I
nte
rna
t
io
na
l J
o
urna
l o
f
I
nfo
rm
a
t
ics a
nd
Co
m
m
un
ica
t
io
n
T
ec
hn
o
lo
g
y
(
I
J
-
I
CT
)
Vo
l.
1
5
,
No
.
2
,
J
u
n
e
20
2
6
,
p
p
.
456
~
4
6
4
I
SS
N:
2252
-
8
7
7
6
,
DOI
:
1
0
.
1
1
5
9
1
/iji
ct
.
v
1
5
i
2
.
pp
456
-
4
6
4
456
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ict.
ia
esco
r
e.
co
m
A crit
i
ca
l review
o
f
inform
a
tion r
et
riev
a
l t
echniq
ues:
current
t
r
ends a
n
d challeng
es
Sa
nk
et
D.
P
a
t
il
1,
2
,
Z
a
hir A
a
la
m
1
1
D
e
p
a
r
t
me
n
t
o
f
I
n
f
o
r
mat
i
o
n
Te
c
h
n
o
l
o
g
y
,
T
h
a
k
u
r
C
o
l
l
e
g
e
o
f
En
g
i
n
e
e
r
i
n
g
a
n
d
T
e
c
h
n
o
l
o
g
y
,
U
n
i
v
e
r
s
i
t
y
o
f
M
u
m
b
a
i
,
M
u
m
b
a
i
,
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
En
g
i
n
e
e
r
i
n
g
,
V
i
d
y
a
v
a
r
d
h
i
n
i
's
C
o
l
l
e
g
e
o
f
En
g
i
n
e
e
r
i
n
g
a
n
d
T
e
c
h
n
o
l
o
g
y
,
U
n
i
v
e
r
s
i
t
y
o
f
M
u
mb
a
i
,
M
u
mb
a
i
,
I
n
d
i
a
Art
ic
le
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Oct
1
5
,
2
0
2
4
R
ev
is
ed
No
v
6
,
2
0
2
5
Acc
ep
ted
Dec
1
4
,
2
0
2
5
Th
e
re
a
lm
o
f
in
f
o
rm
a
ti
o
n
re
tri
e
v
a
l
is
witn
e
ss
in
g
tran
s
fo
rm
a
ti
v
e
a
d
v
a
n
c
e
m
e
n
ts,
d
riv
e
n
b
y
th
e
i
n
teg
ra
ti
o
n
o
f
d
e
e
p
lea
rn
in
g
te
c
h
n
iq
u
e
s,
sp
e
c
ialize
d
a
lg
o
rit
h
m
s,
a
n
d
d
o
m
a
in
-
sp
e
c
ifi
c
a
p
p
li
c
a
ti
o
n
s
.
In
fo
rm
a
ti
o
n
re
tri
e
v
a
l
sy
ste
m
s
p
lay
a
n
imp
o
rt
a
n
t
ro
le
in
m
a
n
y
a
p
p
li
c
a
ti
o
n
s
in
c
lu
d
i
n
g
in
th
e
Artifi
c
ial
In
telli
g
e
n
c
e
p
o
we
re
d
sy
ste
m
s
th
a
t
c
a
n
b
e
se
e
n
in
m
a
n
y
a
p
p
li
c
a
ti
o
n
s.
In
f
o
rm
a
ti
o
n
Re
tri
e
v
a
l,
g
e
n
e
r
a
ll
y
,
a
c
ts
a
n
imp
o
rtan
t
t
a
sk
in
th
e
k
n
o
wle
d
g
e
d
isc
o
v
e
r
y
p
h
a
se
o
f
a
n
y
q
u
e
ry
b
a
se
d
i
n
telli
g
e
n
t
sy
s
tem
.
Th
is
p
a
p
e
r
p
re
se
n
ts
a
c
o
m
p
re
h
e
n
si
v
e
re
v
iew
b
y
c
o
n
d
u
c
ti
n
g
a
d
e
tailed
a
n
a
ly
sis
o
f
th
e
tec
h
n
o
lo
g
ica
l
n
u
a
n
c
e
s,
d
a
tas
e
t
sp
e
c
ifi
c
a
ti
o
n
s,
a
n
d
p
iv
o
tal
fi
n
d
i
n
g
s.
