
t
ly
an
d
en
h
an
ce
th
e
p
er
f
o
r
m
a
n
ce
with
r
esp
ec
t
to
r
esp
o
n
s
e
tim
e.
T
h
er
ef
o
r
e,
a
d
ee
p
n
e
u
r
al
n
etwo
r
k
(
DNN)
-
b
ased
leg
al
s
u
b
-
d
o
m
ain
ca
teg
o
r
izatio
n
m
eth
o
d
is
co
n
s
id
er
ed
in
th
is
wo
r
k
f
o
r
f
i
n
d
in
g
t
h
e
ap
p
r
o
p
r
iaten
ess
o
f
t
h
e
q
u
e
r
ies
with
r
esp
ec
t
to
th
e
co
n
s
id
er
ed
8
leg
al
s
u
b
-
d
o
m
ain
s
f
o
r
q
u
ic
k
r
etr
iev
al.
A
q
u
er
y
-
d
o
cu
m
e
n
t
r
elev
an
ce
(
QDR)
alg
o
r
ith
m
is
also
p
r
esen
ted
in
th
is
wo
r
k
to
f
u
r
th
e
r
r
an
k
th
e
o
u
tp
u
t
d
o
cu
m
en
ts
as p
er
th
eir
r
elev
a
n
ce
.
T
h
e
p
er
f
o
r
m
a
n
ce
o
f
th
e
p
r
esen
ted
tech
n
iq
u
e
is
an
aly
ze
d
u
n
d
er
s
ev
e
r
al
ex
p
e
r
im
en
ts
.
T
ests
wer
e
co
n
d
u
cte
d
o
n
v
ar
ie
d
n
u
m
b
er
o
f
u
s
er
q
u
er
ies
b
el
o
n
g
in
g
to
th
e
s
u
b
d
o
m
ain
s
co
n
s
id
er
ed
a
n
d
th
e
ac
c
u
r
ac
y
a
n
d
th
e
tim
e
r
eq
u
ir
ed
f
o
r
class
if
icatio
n
ar
e
a
n
aly
ze
d
.
T
h
e
m
o
d
el
ac
h
iev
es
an
av
er
a
g
e
ac
c
u
r
ac
y
o
f
9
8
%
with
av
er
ag
e
class
if
icatio
n
tim
e
o
f
0
.
3
s
ec
o
n
d
s
.
T
h
e
DNN
-
b
ased
leg
al
s
u
b
-
d
o
m
ain
class
if
icatio
n
tech
n
iq
u
e
is
also
co
m
p
ar
ed
with
o
th
e
r
class
if
ie
r
s
s
u
ch
as
lo
g
is
tic
r
eg
r
ess
io
n
(
L
R
)
,
r
an
d
o
m
f
o
r
est
(
R
F),
k
-
n
ea
r
est
n
eig
h
b
o
r
s
(
KNN)
,
an
d
XGBo
o
s
t
(
XGB)
class
if
ier
s
tr
ain
ed
in
th
e
s
am
e
en
v
ir
o
n
m
en
t.
T
h
e
r
esu
lts
in
d
i
ca
te
th
e
s
tr
en
g
th
o
f
th
e
p
r
esen
ted
tech
n
iq
u
e
i
n
r
e
lev
an
t
leg
al
d
o
c
u
m
en
t
r
etr
iev
al.
T
h
e
p
r
esen
te
d
I
R
s
y
s
tem
’
s
p
er
f
o
r
m
a
n
ce
f
o
r
I
n
d
ian
leg
al
d
o
m
ain
is
also
ass
ess
ed
o
v
er
th
e
two
r
etr
iev
al
m
o
d
els:
B
o
o
lean
r
etr
iev
al
m
o
d
e
l
(
B
M)
[
8
]
,
an
d
th
e
f
u
zz
y
clu
s
ter
in
g
-
b
ased
s
em
a
n
tic
r
etr
iev
al
(
FC
SR
)
m
o
d
el
[
1
0
]
.
T
h
e
p
r
esen
te
d
m
o
d
el
ac
h
i
ev
es
1
3
%
an
d
1
2
%
av
er
ag
e
in
cr
ea
s
ed
r
esu
lts
f
o
r
p
r
ec
is
io
n
an
d
r
ec
all
s
co
r
es
r
esp
ec
tiv
ely
o
v
er
t
h
e
two
m
o
d
els
s
h
o
win
g
th
e
ef
f
ec
tiv
en
ess
o
f
th
e
p
r
esen
ted
tech
n
iq
u
es.
T
h
e
r
em
in
d
er
o
f
th
e
p
ap
e
r
is
o
r
g
an
ized
as
f
o
ll
o
ws.
T
h
e
p
r
o
p
o
s
ed
m
o
d
el
f
o
r
le
g
al
d
o
cu
m
e
n
t
I
R
is
d
is
cu
s
s
ed
in
d
etail
in
s
ec
tio
n
2
.
T
h
e
d
etails
o
f
th
e
p
er
f
o
r
m
an
ce
an
al
y
s
is
an
d
r
esu
lts
ar
e
ex
p
lain
ed
in
s
ec
tio
n
3
.
Sectio
n
4
s
u
m
m
ar
izes
th
e
r
esear
ch
f
in
d
i
n
g
s
with
a
d
is
c
u
s
s
io
n
o
n
th
e
s
co
p
e
o
f
f
u
tu
r
e
r
esear
ch
in
th
is
wo
r
k
.
2.
L
E
G
A
L
DO
CU
M
E
N
T
R
E
T
RIE
V
AL
M
O
DE
L
T
h
is
s
ec
tio
n
p
r
esen
ts
a
d
etail
ed
ex
p
lan
atio
n
o
n
th
e
d
o
m
ai
n
class
if
icatio
n
-
b
ased
le
g
al
i
n
f
o
r
m
atio
n
r
etr
iev
al
s
y
s
tem
(
DC
L
I
R
S)
f
o
r
I
n
d
ian
ca
s
e
d
o
cu
m
en
ts
.
As
l
ik
e
d
ev
el
o
p
m
en
t
o
f
an
y
o
th
e
r
s
tan
d
ar
d
I
R
m
o
d
el
f
o
r
d
o
cu
m
e
n
t
r
etr
iev
al
,
o
u
r
m
o
d
el
also
co
n
s
id
er
s
th
e
3
m
ajo
r
p
h
ases
in
t
h
e
d
o
cu
m
en
t
r
etr
i
ev
al
p
r
o
c
ess
.
T
h
o
s
e
p
h
ases
in
clu
d
e:
d
o
cu
m
e
n
t
r
e
p
o
s
ito
r
y
cr
ea
tio
n
,
q
u
er
y
p
r
o
c
ess
in
g
,
an
d
d
o
cu
m
en
t
r
etr
iev
al
an
d
r
an
k
i
n
g
.
T
h
e
d
o
cu
m
e
n
t
r
e
p
o
s
ito
r
y
cr
ea
tio
n
p
h
ase
f
o
cu
s
es
o
n
c
o
llectin
g
th
e
d
o
cu
m
en
ts
wh
ich
ar
e
u
s
ed
in
th
e
r
etr
iev
al
p
r
o
ce
s
s
f
o
llo
wed
b
y
an
in
d
e
x
ed
m
ec
h
an
is
m
.
I
n
th
is
wo
r
k
,
th
e
leg
al
d
o
cu
m
e
n
ts
an
d
r
ep
o
r
ts
ar
e
co
llected
to
cr
ea
te
a
leg
al
d
o
cu
m
en
t r
ep
o
s
ito
r
y
an
d
th
e
d
o
cu
m
en
ts
ar
e
ca
t
eg
o
r
ized
with
r
esp
ec
t to
th
eir
leg
al
s
u
b
-
d
o
m
ain
s
.
T
h
e
m
eth
o
d
o
lo
g
y
u
s
ed
f
o
r
r
e
p
o
s
ito
r
y
cr
ea
tio
n
f
o
r
th
e
I
n
d
ian
leg
al
d
o
cu
m
en
ts
is
d
is
cu
s
s
ed
in
s
ec
tio
n
2
.
1
.
T
h
e
u
s
er
q
u
e
r
y
p
r
o
ce
s
s
in
g
p
h
ase
p
r
o
ce
s
s
es
th
e
q
u
er
ies
en
ter
e
d
b
y
th
e
u
s
er
to
n
o
r
m
alize
th
e
tex
t
an
d
o
b
tain
th
e
k
ey
wo
r
d
s
wh
ich
ar
e
u
s
ed
in
th
e
r
etr
iev
al
p
r
o
ce
s
s
.
T
h
e
d
etai
ls
o
f
th
e
q
u
er
y
p
r
o
ce
s
s
in
g
tec
h
n
iq
u
es
u
s
ed
in
th
is
wo
r
k
as d
is
cu
s
s
ed
in
s
ec
tio
n
2
.
2
.
B
a
s
ed
o
n
th
e
m
at
ch
i
n
g
o
f
t
h
e
u
s
er
q
u
er
y
k
e
y
t
er
m
s
wi
th
th
e
d
o
cu
m
en
t
k
ey
te
r
m
s
,
a
l
is
t
o
f
d
o
cu
m
en
t
s
ar
e
r
e
tr
iev
ed
th
r
o
u
g
h
th
e
d
o
cu
m
en
t
r
e
tr
iev
al
p
h
a
s
e
an
d
ar
e
r
an
k
ed
wi
th
r
e
s
p
e
c
t
to
th
e
ir
r
e
lev
an
c
e
to
th
e
u
s
er
q
u
er
ie
s
.
T
h
er
e
a
r
e
v
a
r
io
u
s
r
an
k
in
g
alg
o
r
i
th
m
s
av
a
il
ab
le
f
o
r
th
e
s
am
e
.
Ho
w
ev
er
,
we
h
av
e
p
r
e
s
en
ted
a
q
u
e
r
y
d
o
cu
m
en
t
r
el
ev
an
ce
s
co
r
e
-
b
a
s
e
d
alg
o
r
i
t
h
m
th
a
t
m
ay
b
e
tt
er
f
u
n
c
tio
n
in
th
e
co
n
s
id
er
ed
leg
a
l
d
o
cu
m
en
t
r
e
tr
iev
a
l
m
o
d
el.
T
h
e
d
e
ta
il
s
o
f
th
e
d
o
cu
m
e
n
t
r
etr
iev
al
ap
p
r
o
ac
h
an
d
th
e
r
an
k
in
g
a
lg
o
r
ith
m
u
s
ed
ar
e
p
r
e
s
en
ted
in
s
ec
t
io
n
2
.
4
.
I
n
ad
d
it
io
n
to
th
o
s
e,
w
e
h
av
e
in
cl
u
d
ed
a
q
u
er
y
d
o
m
ain
cla
s
s
if
i
ca
tio
n
p
h
a
s
e
to
wo
r
k
af
t
er
th
e
q
u
e
r
y
p
r
o
ce
s
s
in
g
p
h
a
s
e.
T
h
e
n
o
v
e
lty
o
f
t
h
i
s
w
o
r
k
i
s
to
c
la
s
s
if
y
th
e
q
u
er
i
es
to
ap
p
r
o
p
r
i
at
e
leg
a
l
s
u
b
d
o
m
ain
s
.
T
h
is
r
e
s
u
lt
ed
in
s
e
ar
c
h
in
g
f
o
r
o
n
ly
th
o
s
e
d
o
cu
m
en
t
s
th
a
t
b
e
lo
n
g
t
o
th
e
s
a
m
e
d
o
m
ain
r
el
at
ed
to
th
e
q
u
er
y
in
s
te
ad
o
f
s
ea
r
ch
in
g
f
o
r
th
e
en
t
ir
e
d
o
c
u
m
en
t
r
ep
o
s
i
to
r
y
.
T
h
e
d
e
ta
il
s
o
f
th
e
leg
al
q
u
er
y
s
u
b
-
d
o
m
a
in
cl
as
s
if
ica
t
io
n
p
h
as
e
u
s
ed
ar
e
d
i
s
cu
s
s
ed
in
s
ec
tio
n
2
.
3
.
T
h
e
in
p
u
t
p
r
o
v
id
ed
to
th
e
m
o
d
el
is
th
e
u
s
e
r
q
u
e
r
i
es
o
n
v
ar
i
ed
leg
al
t
o
p
ic
s
an
d
af
t
er
p
r
o
ce
s
s
in
g
th
r
o
u
g
h
v
ar
io
u
s
p
h
a
s
e
s
it
p
r
e
s
en
ts
a
r
an
k
ed
li
s
t
o
f
r
el
at
ed
d
o
cu
m
e
n
t
s
a
s
th
e
o
u
tp
u
t.
T
h
e
p
r
o
p
o
s
ed
leg
al
d
o
cu
m
en
t
r
e
tr
iev
a
l
s
y
s
te
m
f
o
r
th
e
I
n
d
ian
d
o
cu
m
en
t
s
is
s
h
o
wn
in
Fig
u
r
e
1
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
A
n
in
fo
r
ma
tio
n
r
etri
ev
a
l sys
t
em
fo
r
I
n
d
ia
n
le
g
a
l d
o
cu
men
ts
(
R
a
s
mi
R
a
n
i D
h
a
l
a
)
249
Fig
u
r
e1
.
Ov
er
v
iew
o
f
t
h
e
leg
a
l I
R
m
o
d
el
2
.
1
.
Repo
s
it
o
ry
c
re
a
t
io
n
At
th
e
in
itial
p
h
ase
o
f
th
e
im
p
lem
en
tatio
n
o
f
th
e
m
o
d
e
l,
a
s
et
o
f
8
0
0
leg
al
d
o
cu
m
en
ts
wer
e
co
n
s
id
er
ed
co
v
e
r
in
g
8
leg
al
s
u
b
d
o
m
ain
s
s
u
ch
as:
cr
im
in
al,
f
am
ily
,
civ
il,
co
r
p
o
r
ate,
in
tellectu
al
p
r
o
p
er
t
y
,
tax
,
en
v
ir
o
n
m
en
tal
an
d
lab
o
r
.
T
h
o
s
e
d
o
cu
m
en
ts
wer
e
co
llected
f
r
o
m
d
i
f
f
er
en
t
in
te
r
n
et
s
o
u
r
ce
s
av
ailab
le
o
v
er
th
e
web
co
v
er
in
g
d
if
f
e
r
en
t
p
u
b
licly
av
ailab
le
leg
al
r
ep
o
r
ts
an
d
d
o
cu
m
e
n
ts
in
th
e
y
ea
r
r
an
g
e
o
f
2
0
2
0
-
2
0
2
4
.
T
h
e
co
llected
d
o
cu
m
en
ts
wer
e
g
r
o
u
p
ed
in
to
th
e
co
n
s
id
er
e
d
s
u
b
-
d
o
m
ain
s
b
y
r
ef
er
r
in
g
to
th
e
w
o
r
d
s
p
r
esen
t
in
th
e
d
o
cu
m
e
n
t
titl
e
an
d
th
e
d
o
m
ain
o
f
th
e
d
o
cu
m
e
n
ts
.
Fo
r
th
is
m
an
u
al
g
r
o
u
p
in
g
p
r
o
ce
s
s
,
leg
al
ex
p
er
t’
s
co
n
s
u
ltatio
n
h
as
b
ee
n
tak
en
.
An
in
v
er
te
d
d
o
cu
m
e
n
t
lis
t
is
th
en
cr
ea
te
d
f
o
r
t
h
e
s
am
e.
T
h
e
co
n
ten
ts
o
f
t
h
e
f
ile
in
clu
d
e:
th
e
d
o
cu
m
e
n
t
I
Ds
,
th
e
y
ea
r
o
f
p
u
b
licatio
n
o
f
th
e
ar
ticle,
th
e
s
et
o
f
ass
o
ciate
d
k
ey
wo
r
d
s
,
an
d
th
e
r
esp
ec
tiv
e
leg
al
s
u
b
-
d
o
m
ain
lab
els.
T
h
e
ass
o
ciate
d
k
e
y
wo
r
d
s
s
et
f
o
r
ea
c
h
d
o
cu
m
e
n
t
is
p
r
e
p
ar
ed
b
y
co
n
s
id
er
in
g
th
e
k
ey
w
o
r
d
s
p
r
e
s
en
t
in
th
e
titl
e
o
f
th
e
d
o
cu
m
en
t
alo
n
g
with
th
e
r
elate
d
o
th
er
d
o
m
ain
s
p
ec
if
ic
in
f
o
r
m
atio
n
ass
o
ciate
d
with
th
e
d
o
cu
m
e
n
ts
.
T
h
e
d
esig
n
e
d
in
v
er
ted
f
ile
is
co
n
s
id
er
ed
f
o
r
r
etr
ie
v
in
g
th
e
d
o
cu
m
e
n
ts
o
n
u
s
er
e
n
ter
ed
q
u
er
ies.
2
.
2
.
Q
uery
p
ro
ce
s
s
ing
I
n
th
is
p
h
ase,
th
e
in
p
u
t
q
u
er
i
es
ar
e
clea
n
ed
to
d
etec
t
th
e
k
ey
ter
m
s
to
b
e
co
n
s
id
er
ed
f
o
r
d
o
cu
m
en
t
r
etr
iev
al.
T
h
e
s
to
p
wo
r
d
s
r
em
o
v
al
an
d
lem
m
atiza
tio
n
tech
n
iq
u
es
wer
e
u
s
ed
f
o
r
th
is
p
u
r
p
o
s
e
to
r
em
o
v
e
th
e
u
n
wan
ted
wo
r
d
s
an
d
to
o
b
tain
th
e
r
o
o
t
w
o
r
d
s
o
f
th
e
wo
r
d
s
r
esp
ec
tiv
ely
.
T
h
is
h
elp
s
in
m
at
ch
in
g
th
e
k
ey
ter
m
with
all
m
o
r
p
h
o
lo
g
ical
v
a
r
ian
t
s
o
f
th
e
r
o
o
t
wo
r
d
to
ad
d
r
ess
all
p
o
s
s
ib
le
u
s
ag
e
o
f
a
wo
r
d
i
n
v
ar
ie
d
co
n
tex
t.
A
k
ey
wo
r
d
ex
p
an
s
io
n
p
r
o
c
ess
is
th
en
a
p
p
lied
t
o
a
d
d
a
s
et
o
f
s
im
ilar
ter
m
s
f
o
r
p
r
ef
er
ab
le
r
etr
iev
al
o
f
t
h
e
d
o
cu
m
e
n
ts
.
Fo
r
th
is
p
u
r
p
o
s
e,
th
e
s
en
s
es
o
f
th
e
wo
r
d
s
in
t
h
e
d
ictio
n
ar
y
ar
e
c
o
n
s
id
er
ed
,
an
d
th
e
s
y
n
o
n
y
m
s
ar
e
co
n
s
id
er
ed
b
y
u
s
in
g
th
e
W
o
r
d
Net
[
8
]
.
T
h
e
u
s
e
o
f
W
o
r
d
Net
allo
ws
ex
p
an
s
io
n
o
f
th
e
in
p
u
t q
u
er
y
ter
m
s
in
to
all
p
o
s
s
ib
le
r
elate
d
wo
r
d
s
h
elp
i
n
g
in
r
etr
iev
al
o
f
m
o
r
e
d
o
c
u
m
en
ts
f
r
o
m
th
e
co
llectio
n
.
Fo
r
ea
c
h
q
u
er
y
q
i
,
a
q
u
e
r
y
k
ey
ter
m
s
et
is
p
r
ep
ar
ed
th
at
i
n
clu
d
es
th
e
f
i
n
al
k
ey
ter
m
s
{
t
1
,
t
2
,
….
t
p
}
in
clu
d
in
g
th
e
r
o
o
t
wo
r
d
s
o
f
t
h
e
q
u
er
y
wo
r
d
s
.
T
h
e
p
r
ep
a
r
ed
k
ey
w
o
r
d
s
et
is
p
r
o
v
id
ed
to
th
e
leg
al
s
u
b
-
d
o
m
ain
class
if
icatio
n
p
h
ase
f
o
r
f
u
r
th
e
r
p
r
o
ce
s
s
in
g
.
T
h
e
d
etail
o
f
th
e
leg
al
s
u
b
-
d
o
m
ain
class
if
icatio
n
p
h
ase
is
p
r
esen
ted
in
s
ec
tio
n
2
.
3
.
2
.
3
.
DNN
-
ba
s
ed
leg
a
l query
do
m
a
in cla
s
s
if
ica
t
io
n
Fo
r
ev
er
y
u
s
er
en
ter
ed
wo
r
d
s
eq
u
en
ce
s
,
th
e
d
o
m
ain
class
if
icatio
n
m
o
d
el
co
n
s
id
er
s
th
e
k
ey
wo
r
d
s
f
r
o
m
th
e
q
u
er
y
p
r
o
ce
s
s
in
g
s
tep
an
d
ca
te
g
o
r
izes
th
e
q
u
er
y
to
ap
p
r
o
p
r
iate
leg
al
s
u
b
-
d
o
m
ai
n
s
.
Fo
r
th
is
p
u
r
p
o
s
e,
a
DNN
b
ased
m
o
d
el
is
co
n
s
id
er
ed
[
2
4
]
.
T
o
tr
ain
th
e
m
o
d
el
to
id
en
tify
d
if
f
e
r
en
t
leg
al
s
u
b
-
d
o
m
ain
s
,
a
d
ataset
is
cr
ea
ted
co
llectin
g
p
o
s
s
ib
le
u
s
er
q
u
er
ies
f
r
o
m
d
i
f
f
er
en
t
in
t
er
n
et
s
o
u
r
ce
s
av
ailab
le
o
v
er
th
e
web
.
A
co
llectio
n
o
f
4
3
5
8
q
u
er
ies
with
ass
o
ciate
d
d
o
m
ain
lab
els
ar
e
p
r
e
p
ar
ed
co
v
er
in
g
th
e
co
n
s
id
er
ed
8
le
g
a
l
s
u
b
d
o
m
ain
s
.