T
h
is
d
e
tailed
re
v
iew
h
a
s
b
e
e
n
d
o
n
e
with
t
h
e
sp
e
c
ial
e
m
p
h
a
sis
o
n
th
e
k
in
d
o
f
tec
h
n
o
l
o
g
y
u
se
d
t
o
a
c
h
iev
e
a
c
c
u
ra
te
in
fo
rm
a
ti
o
n
re
tri
e
v
a
l,
d
o
m
a
in
o
f
th
e
stu
d
y
,
a
n
d
t
h
e
sy
ste
m
’s
a
b
il
it
y
t
o
re
tain
o
r
w
o
rk
wi
th
tab
les
a
n
d
fi
g
u
re
s,
a
m
o
n
g
o
th
e
r
p
a
ra
m
e
ters
.
Na
v
ig
a
ti
n
g
t
h
ro
u
g
h
th
e
ric
h
tap
e
stry
o
f
m
e
th
o
d
o
lo
g
ies
,
t
h
e
p
a
p
e
r
u
n
d
e
r
sc
o
re
s
th
e
p
iv
o
tal
r
o
le
o
f
d
e
e
p
lea
rn
in
g
fra
m
e
wo
rk
s
in
re
v
o
l
u
ti
o
n
izi
n
g
tr
a
d
it
io
n
a
l
re
tri
e
v
a
l
p
a
ra
d
i
g
m
s.
F
u
rth
e
rm
o
re
,
it
sh
e
d
s
li
g
h
t
o
n
th
e
in
n
o
v
a
ti
v
e
in
teg
ra
ti
o
n
o
f
tex
t
u
a
l
in
f
o
rm
a
ti
o
n
,
a
lg
o
rit
h
m
i
c
a
d
v
a
n
c
e
m
e
n
ts,
a
n
d
s
p
e
c
ialize
d
d
a
tas
e
ts
to
e
n
h
a
n
c
e
th
e
e
ffica
c
y
a
n
d
g
ra
n
u
larit
y
o
f
i
n
fo
rm
a
ti
o
n
re
t
riev
a
l
m
e
c
h
a
n
ism
s
.
K
ey
w
o
r
d
s
:
Dee
p
l
ea
r
n
in
g
I
n
f
o
r
m
atio
n
r
etr
ie
v
al
I
R
s
y
s
tem
L
STM
NL
P
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
:
San
k
et
D
.
Patil
Dep
ar
tm
en
t o
f
I
n
f
o
r
m
atio
n
T
e
ch
n
o
lo
g
y
,
T
h
ak
u
r
C
o
lleg
e
o
f
E
n
g
in
ee
r
in
g
an
d
T
ec
h
n
o
lo
g
y
Un
iv
er
s
ity
o
f
Mu
m
b
ai
Ma
h
atm
a
Gan
d
h
i Ro
ad
,
Mu
m
b
ai,
I
n
d
ia
E
m
ail:
s
an
k
etp
atilv
ce
t@
g
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
I
n
an
ag
e
d
e
f
in
ed
b
y
d
ig
ital
p
r
o
life
r
atio
n
,
th
e
in
t
r
icac
ies
o
f
in
f
o
r
m
atio
n
r
etr
iev
al
h
av
e
b
ec
o
m
e
b
o
th
an
ac
ad
em
ic
p
u
r
s
u
it
an
d
an
o
p
er
atio
n
al
im
p
er
ativ
e.
T
h
e
in
tr
ig
u
i
n
g
d
an
ce
b
etwe
en
h
u
m
a
n
c
o
g
n
itio
n
,
co
m
p
u
tatio
n
al
alg
o
r
ith
m
s
,
an
d
v
ast
d
atasets
h
as
p
av
ed
th
e
way
f
o
r
g
r
o
u
n
d
-
b
r
ea
k
in
g
r
esear
ch
in
m
an
y
f
ield
s
o
f
r
esear
ch
an
d
b
u
s
in
ess
es.
T
h
e
‘
d
ata’
h
as
b
ee
n
at
th
e
h
ea
r
t
o
f
m
an
y
ar
tific
ial
in
tellig
en
c
e/m
ac
h
in
e
lear
n
in
g
/
d
ee
p
lear
n
in
g
b
r
ea
k
th
r
o
u
g
h
s
[
1
]
.
R
etr
iev
al
an
d
e
x
tr
ac
tio
n
o
f
r
elev
an
t
in
f
o
r
m
atio
n
f
r
o
m
th
e
h
u
m
o
n
g
o
u
s
r
e
p
o
s
ito
r
y
o
f
d
ata
is
an
im
p
o
r
tan
t
task
.
T
h
is
task
in
v
o
lv
es
s
tr
ea
m
lin
in
g
t
h
e
p
r
o
ce
s
s
o
f
ex
tr
ac
tin
g
m
ea
n
in
g
f
u
l
in
s
ig
h
ts
f
r
o
m
v
o
lu
m
in
o
u
s
in
f
o
r
m
atio
n
r
e
p
o
s
ito
r
ies.