T
h
e
q
u
er
ies
co
n
s
id
er
ed
f
o
r
th
e
d
o
m
ain
class
if
icatio
n
task
co
v
er
th
e
8
d
o
m
ain
s
alm
o
s
t
in
e
q
u
al
p
r
o
p
o
r
tio
n
.
T
h
e
d
o
m
ain
-
wis
e
d
is
tr
ib
u
tio
n
o
f
t
h
e
p
r
e
p
ar
ed
d
ata
s
et
an
d
th
e
tr
ain
in
g
an
d
test
in
g
p
r
o
p
o
r
ti
o
n
s
co
n
s
id
er
e
d
a
r
e
s
h
o
wn
in
Fig
u
r
e
2
.
Du
r
i
n
g
p
r
ep
ar
atio
n
o
f
th
e
s
am
p
le
d
ata
f
o
r
th
e
m
o
d
el,
it
is
ass
u
m
ed
th
at
an
y
u
s
er
en
te
r
ed
q
u
er
y
m
ay
b
e
r
elate
d
to
at
m
o
s
t
3
d
o
m
ain
class
es.
T
h
er
ef
o
r
e,
th
e
co
n
s
id
er
ed
p
r
o
b
lem
is
a
m
u
lti
-
class
lab
el
class
if
icatio
n
p
r
o
b
lem
with
m
ax
im
u
m
3
class
lab
els
f
o
r
ea
ch
q
u
er
y
.
Ap
p
r
o
x
im
ately
5
2
%
o
f
th
e
p
r
ep
ar
ed
d
ataset
ar
e
r
elate
d
to
a
s
in
g
le
d
o
m
ain
an
d
4
8
%
ar
e
to
th
e
m
u
ltip
le
d
o
m
ain
g
r
o
u
p
s
.
T
h
e
d
e
ep
n
eu
r
al
n
etwo
r
k
(
DNN)
b
ased
class
if
ier
is
tr
ai
n
ed
o
n
8
0
%
o
f
th
e
p
r
ep
ar
e
d
d
ata
s
et
o
n
th
e
co
n
s
id
er
ed
8
d
o
m
ain
s
.
T
h
e
m
o
d
el
is
th
en
ap
p
lied
to
p
r
ed
ict
th
e
c
ateg
o
r
y
o
f
a
n
y
n
ew
q
u
e
r
y
.
Fo
r
t
h
is
p
u
r
p
o
s
e,
th
e
r
em
ai
n
in
g
2
0
%
o
f
th
e
d
ata
s
et
is
co
n
s
id
er
ed
a
n
d
th
e
r
esu
lts
ar
e
an
aly
ze
d
.
T
h
e
T
F
-
I
DF
(
ter
m
f
r
eq
u
e
n
c
ies
(
T
F)
an
d
in
v
er
s
e
d
o
cu
m
en
t
f
r
eq
u
en
cies
(
I
DF)
)
s
co
r
e
s
[
2
5
]
is
co
n
s
id
er
ed
f
o
r
f
ea
tu
r
e
v
ec
to
r
cr
ea
tio
n
o
f
t
h
e
m
o
d
el.
Fo
r
an
y
q
u
e
r
y
q
,
th
e
T
F
-
I
DF
o
f
an
y
ter
m
t
in
q
is
esti
m
ated
b
y
u
s
in
g
th
e
f
o
r
m
u
l
as
g
iv
en
in
(
1
)
,
(
2
)
a
n
d
(
3
)
.
T
h
e
n
u
m
b
er
o
f
k
ey
wo
r
d
s
co
n
s
id
er
ed
f
o
r
th
e
wo
r
d
r
ep
r
esen
tatio
n
r
a
n
g
es
b
etwe
e
n
1
to
1
0
an
d
a
ze
r
o
-
f
i
lli
n
g
a
p
p
r
o
a
c
h
is
a
d
o
p
te
d
f
o
r
t
h
e
f
ea
tu
r
e
v
al
u
e
wit
h
less
th
a
n
1
0
k
e
y
te
r
m
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
1
6
,
No
.
1
,
Feb
r
u
ar
y
20
2
6
:
2
4
6
-
255
250
−
(
)
=
(
,
)
∗
(
1
)
(
,
)
=
ℎ
ℎ
(
2
)
(
)
=
l
og
2
(
ℎ
)
(
3
)
T
h
e
tr
ai
n
i
n
g
ex
am
p
le
(X
i
,
Y
i
)
f
o
r
i
=
1
t
o
3
4
8
8
is
p
r
o
v
i
d
e
d
a
s
t
h
e
i
n
p
u
t
to
t
h
e
m
o
d
el
.
T
h
e
v
e
ct
o
r
X
i
is
th
e
f
e
at
u
r
e
v
al
u
e
o
f
m
a
x
im
u
m
s
iz
e
1
0
a
n
d
Y
i
v
e
ct
o
r
r
ep
r
ese
n
ts
t
h
e
co
n
s
i
d
e
r
ed
8
l
eg
al
s
u
b
-
d
o
m
ai
n
s
.
T
h
e
d
o
m
ai
n
m
a
p
p
i
n
g
o
f
al
l
t
h
e
k
e
y
w
o
r
d
s
is
p
er
f
o
r
m
e
d
b
y
b
in
a
r
y
v
a
l
u
e
f
i
lli
n
g
t
ec
h
n
i
q
u
e,
wh
e
r
e
1
i
n
d
ic
ates
b
el
o
n
g
i
n
g
n
ess
a
n
d
0
i
n
d
i
ca
t
es
n
o
t
r
el
e
v
a
n
t
.
I
f
a
n
y
q
u
er
y
i
is
r
e
lat
ed
to
th
e
f
ir
s
t
a
n
d
f
i
f
t
h
l
ab
el
,
t
h
e
co
r
r
es
p
o
n
d
i
n
g
r
ep
r
ese
n
ta
ti
o
n
f
o
r
t
h
e
s
am
e
c
o
n
s
i
d
e
r
e
d
is
:
Y
i
=
[
1
,
0
,
0
,
0
,
1
,
0
,
0
,
0
]
.
T
h
e
n
u
m
b
e
r
o
f
o
u
t
p
u
t
class
es
is
i
n
d
ic
ate
d
as
n
o
d
es
in
t
h
e
o
u
t
p
u
t
la
y
e
r
.
T
h
e
“
S
i
g
mo
i
d
”
ac
ti
v
at
io
n
f
u
n
c
ti
o
n
is
co
n
s
i
d
e
r
e
d
a
n
d
t
h
e
tr
a
in
e
d
m
o
d
el
is
f
i
tte
d
wi
th
th
e
b
i
n
ar
y
c
r
o
s
s
-
e
n
tr
o
p
y
l
o
s
s
f
u
n
ct
io
n
.
T
h
e
in
p
u
t
l
ay
e
r
u
s
es
t
h
e
Re
LU
ac
t
iv
ati
o
n
f
u
n
cti
o
n
.
T
h
e
d
et
ail
e
d
n
e
tw
o
r
k
a
r
c
h
it
ec
t
u
r
e
is
s
h
o
w
n
i
n
F
ig
u
r
e
3
.
Fig
u
r
e
2
.
Do
m
a
in
-
w
is
e
d
is
tr
i
b
u
ti
o
n
o
f
d
ata
s
et
Fig
u
r
e
3
.
Net
wo
r
k
ar
c
h
it
ec
t
u
r
e
o
f
DNN
2
.
4
.
Do
cu
m
ent
re
t
riev
a
l a
nd
ra
nk
ing
As
p
er
th
e
d
o
m
a
in
cl
ass
es
o
b
t
ain
e
d
i
n
t
h
e
DNN
-
b
ase
d
d
o
m
ain
cl
ass
i
f
ic
ati
o
n
t
ec
h
n
iq
u
e,
th
e
w
o
r
d
s
i
n
th
e
q
u
e
r
y
a
r
e
m
a
tc
h
e
d
w
it
h
t
h
e
d
o
c
u
m
e
n
t
i
n
v
e
r
t
ed
f
i
le
co
n
t
e
n
ts
b
el
o
n
g
i
n
g
t
o
s
a
m
e
d
o
m
ai
n
s
.
L
et
Q
d
e
n
o
t
e
t
h
e
p
o
s
s
ib
le
q
u
e
r
i
es
{
q
1
,
q
2
,
…
,
q
n
}
a
n
d
D
r
e
p
r
ese
n
ts
a
d
o
cu
m
e
n
t
c
o
r
p
u
s
c
o
n
t
ai
n
i
n
g
l
eg
al
ar
t
icl
es
(
i
.
e
.
,
D
={
d
1
,d
2
,
…,
d
r
})
.
T
h
e
o
b
jec
ti
v
e
is
t
o
f
et
ch
a
s
u
b
s
et
D’
⊆
D
,
wh
e
r
e
ea
c
h
d
i
∈
D’
is
r
ele
v
an
t
to
t
h
e
a
n
y
q
u
er
y
∈
Q
.
T
h
e
r
ep
o
r
ts
f
et
ch
ed
b
y
th
e
m
o
d
el
a
r
e
t
h
e
n
r
a
n
k
ed
u
s
i
n
g
a
q
u
er
y
-
d
o
cu
m
en
t
r
e
le
v
a
n
c
e
(
QDR)
s
c
o
r
e
-
b
ase
d
tec
h
n
i
q
u
e
as
p
r
es
en
te
d
i
n
A
lg
o
r
it
h
m
(
1
)
.
I
n
t
h
e
al
g
o
r
it
h
m
,
μ
(
d
i
)
is
t
h
e
f
u
n
cti
o
n
w
h
ic
h
esti
m
a
tes
t
h
e
s
ig
n
i
f
ic
a
n
ce
o
f
d
i
to
q
i
f
o
r
i=
1
,
2
,
…
.
,
m
,
wh
e
r
e
m
is
t
h
e
to
tal
n
u
m
b
e
r
o
f
d
o
cu
m
e
n
ts
r
e
tr
ie
v
e
d
.
T
h
e
d
o
c
u
m
e
n
t d
m
wit
h
m
a
x
i
m
u
m
r
el
ev
a
n
ce
s
c
o
r
e
(
MR
S
)
is
o
b
t
ai
n
e
d
as
p
er
q
u
e
r
y
t
er
m
s
a
n
d
d
o
c
u
m
e
n
t
te
r
m
m
atc
h
i
n
g
r
es
u
l
ts
a
n
d
ass
ig
n
ed
wit
h
a
m
e
m
b
e
r
s
h
ip
v
alu
e
o
f
1
i
n
d
ic
ati
n
g
t
h
e
m
o
s
t
r
ele
v
a
n
t
d
o
c
u
m
e
n
t
as
p
er
t
h
e
c
o
n
s
id
e
r
e
d
q
u
er
y
.
All
o
t
h
e
r
d
o
c
u
m
e
n
ts
i
n
D’
ar
e
ass
i
g
n
e
d
wit
h
a
v
al
u
e
b
et
we
en
[0
-
1
]
b
y
t
h
e
m
em
b
er
s
h
i
p
f
u
n
c
ti
o
n
μ
(
d
i
)
co
n
s
i
d
er
i
n
g
th
e
n
u
m
b
e
r
o
f
k
e
y
w
o
r
d
m
a
tc
h
s
co
r
es.
Af
te
r
o
b
tai
n
i
n
g
th
e
s
c
o
r
es
f
o
r
all
d
o
cu
m
e
n
ts
i
n
D’
,
t
h
e
r
ele
v
a
n
ce
s
c
o
r
e
s
et
S
is
u
s
ed
a
n
d
th
e
r
etr
ie
v
e
d
d
o
c
u
m
en
ts
ar
e
r
e
o
r
d
e
r
e
d
a
n
d
p
r
es
en
te
d
as
th
e
o
u
t
p
u
t
o
f
th
e
m
o
d
el
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
A
n
in
fo
r
ma
tio
n
r
etri
ev
a
l sys
t
em
fo
r
I
n
d
ia
n
le
g
a
l d
o
cu
men
ts
(
R
a
s
mi
R
a
n
i D
h
a
l
a
)
251
Alg
o
r
it
h
m
1
.
QDR
s
c
o
r
e
-
b
ase
d
r
a
n
k
i
n
g
Step
-
1: Estimate the relevant score set
S
= {(
d
i
, μ(d
i
)} for
D’
on query
q
j
Step
-
2: Obtain d
m
with
MRS f
or each document in
D’
Step
-
3:
As
si
gn
a
va
lu
e
o
f
1
to
th
e
d
m
an
d
a
va
lu
e
be
tw
ee
n
[0
-
1]
to
ot
he
r
do
cu
me
nt
s
in
D’
as per the number of keywords match scores by using the function
μ(d
i
).
Step
-
4: Use the values obtained in
S
for ranking the of output documents.
Step
-
5:
If
th
e
sc
or
e
ob
ta
in
ed
on
an
y
do
cu
me
nt
d
i
i
n
D’
is
sa
me
as
an
y
ot
he
r
do
cu
me
nt
d
j
in
D’
,
apply reordering of the list considering the recent reports first mechanism.
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
T
h
e
DC
L
I
R
S
p
r
esen
ted
in
th
is
p
ap
er
is
im
p
lem
en
ted
u
n
d
er
p
y
th
o
n
en
v
ir
o
n
m
en
t
with
th
e
u
s
e
o
f
n
atu
r
al
lan
g
u
ag
e
to
o
lk
it
(
N
L
T
K)
to
o
l
f
o
r
tex
t
p
r
ep
r
o
ce
s
s
in
g
.
T
h
e
p
er
f
o
r
m
an
ce
o
f
t
h
e
p
r
esen
ted
le
g
al
d
o
cu
m
e
n
t
r
etr
iev
al
s
y
s
tem
is
ass
e
s
s
ed
th
r
o
u
g
h
f
o
u
r
p
h
as
es
o
f
ex
p
er
im
en
ts
.
I
n
th
e
f
ir
s
t
p
h
ase
o
f
r
esu
lt
an
aly
s
is
,
th
e
leg
al
s
u
b
-
d
o
m
ain
class
if
icatio
n
m
o
d
el
is
test
ed
to
ass
ess
its
p
er
f
o
r
m
an
ce
in
a
p
p
r
o
p
r
iate
d
o
m
ain
class
if
icatio
n
.
Fo
r
th
is
p
u
r
p
o
s
e,
2
0
%
o
f
t
h
e
r
e
m
ain
in
g
d
ata
s
et
f
r
o
m
t
h
e
p
r
ep
ar
e
d
d
ata
s
et
is
co
n
s
id
er
ed
.
T
h
e
ass
es
s
m
en
t
m
etr
ics
co
n
s
id
er
e
d
ar
e
m
o
d
el
ac
cu
r
ac
y
,
p
r
ec
is
io
n
s
co
r
es
a
n
d
F1
s
co
r
e.
T
h
e
p
r
esen
ted
leg
al
s
u
b
-
d
o
m
ain
class
if
icatio
n
m
o
d
el
s
u
cc
ess
f
u
lly
class
if
ies
th
e
d
o
m
ain
s
o
f
th
e
n
ew
s
am
p
les
with
av
er
ag
e
ac
c
u
r
ac
y
o
f
9
8
.
3
7
%
an
d
p
r
ec
is
io
n
s
co
r
e
an
d
F1
s
co
r
e
o
f
0
.
9
8
.
Du
e
to
th
e
d
is
tin
ctiv
e
ch
ar
ac
ter
is
tics
o
f
th
e
leg
al
d
o
cu
m
e
n
ts
,
p
r
esen
ce
o
f
in
f
o
r
m
atio
n
in
a
b
s
tr
ac
t,
f
o
r
m
al
o
r
in
a
ju
d
icial
lan
g
u
ag
e,
av
ail
ab
ilit
y
o
f
d
if
f
er
e
n
t
q
u
o
tatio
n
s
f
r
o
m
o
th
er
ju
d
g
m
e
n
ts
,
leg
is
lativ
e
r
ef
er
en
ce
s
an
d
p
r
esen
ce
o
f
lar
g
e
n
ar
r
ativ
e
p
ar
ts
,
th
e
leg
al
d
ata
ar
e
co
n
s
id
er
ed
to
b
e
v
er
y
co
m
p
lex
p
atter
n
s
in
d
esig
n
in
g
a
n
y
tex
t
p
r
o
ce
s
s
in
g
ap
p
licatio
n
s
.
As
th
e
DNN
-
b
ased
m
o
d
els
ca
n
au
t
o
m
atica
lly
lear
n
co
m
p
le
x
f
ea
tu
r
es
f
r
o
m
r
aw
d
ata
an
d
ca
n
d
ea
l
with
lar
g
e
a
n
d
co
m
p
lex
d
atasets
also
,
th
er
ef
o
r
e,
th
e
p
r
esen
ted
leg
al
d
o
m
ain
class
if
icatio
n
tech
n
iq
u
e
is
co
n
s
id
er
ed
to
b
e
m
o
r
e
ef
f
ec
ti
v
e
in
t
h
e
leg
al
d
o
cu
m
e
n
ts
ad
d
r
ess
in
g
a
v
ar
iety
o
f
f
o
r
m
s
.
I
n
th
e
s
ec
o
n
d
ex
p
e
r
im
en
tal
p
h
ase,
th
e
leg
al
d
o
m
ai
n
class
if
icatio
n
m
o
d
el
is
ev
alu
ate
d
with
o
th
er
class
if
ier
s
.
Fo
r
th
is
p
u
r
p
o
s
e,
t
h
e
lo
g
is
tic
r
eg
r
ess
io
n
(
L
R
)
,
r
an
d
o
m
f
o
r
est
(
R
F),
k
-
n
ea
r
est
n
eig
h
b
o
r
s
(
KNN)
,
an
d
XGBo
o
s
t
(
XGB)
class
if
i
er
s
[
1
6
]
a
r
e
u
s
ed
.
T
h
e
r
esu
lt
s
o
b
tain
ed
in
all
t
h
e
ex
p
e
r
im
en
ts
ar
e
s
h
o
wn
in
T
ab
le
1
i
t m
ay
b
e
o
b
s
er
v
ed
f
r
o
m
th
e
r
esu
lts
s
h
o
wn
in
Fig
u
r
e
4
th
at
th
e
DNN
-
b
ased
q
u
er
y
cl
ass
if
icatio
n
m
o
d
el
ac
h
iev
es
th
e
h
ig
h
est
ac
cu
r
ac
y
s
co
r
es,
ap
p
r
o
x
im
ately
9
8
%
in
all
th
e
co
n
s
id
er
ed
ev
alu
atio
n
p
ar
a
m
eter
s
co
m
p
ar
ed
to
th
e
o
th
er
class
if
ier
s
.
T
h
e
DNN
m
o
d
el
ac
h
ie
v
e
s
an
in
c
r
ea
s
e
in
ac
cu
r
ac
y
o
f
3
.
5
8
%
o
v
er
th
e
L
R
m
o
d
el,
1
.
9
5
%
o
v
er
th
e
R
F
m
o
d
el,
6
.
4
4
%
o
v
er
KNN
an
d
3
.
4
8
%
o
v
er
XGB
m
o
d
el.
I
n
ter
m
s
o
f
th
e
p
r
ec
is
io
n
m
ea
s
u
r
es,
th
e
DNN
m
o
d
el
ac
h
iev
es
an
in
cr
ea
s
e
o
f
3
%
o
v
e
r
th
e
L
R
m
o
d
el,
1
%
o
v
er
th
e
R
F,
4
%
o
v
er
th
e
KNN
m
o
d
el,
an
d
2
%
o
v
er
th
e
XGB
m
o
d
el.
W
h
ile
in
ter
m
s
o
f
th
e
F1
-
s
co
r
e
m
ea
s
u
r
e,
th
e
p
r
esen
ted
DNN
–
b
ased
d
o
m
ain
class
if
icatio
n
m
o
d
el
ac
h
ie
v
es
an
i
n
cr
ea
s
e
o
f
3
%
o
v
er
L
R
,
2
%
o
v
er
R
F,
6
%
o
v
er
KNN,
a
n
d
3
%
o
v
er
XGB
clas
s
if
ier
s
.
T
h
is
s
h
o
ws
th
e
p
r
esen
ted
m
o
d
el
is
b
est
f
itted
in
th
e
co
n
s
id
er
ed
d
o
m
ain
an
d
th
e
d
ata
s
et
o
v
er
t
h
e
o
t
h
er
class
if
ier
s
.
T
h
e
co
n
f
u
s
io
n
m
atr
ix
(
C
M)
f
o
r
th
e
co
n
s
id
er
ed
class
if
ier
s
is
s
h
o
wn
in
Fig
u
r
e
5
.
T
h
is
in
d
icate
s
th
e
ac
tu
al
lab
el
an
d
th
e
p
r
ed
icted
lab
els
b
y
th
e
r
esp
ec
tiv
e
m
o
d
els
in
th
e
test
s
co
n
d
u
cted
.
I
t
m
a
y
b
e
o
b
s
er
v
ed
th
at
f
o
r
all
8
c
o
n
s
i
d
er
ed
d
o
m
ain
lab
els
,
th
e
DN
N
-
b
ased
m
o
d
el
o
u
tp
er
f
o
r
m
s
t
h
e
o
th
er
m
o
d
els
in
ter
m
s
o
f
ac
cu
r
ately
p
r
ed
ictin
g
th
e
d
o
m
ain
s
o
f
th
e
u
s
er
q
u
er
ie
s
.
T
ab
le
1
.
R
esu
lt a
n
aly
s
is
o
f
D
NN
-
b
ased
class
if
ier
with
o
th
er
class
if
ier
s
Te
x
t
c
l
a
ssi
f
i
e
r
A
c
c
u
r
a
c
y
%
P
r
e
c
i
s
i
o
n
S
c
o
r
e
F
1
S
c
o
r
e
Lo
g
i
s
t
i
c
r
e
g
r
e
ssi
o
n
9
4
.
7
9
0
.
9
5
0
.
9
5
R
a
n
d
o
m
f
o
r
e
s
t
9
6
.
4
2
0
.
9
7
0
.
9
6
K
-
n
e
a
r
e
s
t
n
e
i
g
h
b
o
r
s
9
1
.
9
3
0
.
9
4
0
.
9
2
X
G
B
o
o
st
9
4
.
8
9
0
.
9
6
0
.
9
5
D
e
e
p
n
e
u
r
a
l
n
e
t
w
o
r
k
9
8
.
3
7
0
.
9
8
0
.
9
8
I
n
th
e
th
i
r
d
p
h
ase
o
f
th
e
e
x
p
er
im
e
n
ts
,
t
h
e
B
M,
a
n
d
FC
SR
m
o
d
els
[
7
]
wer
e
co
n
s
id
er
e
d
to
c
o
m
p
ar
e
t
h
e
r
esu
lts
o
f
th
e
p
r
es
en
te
d
DC
L
I
R
S.
Pre
cisi
o
n
ev
alu
atio
n
m
e
asu
r
es
an
d
r
ec
all
m
etr
ics
ar
e
co
n
s
id
er
ed
f
o
r
th
is
p
u
r
p
o
s
e.
A
to
tal
o
f
4
0
r
a
n
d
o
m
leg
al
q
u
er
ies
wer
e
co
llecte
d
f
r
o
m
d
if
f
er
e
n
t
u
s
er
s
co
v
er
i
n
g
th
e
8
co
n
s
id
er
ed
leg
al
d
o
m
ai
n
s
.
T
a
b
le
2
s
h
o
w
s
t
h
e
av
e
r
a
g
e
ac
c
u
r
a
cy
p
e
r
ce
n
ta
g
e
o
f
t
h
e
test
s
.
W
h
ile
th
e
B
M
m
o
d
el
u
s
es
th
e
tech
n
iq
u
e
o
f
p
r
esen
ce
o
r
a
b
s
en
ce
o
f
th
e
k
ey
wo
r
d
s
in
th
e
d
o
cu
m
e
n
ts
,
th
e
FC
SR
f
o
cu
s
e
s
o
n
ca
lcu
latin
g
th
e
r
elev
an
ce
s
co
r
e
f
o
r
th
e
d
o
cu
m
en
ts
to
b
elo
n
g
to
s
o
m
e
d
o
m
ain
g
r
o
u
p
s
.
Ho
wev
er
,
b
o
th
m
o
d
els
co
n
s
id
er
ed
a
d
ir
ec
t
m
atch
o
f
th
e
k
e
y
ter
m
s
an
d
ar
e
u
n
ab
le
to
ad
d
r
ess
th
e
s
y
n
o
n
y
m
o
r
an
to
n
y
m
co
n
ce
p
ts
.
T
h
e
m
o
d
el
p
r
esen
ted
ad
d
r
ess
es
th
o
s
e
is
s
u
es
r
esu
ltin
g
in
ac
h
iev
in
g
b
ette
r
r
esu
lts
in
all
th
e
test
s
co
n
d
u
cted
.
T
h
e
DC
L
I
R
S
atta
in
a
9
6
%
p
r
ec
is
i
o
n
a
n
d
9
5
%
r
ec
all
a
v
e
r
a
g
e
ac
c
u
r
a
cy
r
es
p
e
cti
v
e
ly
.
As
c
o
m
p
a
r
e
d
t
o
BM
,
t
h
e
r
e
h
as
b
ee
n
a
n
in
c
r
ea
s
e
o
f
1
5
%
an
d
1
3
%
in
p
r
ec
is
io
n
an
d
r
ec
all
m
ea
s
u
r
e
r
e
s
p
ec
tiv
ely
.
I
n
c
o
m
p
ar
is
o
n
with
th
e
FC
SR
m
o
d
el,
th
e
DC
L
I
R
S
ac
h
iev
es
an
in
cr
e
ased
p
r
ec
is
io
n
an
d
r
ec
all
m
ea
s
u
r
e
o
f
1
1
%
in
b
o
th
m
ea
s
u
r
es
.
Ov
er
all,
th
e
m
o
d
el
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
1
6
,
No
.
1
,
Feb
r
u
ar
y
20
2
6
:
2
4
6
-
255
252
ac
h
iev
es
an
av
er
a
g
e
1
3
%
in
cr
ea
s
e
in
p
r
ec
is
io
n
m
ea
s
u
r
e
an
d
1
2
%
in
cr
ea
s
e
ac
c
u
r
ac
y
in
r
ec
all
m
ea
s
u
r
e
co
m
p
ar
ed
to
th
e
two
c
o
n
s
id
er
e
d
m
o
d
els.
Fig
u
r
e
4
.
Per
f
o
r
m
an
c
e
co
m
p
ar
is
o
n
o
f
th
e
q
u
er
y
d
o
m
ain
class
if
icatio
n
tech
n
iq
u
es
Fig
u
r
e
5
.
C
M
f
o
r
th
e
d
o
m
ain
c
lass
if
icatio
n
tech
n
iq
u
es
9
4
.
7
9
%
9
6
.
4
2
%
9
1
.
9
3
%
9
4
.
8
9
%
9
8
.
3
7
%
0
.
9
5
%
0
.
9
7
%
0
.
9
4
%
0
.
9
6
%
0
.
9
8
%
0
.
9
5
%
0
.
9
6
%
0
.
9
2
%
0
.
9
5
%
0
.
9
8
%
88.
00%
90.
00%
92.
00%
94.
00%
96.
00%
98.
00%
100
.00%
L
ogi
s
t
i
c
R
e
g
r
e
s
s
i
o
n
R
a
ndom
For
e
s
t
K
-
Ne
are
s
t
Ne
i
g
h
b
or
s
XG
B
o
os
t
D
e
e
p N
e
ur
al
Ne
t
w
ork
Per
f
o
r
ma
nc
e
(%
)
C
o
ns
i
de
r
e
d
M
o
de
l
s
A
c
c
ur
ac
y
P
r
e
c
i
si
o
n
F
1
-
sc
o
r
e
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
A
n
in
fo
r
ma
tio
n
r
etri
ev
a
l sys
t
em
fo
r
I
n
d
ia
n
le
g
a
l d
o
cu
men
ts
(
R
a
s
mi
R
a
n
i D
h
a
l
a
)
253
T
ab
le
2
.
R
esu
lt a
n
aly
s
is
o
f
I
R
m
o
d
els
I
R
mo
d
e
l
P
r
e
c
i
s
i
o
n
%
R
e
c
a
l
l
%
BM
81
82
F
C
S
R
85
84
D
C
LI
R
S
96
95
I
n
th
e
f
o
u
r
t
h
ex
p
er
im
en
tal
p
h
a
s
e,
4
0
q
u
er
ies
wer
e
co
llected
r
an
d
o
m
ly
an
d
av
ailab
ilit
y
o
f
a
p
p
r
o
p
r
iate
r
elate
d
d
o
c
u
m
en
ts
in
t
h
e
r
ep
o
s
ito
r
y
ar
e
ch
ec
k
ed
m
an
u
ally
.
T
h
e
DC
L
I
R
S
is
ev
alu
ated
o
n
th
o
s
e
s
am
p
les
an
d
th
e
r
elev
an
t
d
o
cu
m
e
n
ts
wer
e
r
etr
iev
ed
b
y
th
e
m
o
d
el.
T
h
e
tim
e
o
f
s
u
b
m
is
s
io
n
o
f
th
e
q
u
er
i
es
an
d
r
etr
iev
al
o
f
ap
p
r
o
p
r
iate
d
o
cu
m
e
n
ts
ar
e
n
o
ted
an
d
ev
alu
ated
f
o
r
all
ex
p
er
im
en
ts
.
T
h
e
d
o
m
ain
-
wis
e
tim
e
in
g
ettin
g
th
e
r
esu
lts
is
s
h
o
wn
in
Fig
u
r
e
6
.
T
h
e
d
o
m
ain
-
wis
e
tim
e
esti
m
ati
o
n
s
ar
e
r
ep
r
esen
ted
in
Fig
u
r
e
6
(
a)
an
d
th
e
av
e
r
ag
e
tim
e
with
r
esp
ec
t
to
k
e
y
ter
m
s
in
q
u
er
ies
is
s
h
o
wn
in
Fig
u
r
e
6
(
b
)
.
I
t
m
ay
b
e
n
o
ticed
th
at
f
o
r
th
e
co
n
s
id
er
e
d
8
leg
al
s
u
b
d
o
m
ain
s
,
th
e
m
o
d
el
m
ain
tain
s
an
av
er
ag
e
class
if
icatio
n
tim
e
o
f
ap
p
r
o
x
im
ately
0
.
3
s
ec
o
n
d
s
.
T
h
is
m
ay
b
e
o
b
s
er
v
ed
f
o
r
m
th
e
g
r
a
p
h
th
at
th
er
e
is
a
lin
ea
r
g
r
o
wth
r
ate
o
f
tim
e
in
all
o
b
s
er
v
atio
n
s
.
(
a)
(
b
)
Fig
u
r
e
6
.
C
o
m
p
ar
is
o
n
o
f
a
v
e
r
a
g
e
ti
m
e
f
o
r
(
a)
l
eg
al
s
u
b
-
d
o
m
ai
n
s
an
d
(
b
)
n
u
m
b
er
o
f
k
e
y
w
o
r
d
s
4.
CO
NCLU
SI
O
N
I
n
th
is
wo
r
k
,
a
leg
al
d
o
c
u
m
en
t
r
etr
iev
al
s
y
s
tem
is
p
r
esen
ted
f
o
r
th
e
I
n
d
ia
n
ca
s
e
r
ep
o
r
ts
.
I
d
e
n
tific
atio
n
o
f
th
e
a
p
p
r
o
p
r
iaten
ess
o
f
th
e
u
s
er
q
u
er
ies
to
r
esp
ec
tiv
e
leg
al
s
u
b
-
d
o
m
ai
n
s
an
d
r
etr
iev
al
o
f
th
e
m
o
s
t
r
elev
an
t
d
o
cu
m
e
n
ts
q
u
ick
ly
ar
e
th
e
m
ai
n
o
b
jectiv
es a
d
d
r
ess
ed
in
th
e
p
r
esen
ted
wo
r
k
.
A
d
o
cu
m
en
t r
e
p
o
s
ito
r
y
is
cr
ea
ted
f
o
r
th
is
p
u
r
p
o
s
e
in
clu
d
in
g
8
0
0
leg
al
d
o
cu
m
en
ts
in
th
e
y
ea
r
r
an
g
e
o
f
2
0
2
0
-
2
0
2
4
co
v
er
i
n
g
8
leg
al
s
u
b
d
o
m
ain
s
.
A
d
ee
p
lear
n
in
g
b
ased
leg
al
s
u
b
-
d
o
m
ain
class
if
icatio
n
ap
p
r
o
ac
h
is
th
en
ap
p
lied
to
class
if
y
th
e
u
s
er
q
u
er
ies
to
ap
p
r
o
p
r
iate
leg
al
d
o
m
ain
s
.
A
QDR
-
s
co
r
e
alg
o
r
ith
m
is
p
r
ese
n
ted
to
r
an
k
th
e
f
etc
h
ed
d
o
cu
m
en
ts
o
n
a
n
y
u
s
er
q
u
er
y
.
Dif
f
e
r
en
t
ev
alu
atio
n
m
etr
ics
wer
e
co
n
s
id
er
ed
to
an
aly
ze
m
o
d
el
p
er
f
o
r
m
a
n
ce
an
d
a
n
u
m
b
e
r
o
f
ex
p
er
im
en
ts
wer
e
co
n
d
u
cted
.
T
h
e
p
r
esen
ted
leg
al
s
u
b
-
d
o
m
ain
class
if
icatio
n
tech
n
iq
u
e
ac
h
iev
es
an
a
v
er
ag
e
p
r
ec
is
io
n
ac
cu
r
ac
y
o
f
9
8
.
3
7
%
an
d
F1
s
co
r
e
o
f
0
.
9
8
in
ac
cu
r
ately
class
if
y
in
g
th
e
q
u
er
ies
to
r
esp
ec
tiv
e
leg
al
s
u
b
d
o
m
ain
s
.
Als
o
,
th
e
tec
h
n
iq
u
e
tak
es
ap
p
r
o
x
im
ately
0
.
3
s
ec
o
n
d
s
on
av
er
a
g
e
to
cl
ass
if
y
th
e
q
u
er
ies
co
n
tain
in
g
k
ey
ter
m
s
in
th
e
r
an
g
e
o
f
1
to
1
0
wo
r
d
s
.
T
h
e
p
r
esen
ted
DC
L
I
R
S
m
o
d
el
ac
h
iev
es
1
3
%
an
d
1
2
%
in
cr
ea
s
ed
ac
cu
r
ac
y
r
esu
lts
in
a
v
er
ag
e
f
o
r
p
r
ec
is
io
n
an
d
r
ec
all
r
esp
ec
tiv
ely
co
m
p
ar
ed
to
th
e
B
M
an
d
th
e
FC
SR
m
o
d
els.
T
h
is
en
s
u
r
es th
e
cr
e
d
i
b
ilit
y
o
f
th
e
p
r
o
p
o
s
ed
m
eth
o
d
o
lo
g
y
i
n
I
n
d
ian
leg
al
d
o
cu
m
e
n
t r
etr
iev
al
p
r
o
ce
s
s
.
T
h
er
e
ar
e
d
iv
e
r
s
e
ar
ea
s
wh
er
e
wo
r
k
in
th
is
r
esear
ch
m
ay
f
u
r
th
er
b
e
ca
r
r
ie
d
o
u
t.
T
h
e
s
em
an
tic
lev
el
p
r
o
ce
s
s
in
g
o
f
t
h
e
wo
r
d
s
p
r
esen
t
in
th
e
u
s
er
q
u
er
ies
m
ay
b
e
an
im
p
o
r
ta
n
t
asp
ec
t
to
b
e
in
cl
u
d
ed
in
t
h
e
wo
r
k
to
p
r
o
ce
s
s
th
e
co
n
tex
t
o
f
th
e
w
o
r
d
s
an
d
ac
h
iev
e
b
etter
r
esu
lts
.
T
h
is
wo
r
k
u
s
es
a
m
an
u
a
l
d
o
m
ain
lab
elin
g
tech
n
iq
u
e
to
lab
el
th
e
d
o
cu
m
e
n
ts
as
p
er
th
eir
r
elev
an
ce
to
d
if
f
er
en
t
s
u
b
d
o
m
ain
s
.
Ho
wev
e
r
,
with
in
cr
ea
s
e
in
n
u
m
b
er
o
f
d
o
cu
m
e
n
ts
an
d
th
e
av
ailab
ilit
y
o
f
d
o
cu
m
en
ts
o
f
n
ew
d
o
m
ain
s
,
d
ev
el
o
p
m
e
n
t
o
f
an
a
u
to
m
atic
lab
elin
g
tech
n
iq
u
e
m
ay
m
a
k
e
th
e
m
o
d
el
m
o
r
e
d
y
n
am
ic
a
n
d
ad
o
p
tiv
e
wh
er
e
n
ew
d
o
m
ai
n
s
an
d
d
o
cu
m
en
ts
m
ay
ea
s
ily
b
e
in
clu
d
ed
.
T
h
is
m
ay
r
esu
lt
in
d
ev
elo
p
m
en
t
o
f
a
m
o
r
e
d
y
n
a
m
ic
m
o
d
el
wh
ich
m
ay
wo
r
k
f
o
r
o
t
h
er
d
o
m
ain
s
also
im
p
r
o
v
in
g
th
e
u
s
ab
ilit
y
o
f
th
e
s
y
s
tem
o
v
er
tim
e
.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
T
h
er
e
is
n
o
f
u
n
d
i
n
g
a
g
en
cies a
s
s
o
ciate
d
with
th
is
r
esear
ch
.
0
.
1
0
.
1
5
0
.
2
0
.
2
5
0
.
3
0
.
3
5
0
.
4
0
.
4
5
0
.
5
1
2
3
4
5
6
7
8
T
i
m
e
(
i
n
se
c
)
D
o
m
ai
n
c
l
as
s
l
ab
e
l
0
0
.
0
5
0
.
1
0
.
1
5
0
.
2
0
.
2
5
0
.
3
0
.
3
5
0
.
4
0
.
4
5
0
.
5
1
2
3
4
5
6
7
8
9
10
A
v
e
r
ag
e
t
i
m
e
(
i
n
se
c
)
N
o
. o
f
k
e
y
wo
r
ds
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
1
6
,
No
.
1
,
Feb
r
u
ar
y
20
2
6
:
2
4
6
-
255
254
AUTHO
R
CO
NT
RI
B
UT
I
O
NS ST
A
T
E
M
E
N
T
T
h
is
jo
u
r
n
al
u
s
es
th
e
C
o
n
tr
ib
u
to
r
R
o
les
T
ax
o
n
o
m
y
(
C
R
ed
iT)
to
r
ec
o
g
n
ize
in
d
iv
id
u
al
au
th
o
r
co
n
tr
ib
u
tio
n
s
,
r
ed
u
ce
au
th
o
r
s
h
ip
d
is
p
u
tes,
an
d
f
ac
ilit
ate
co
llab
o
r
atio
n
.
Na
m
e
o
f
Aut
ho
r
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
R
asm
i Ran
i D
h
ala
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
A
V
S Pav
an
Ku
m
ar
✓
✓
✓
✓
✓
✓
✓
✓
So
u
m
y
a
Priy
ad
a
r
s
in
i
Pan
d
a
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
C
:
C
o
n
c
e
p
t
u
a
l
i
z
a
t
i
o
n
M
:
M
e
t
h
o
d
o
l
o
g
y
So
:
So
f
t
w
a
r
e
Va
:
Va
l
i
d
a
t
i
o
n
Fo
:
Fo
r
mal
a
n
a
l
y
s
i
s
I
:
I
n
v
e
s
t
i
g
a
t
i
o
n
R
:
R
e
so
u
r
c
e
s
D
:
D
a
t
a
C
u
r
a
t
i
o
n
O
:
W
r
i
t
i
n
g
-
O
r
i
g
i
n
a
l
D
r
a
f
t
E
:
W
r
i
t
i
n
g
-
R
e
v
i
e
w
&
E
d
i
t
i
n
g
Vi
:
Vi
su
a
l
i
z
a
t
i
o
n
Su
:
Su
p
e
r
v
i
s
i
o
n
P
:
P
r
o
j
e
c
t
a
d
mi
n
i
st
r
a
t
i
o
n
Fu
:
Fu
n
d
i
n
g
a
c
q
u
i
si
t
i
o
n
CO
NF
L
I
C
T
O
F
I
N
T
E
R
E
S
T
ST
A
T
E
M
E
NT
T
h
er
e
ar
e
n
o
co
n
f
licts
o
f
in
ter
est r
eg
ar
d
in
g
t
h
e
p
u
b
licatio
n
o
f
th
is
p
ap
er
.
DATA AV
AI
L
AB
I
L
I
T
Y
T
h
e
d
atasets
u
s
ed
f
o
r
th
is
r
esear
ch
wo
r
k
ar
e
av
ailab
le
f
r
o
m
th
e
co
r
r
esp
o
n
d
in
g
au
th
o
r
o
n
r
ea
s
o
n
ab
le
r
eq
u
ests
.
RE
F
E
R
E
NC
E
S
[
1
]
R
.
B
a
n
sal
a
n
d
S
.
C
h
a
w
l
a
,
“
D
e
si
g
n
a
n
d
d
e
v
e
l
o
p
me
n
t
o
f
se
ma
n
t
i
c
w
e
b
-
b
a
se
d
s
y
st
e
m
f
o
r
c
o
m
p
u
t
e
r
sci
e
n
c
e
d
o
mai
n
-
s
p
e
c
i
f
i
c
i
n
f
o
r
mat
i
o
n
r
e
t
r
i
e
v
a
l
,
”
Pe
rs
p
e
c
t
i
v
e
s i
n
S
c
i
e
n
c
e
,
v
o
l
.
8
,
p
p
.
3
3
0
–
3
3
3
,
2
0
1
6
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
p
i
sc.
2
0
1
6
.
0
4
.
0
6
7
.
[
2
]
H
.
K
.
A
z
a
d
a
n
d
A
.
D
e
e
p
a
k
,
“
Q
u
e
r
y
e
x
p
a
n
s
i
o
n
t
e
c
h
n
i
q
u
e
s
f
o
r
i
n
f
o
r
m
a
t
i
o
n
r
e
t
r
i
e
v
a
l
:
A
s
u
r
v
e
y
,
”
I
n
f
o
rm
a
t
i
o
n
Pro
c
e
ss
i
n
g
a
n
d
Ma
n
a
g
e
m
e
n
t
,
v
o
l
.
5
6
,
n
o
.
5
,
p
p
.
1
6
9
8
–
1
7
3
5
,
2
0
1
9
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
p
m.
2
0
1
9
.
0
5
.
0
0
9
.
[
3
]
K
.
A
.
H
a
m
b
a
r
d
e
a
n
d
H
.
P
r
o
e
n
c
a
,
“
I
n
f
o
r
mat
i
o
n
r
e
t
r
i
e
v
a
l
:
r
e
c
e
n
t
a
d
v
a
n
c
e
s
a
n
d
b
e
y
o
n
d
,
”
I
E
EE
A
c
c
e
ss
,
v
o
l
.
1
1
,
p
p
.
7
6
5
8
1
–
7
6
6
0
4
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
3
.
3
2
9
5
7
7
6
.
[
4
]
W
.
C
h
e
n
e
t
a
l
.
,
“
D
e
e
p
l
e
a
r
n
i
n
g
f
o
r
i
n
st
a
n
c
e
r
e
t
r
i
e
v
a
l
:
A
s
u
r
v
e
y
,
”
I
E
EE
T
ra
n
sa
c
t
i
o
n
s
o
n
P
a
t
t
e
rn
A
n
a
l
y
s
i
s
a
n
d
Ma
c
h
i
n
e
I
n
t
e
l
l
i
g
e
n
c
e
,
v
o
l
.
4
5
,
n
o
.
6
,
p
p
.
7
2
7
0
–
7
2
9
2
,
2
0
2
3
,
d
o
i
:
1
0
.
1
1
0
9
/
TPA
M
I
.
2
0
2
2
.
3
2
1
8
5
9
1
.
[
5
]
Y
.
Zh
u
,
E.
Y
a
n
,
a
n
d
I
.
Y
.
S
o
n
g
,
“
A
n
a
t
u
r
a
l
l
a
n
g
u
a
g
e
i
n
t
e
r
f
a
c
e
t
o
a
g
r
a
p
h
-
b
a
se
d
b
i
b
l
i
o
g
r
a
p
h
i
c
i
n
f
o
r
m
a
t
i
o
n
r
e
t
r
i
e
v
a
l
s
y
st
e
m,
”
D
a
t
a
a
n
d
K
n
o
w
l
e
d
g
e
E
n
g
i
n
e
e
r
i
n
g
,
v
o
l
.
1
1
1
,
p
p
.
7
3
–
8
9
,
2
0
1
7
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
d
a
t
a
k
.
2
0
1
7
.
0
6
.
0
0
6
.
[
6
]
M
.
La
n
,
C
.
L.
Ta
n
,
J.
S
u
,
a
n
d
Y
.
Lu
,
“
S
u
p
e
r
v
i
se
d
a
n
d
t
r
a
d
i
t
i
o
n
a
l
t
e
r
m
w
e
i
g
h
t
i
n
g
me
t
h
o
d
s
f
o
r
a
u
t
o
ma
t
i
c
t
e
x
t
c
a
t
e
g
o
r
i
z
a
t
i
o
n
,
”
I
E
EE
T
ra
n
s
a
c
t
i
o
n
s
o
n
P
a
t
t
e
r
n
A
n
a
l
y
si
s
a
n
d
Ma
c
h
i
n
e
I
n
t
e
l
l
i
g
e
n
c
e
,
v
o
l
.
3
1
,
n
o
.
4
,
p
p
.
7
2
1
–
7
3
5
,
2
0
0
9
,
d
o
i
:
1
0
.
1
1
0
9
/
TPA
M
I
.
2
0
0
8
.
1
1
0
.
[
7
]
S
.
P
.
P
a
n
d
a
a
n
d
J
.
P
.
M
o
h
a
n
t
y
,
“
A
n
i
n
st
i
t
u
t
i
o
n
a
l
st
u
d
e
n
t
p
r
o
j
e
c
t
r
e
p
o
r
t
r
e
t
r
i
e
v
a
l
s
y
s
t
e
m
u
si
n
g
d
e
e
p
n
e
u
r
a
l
n
e
t
w
o
r
k
-
b
a
s
e
d
d
o
ma
i
n
c
l
a
ss
i
f
i
c
a
t
i
o
n
t
e
c
h
n
i
q
u
e
,
”
Pro
g
r
e
ss
i
n
Art
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
,
v
o
l
.
1
4
,
n
o
.
3
,
p
p
.
3
7
1
–
3
8
5
,
2
0
2
5
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
3
7
4
8
-
0
2
5
-
0
0
3
7
1
-
2.
[
8
]
N
.
G
i
r
d
h
a
r
,
M
.
C
o
u
s
t
a
t
y
,
a
n
d
A
.
D
o
u
c
e
t
,
“
D
i
g
i
t
i
z
i
n
g
h
i
st
o
r
y
:
t
r
a
n
si
t
i
o
n
i
n
g
h
i
s
t
o
r
i
c
a
l
p
a
p
e
r
d
o
c
u
m
e
n
t
s
t
o
d
i
g
i
t
a
l
c
o
n
t
e
n
t
f
o
r
i
n
f
o
r
mat
i
o
n
r
e
t
r
i
e
v
a
l
a
n
d
mi
n
i
n
g
-
a
c
o
mp
r
e
h
e
n
si
v
e
su
r
v
e
y
,
”
I
EE
E
T
ra
n
s
a
c
t
i
o
n
s
o
n
C
o
m
p
u
t
a
t
i
o
n
a
l
S
o
c
i
a
l
S
y
st
e
m
s
,
v
o
l
.
1
1
,
n
o
.
5
,
p
p
.
6
1
5
1
–
6
1
8
0
,
2
0
2
4
,
d
o
i
:
1
0
.
1
1
0
9
/
T
C
S
S
.
2
0
2
4
.
3
3
7
8
4
1
9
.
[
9
]
H
.
W
u
e
t
a
l
.
,
“
R
e
su
l
t
d
i
v
e
r
s
i
f
i
c
a
t
i
o
n
i
n
s
e
a
r
c
h
a
n
d
r
e
c
o
mm
e
n
d
a
t
i
o
n
:
a
s
u
r
v
e
y
,
”
I
EE
E
T
ra
n
s
a
c
t
i
o
n
s
o
n
K
n
o
w
l
e
d
g
e
a
n
d
D
a
t
a
En
g
i
n
e
e
ri
n
g
,
v
o
l
.
3
6
,
n
o
.
1
0
,
p
p
.
5
3
5
4
–
5
3
7
3
,
2
0
2
4
,
d
o
i
:
1
0
.
1
1
0
9
/
T
K
D
E.
2
0
2
4
.
3
3
8
2
2
6
2
.
[
1
0
]
Q
.
H
.
N
g
o
,
T.
K
e
c
h
a
d
i
,
a
n
d
N
.
A
.
L
e
-
K
h
a
c
,
“
D
o
mai
n
s
p
e
c
i
f
i
c
e
n
t
i
t
y
r
e
c
o
g
n
i
t
i
o
n
w
i
t
h
sem
a
n
t
i
c
-
b
a
se
d
d
e
e
p
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
,
”
I
EEE
A
c
c
e
ss
,
v
o
l
.
9
,
p
p
.
1
5
2
8
9
2
–
1
5
2
9
0
2
,
2
0
2
1
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
1
.
3
1
2
8
1
7
8
.
[
1
1
]
H
.
A
.
A
l
m
u
z
a
i
n
i
a
n
d
A
.
M
.
A
z
m
i
,
“
I
mp
a
c
t
o
f
s
t
e
mm
i
n
g
a
n
d
w
o
r
d
e
m
b
e
d
d
i
n
g
o
n
d
e
e
p
l
e
a
r
n
i
n
g
-
b
a
se
d
A
r
a
b
i
c
t
e
x
t
c
a
t
e
g
o
r
i
z
a
t
i
o
n
,
”
I
EEE
A
c
c
e
ss
,
v
o
l
.
8
,
p
p
.
1
2
7
9
1
3
–
1
2
7
9
2
8
,
2
0
2
0
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
0
.
3
0
0
9
2
1
7
.
[
1
2
]
S
.
C
h
a
n
g
,
G
.
J
.
A
h
n
,
a
n
d
S
.
P
a
r
k
,
“
I
mp
r
o
v
i
n
g
p
e
r
f
o
r
ma
n
c
e
o
f
n
e
u
r
a
l
I
R
mo
d
e
l
s
b
y
u
si
n
g
a
k
e
y
w
o
r
d
-
e
x
t
r
a
c
t
i
o
n
-
b
a
s
e
d
w
e
a
k
-
su
p
e
r
v
i
si
o
n
me
t
h
o
d
,
”
I
EE
E
A
c
c
e
ss
,
v
o
l
.
1
2
,
p
p
.
4
6
8
5
1
–
4
6
8
6
3
,
2
0
2
4
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
2
4
.
3
3
8
2
1
9
0
.
[
1
3
]
Y
.
Z
h
u
e
t
a
l
.
,
“
La
r
g
e
l
a
n
g
u
a
g
e
m
o
d
e
l
s
f
o
r
i
n
f
o
r
ma
t
i
o
n
r
e
t
r
i
e
v
a
l
:
A
s
u
r
v
e
y
,
”
AC
M
T
r
a
n
s
a
c
t
i
o
n
s
o
n
I
n
f
o
rm
a
t
i
o
n
S
y
s
t
e
m
s
,
v
o
l
.
a
r
X
i
v
:
2
3
0
8
,
2
0
2
5
,
d
o
i
:
1
0
.
1
1
4
5
/
3
7
4
8
3
0
4
.
[
1
4
]
W
.
S
o
n
g
,
J
.
Z.
L
i
a
n
g
,
X
.
L.
C
a
o
,
a
n
d
S
.
C
.
P
a
r
k
,
“
A
n
e
f
f
e
c
t
i
v
e
q
u
e
r
y
r
e
c
o
mm
e
n
d
a
t
i
o
n
a
p
p
r
o
a
c
h
u
si
n
g
sem
a
n
t
i
c
st
r
a
t
e
g
i
e
s
f
o
r
i
n
t
e
l
l
i
g
e
n
t
i
n
f
o
r
m
a
t
i
o
n
r
e
t
r
i
e
v
a
l
,
”
Ex
p
e
rt
S
y
s
t
e
m
s
w
i
t
h
Ap
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
4
1
,
n
o
.
2
,
p
p
.
3
6
6
–
3
7
2
,
2
0
1
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
sw
a
.
2
0
1
3
.
0
7
.
0
5
2
.
[
1
5
]
M
.
Y
.
C
h
e
n
,
H
.
C
.
C
h
u
,
a
n
d
Y
.
M
.
C
h
e
n
,
“
D
e
v
e
l
o
p
i
n
g
a
sema
n
t
i
c
-
e
n
a
b
l
e
i
n
f
o
r
ma
t
i
o
n
r
e
t
r
i
e
v
a
l
mec
h
a
n
i
sm,
”
Ex
p
e
r
t
S
y
st
e
m
s
w
i
t
h
Ap
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
3
7
,
n
o
.
1
,
p
p
.
3
2
2
–
3
4
0
,
2
0
1
0
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
sw
a
.
2
0
0
9
.
0
5
.
0
5
5
.
[
1
6
]
C
.
S
a
n
so
n
e
a
n
d
G
.
S
p
e
r
l
í
,
“
L
e
g
a
l
i
n
f
o
r
mat
i
o
n
r
e
t
r
i
e
v
a
l
sy
s
t
e
ms:
st
a
t
e
-
of
-
t
h
e
-
a
r
t
a
n
d
o
p
e
n
i
ssu
e
s,”
I
n
f
o
rm
a
t
i
o
n
S
y
s
t
e
m
s
,
v
o
l
.
1
0
6
,
p
.
1
0
1
9
6
7
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
s.
2
0
2
1
.
1
0
1
9
6
7
.
[
1
7
]
T.
B
e
n
c
h
-
C
a
p
o
n
e
t
a
l
.
,
“
A
h
i
st
o
r
y
o
f
A
I
a
n
d
l
a
w
i
n
5
0
p
a
p
e
r
s
:
2
5
Y
e
a
r
s
o
f
t
h
e
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
A
I
a
n
d
l
a
w
,
”
Ar
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
a
n
d
L
a
w
,
v
o
l
.
2
0
,
n
o
.
3
,
p
p
.
2
1
5
–
3
1
9
,
2
0
1
2
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
0
5
0
6
-
0
1
2
-
9
1
3
1
-
x.
[
1
8
]
K
.
D
.
A
s
h
l
e
y
,
Ar
t
i
f
i
c
i
a
l
i
n
t
e
l
l
i
g
e
n
c
e
a
n
d
l
e
g
a
l
a
n
a
l
y
t
i
c
s:
N
e
w
t
o
o
l
s
f
o
r
l
a
w
p
r
a
c
t
i
c
e
i
n
t
h
e
d
i
g
i
t
a
l
a
g
e
.
C
a
m
b
r
i
d
g
e
U
n
i
v
e
r
si
t
y
P
r
e
ss,
2
0
1
7
.
[
1
9
]
M
.
P
a
l
m
i
r
a
n
i
a
n
d
G
.
G
o
v
e
r
n
a
t
o
r
i
,
“
M
o
d
e
l
l
i
n
g
l
e
g
a
l
k
n
o
w
l
e
d
g
e
f
o
r
G
D
P
R
c
o
m
p
l
i
a
n
c
e
c
h
e
c
k
i
n
g
,
”
i
n
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
A
p
p
l
i
c
a
t
i
o
n
s
,
2
0
1
8
,
v
o
l
.
3
1
3
,
p
p
.
1
0
1
–
1
1
0
,
d
o
i
:
1
0
.
3
2
3
3
/
9
7
8
-
1
-
6
1
4
9
9
-
9
3
5
-
5
-
1
0
1
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
A
n
in
fo
r
ma
tio
n
r
etri
ev
a
l sys
t
em
fo
r
I
n
d
ia
n
le
g
a
l d
o
cu
men
ts
(
R
a
s
mi
R
a
n
i D
h
a
l
a
)
255
[
2
0
]
M
.
M
e
d
v
e
d
e
v
a
,
M
.
V
o
l
s
,
a
n
d
M
.
W
i
e
l
i
n
g
,
“
U
si
n
g
ma
c
h
i
n
e
l
e
a
r
n
i
n
g
t
o
p
r
e
d
i
c
t
d
e
c
i
s
i
o
n
s
o
f
t
h
e
E
u
r
o
p
e
a
n
C
o
u
r
t
o
f
H
u
ma
n
R
i
g
h
t
s,”
Art
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
a
n
d
L
a
w
,
v
o
l
.
2
8
,
n
o
.
2
,
p
p
.
2
3
7
–
2
6
6
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
0
7
/
s1
0
5
0
6
-
019
-
0
9
2
5
5
-
y.
[
2
1
]
S
.
B
r
ü
n
i
n
g
h
a
u
s
a
n
d
K
.
D
.
A
sh
l
e
y
,
“
I
mp
r
o
v
i
n
g
t
h
e
r
e
p
r
e
se
n
t
a
t
i
o
n
o
f
l
e
g
a
l
c
a
se
t
e
x
t
s
w
i
t
h
i
n
f
o
r
ma
t
i
o
n
e
x
t
r
a
c
t
i
o
n
me
t
h
o
d
s,”
i
n
Pro
c
e
e
d
i
n
g
s
o
f
t
h
e
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
Art
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
a
n
d
L
a
w
,
2
0
0
1
,
p
p
.
4
2
–
5
1
,
d
o
i
:
1
0
.
1
1
4
5
/
3
8
3
5
3
5
.
3
8
3
5
4
0
.
[
2
2
]
M
.
v
a
n
O
p
i
j
n
e
n
a
n
d
C
.
S
a
n
t
o
s
,
“
O
n
t
h
e
c
o
n
c
e
p
t
o
f
r
e
l
e
v
a
n
c
e
i
n
l
e
g
a
l
i
n
f
o
r
mat
i
o
n
r
e
t
r
i
e
v
a
l
,
”
Art
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
a
n
d
L
a
w
,
v
o
l
.
2
5
,
n
o
.
1
,
p
p
.
6
5
–
8
7
,
2
0
1
7
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
0
5
0
6
-
0
1
7
-
9
1
9
5
-
8.
[
2
3
]
C
.
B
i
a
g
i
o
l
i
,
E.
F
r
a
n
c
e
sc
o
n
i
,
A
.
P
a
ss
e
r
i
n
i
,
S
.
M
o
n
t
e
m
a
g
n
i
,
a
n
d
C
.
S
o
r
i
a
,
“
A
u
t
o
ma
t
i
c
sem
a
n
t
i
c
s
e
x
t
r
a
c
t
i
o
n
i
n
l
a
w
d
o
c
u
me
n
t
s,
”
i
n
Pro
c
e
e
d
i
n
g
s
o
f
t
h
e
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
Art
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
a
n
d
L
a
w
,
2
0
0
5
,
p
p
.
1
3
3
–
1
4
0
,
d
o
i
:
1
0
.
1
1
4
5
/
1
1
6
5
4
8
5
.
1
1
6
5
5
0
6
.
[
2
4
]
D
.
S
o
n
g
,
A
.
V
o
l
d
,
K
.
M
a
d
a
n
,
a
n
d
F
.
S
c
h
i
l
d
e
r
,
“
M
u
l
t
i
-
l
a
b
e
l
l
e
g
a
l
d
o
c
u
me
n
t
c
l
a
s
si
f
i
c
a
t
i
o
n
:
A
d
e
e
p
l
e
a
r
n
i
n
g
-
b
a
s
e
d
a
p
p
r
o
a
c
h
w
i
t
h
l
a
b
e
l
-
a
t
t
e
n
t
i
o
n
a
n
d
d
o
ma
i
n
-
s
p
e
c
i
f
i
c
p
r
e
-
t
r
a
i
n
i
n
g
,
”
I
n
f
o
rm
a
t
i
o
n
S
y
st
e
m
s
,
v
o
l
.
1
0
6
,
p
.
1
0
1
7
1
8
,
2
0
2
2
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
i
s.2
0
2
1
.
1
0
1
7
1
8
.
[
2
5
]
S
.
S
h
a
r
ma
,
S
.
S
r
i
v
a
st
a
v
a
,
P
.
V
e
r
ma
,
A
.
V
e
r
ma
,
a
n
d
S
.
N
.
C
h
a
u
r
a
s
i
a
,
“
A
c
o
mp
r
e
h
e
n
s
i
v
e
a
n
a
l
y
s
i
s
o
f
I
n
d
i
a
n
l
e
g
a
l
d
o
c
u
m
e
n
t
s
su
mm
a
r
i
z
a
t
i
o
n
t
e
c
h
n
i
q
u
e
s,
”
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
1
9
8
3
-
y.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Ra
sm
i
R
a
n
i
Dh
a
la
h
a
s
re
c
e
iv
e
d
a
M
.
Tec
h
.
d
e
g
re
e
i
n
c
o
m
p
u
ter
sc
ien
c
e
a
n
d
e
n
g
in
e
e
rin
g
a
n
d
is
c
u
rre
n
tl
y
p
u
r
su
in
g
P
h
.
D.
i
n
c
o
m
p
u
ter
sc
ien
c
e
a
n
d
e
n
g
i
n
e
e
rin
g
a
t
G
IET
Un
iv
e
rsity
,
G
u
n
u
p
u
r,
In
d
ia
.
He
r
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
a
rti
ficia
l
in
telli
g
e
n
c
e
,
n
a
tu
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
i
n
fo
rm
a
ti
o
n
re
tri
e
v
a
l.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
ra
sm
i.
ra
n
id
h
a
la@
g
iet.
e
d
u
.
A
V
S
Pa
v
a
n
K
u
m
a
r
is
c
u
rr
e
n
tl
y
wo
rk
in
g
a
s
a
n
a
ss
o
c
iate
p
r
o
fe
ss
o
r
a
t
G
a
n
d
h
i
In
stit
u
te
o
f
En
g
i
n
e
e
rin
g
a
n
d
Tec
h
n
o
lo
g
y
U
n
iv
e
rsit
y
,
G
u
n
u
p
u
r.
He
h
a
s
a
M
.
Tec
h
.
a
n
d
P
h
.
D.
d
e
g
re
e
in
c
o
m
p
u
ter
sc
ien
c
e
a
n
d
e
n
g
i
n
e
e
rin
g
.
His
re
se
a
rc
h
in
t
e
re
st
in
c
lu
d
e
s
d
a
ta
m
in
i
n
g
,
m
a
c
h
in
e
lea
rn
in
g
,
a
n
d
n
a
tu
ra
l
lan
g
u
a
g
e
p
r
o
c
e
ss
in
g
.
He
h
a
s
m
o
re
th
a
n
1
8
y
e
a
rs
o
f
tea
c
h
i
n
g
e
x
p
e
rien
c
e
a
n
d
h
a
s
p
u
b
li
s
h
e
d
v
a
r
io
u
s
re
se
a
rc
h
a
rti
c
les
in
re
p
u
ted
j
o
u
r
n
a
ls
a
n
d
c
o
n
fe
re
n
c
e
s.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
a
v
sp
a
v
a
n
k
u
m
a
r@g
iet.
e
d
u
.
S
o
u
m
y
a
Priy
a
d
a
r
sin
i
P
a
n
d
a
is
c
u
rre
n
tl
y
wo
r
k
i
n
g
a
s
a
S
r.
a
ss
istan
t
p
r
o
fe
ss
o
r
i
n
th
e
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter
S
c
i
e
n
c
e
a
n
d
En
g
in
e
e
rin
g
,
S
i
li
c
o
n
U
n
iv
e
rsit
y
,
Od
is
h
a
,
In
d
ia.
S
h
e
h
a
s
M
.
Tec
h
.
a
n
d
P
h
.
D
.
d
e
g
re
e
i
n
c
o
m
p
u
ter
sc
ien
c
e
a
n
d
e
n
g
in
e
e
r
in
g
a
n
d
h
a
s
p
u
b
l
ish
e
d
m
o
re
th
a
n
3
0
re
se
a
rc
h
p
a
p
e
rs
in
re
p
u
t
e
d
jo
u
r
n
a
ls
a
n
d
c
o
n
fe
re
n
c
e
s.
He
r
re
se
a
rc
h
in
tere
st
in
c
lu
d
e
s
n
a
tu
ra
l
lan
g
u
a
g
e
p
ro
c
e
ss
in
g
,
s
p
e
e
c
h
p
ro
c
e
ss
in
g
,
a
rti
f
icia
l
in
telli
g
e
n
c
e
,
in
fo
rm
a
ti
o
n
re
tri
e
v
a
l
,
a
n
d
m
a
c
h
in
e
lea
rn
i
n
g
.
S
h
e
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
so
u
m
y
a
.
p
a
n
d
a
@s
il
ico
n
.
a
c
.
in
.
Evaluation Warning : The document was created with Spire.PDF for Python.