An
I
R
s
y
s
tem
ca
n
b
e
d
ef
in
ed
as
a
s
o
f
twar
e
a
p
p
licatio
n
th
at
m
an
ag
es
th
e
o
r
g
an
is
atio
n
,
s
to
r
i
n
g
,
r
etr
iev
i
n
g
,
an
d
ass
ess
in
g
in
f
o
r
m
atio
n
f
r
o
m
d
o
c
u
m
en
t
r
ep
o
s
ito
r
ie
s
,
esp
ec
ially
tex
tu
al
in
f
o
r
m
atio
n
,
wh
ich
is
k
n
o
wn
as
in
f
o
r
m
atio
n
r
etr
iev
al
(
I
R
)
.
I
n
f
o
r
m
atio
n
r
etr
iev
al
is
th
e
p
r
o
ce
s
s
o
f
g
ettin
g
co
n
ten
t
f
r
o
m
v
ast
co
m
p
u
ter
-
s
t
o
r
ed
c
o
llectio
n
s
th
at
m
a
y
ty
p
i
ca
lly
b
e
r
ec
o
r
d
e
d
in
an
u
n
s
tr
u
ctu
r
ed
m
a
n
n
er
,
i.e
.
,
tex
t,
wh
ich
m
ee
ts
a
d
em
a
n
d
f
o
r
in
f
o
r
m
atio
n
[
2
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
I
SS
N:
2252
-
8
7
7
6
A
crit
ica
l revie
w
o
f in
fo
r
ma
tio
n
r
etri
ev
a
l te
ch
n
iq
u
es:
cu
r
r
en
t tren
d
s
…
(
S
a
n
ke
t D
.
P
a
til
)
457
T
h
e
u
s
es o
f
I
R
s
y
s
tem
s
ar
e
m
a
n
if
o
ld
[
3
]
:
1.
W
eb
s
ea
r
ch
en
g
in
es
:
Platfo
r
m
s
lik
e
Go
o
g
le,
a
n
d
B
in
g
e
m
p
lo
y
ad
v
a
n
ce
d
I
R
tech
n
i
q
u
es
to
in
d
e
x
a
n
d
r
etr
iev
e
web
p
a
g
es
b
ased
o
n
u
s
er
q
u
er
ies.
2.
Dig
ital
lib
r
ar
ies:
I
R
s
y
s
tem
s
f
ac
ilit
ate
th
e
o
r
g
a
n
izatio
n
,
s
to
r
ag
e,
a
n
d
r
etr
ie
v
al
o
f
d
ig
it
al
r
eso
u
r
ce
s
in
lib
r
ar
ies an
d
ac
ad
em
ic
r
ep
o
s
it
o
r
ies.
3.
E
-
co
m
m
er
ce
:
Pro
d
u
ct
s
ea
r
ch
f
u
n
ctio
n
alities
o
n
o
n
lin
e
s
h
o
p
p
in
g
p
latf
o
r
m
s
r
ely
o
n
I
R
s
y
s
tem
s
to
d
is
p
lay
r
elev
an
t p
r
o
d
u
cts to
u
s
er
s
.
4.
Hea
lth
ca
r
e:
I
R
p
lay
s
a
p
iv
o
tal
r
o
le
in
m
ed
ical
d
atab
ases
,
aid
in
g
p
r
o
f
ess
io
n
als
in
ac
ce
s
s
in
g
r
elev
an
t
r
esear
ch
p
ap
e
r
s
,
p
atien
t r
ec
o
r
d
s
,
an
d
d
iag
n
o
s
tic
in
f
o
r
m
atio
n
.
T
h
e
im
p
o
r
tan
ce
o
f
th
e
I
R
s
y
s
tem
s
is
cr
u
cial
in
m
an
y
a
p
p
lica
tio
n
s
an
d
u
s
ec
ases
ac
r
o
s
s
s
ec
t
o
r
s
[
4
]
:
1.
E
f
f
icien
t
ac
ce
s
s
to
i
n
f
o
r
m
atio
n
:
I
n
f
o
r
m
atio
n
r
etr
iev
al
(
I
R
)
s
y
s
tem
s
en
ab
le
u
s
er
s
to
s
w
if
tly
ac
ce
s
s
an
d
r
etr
iev
e
r
elev
an
t
in
f
o
r
m
atio
n
f
r
o
m
v
ast r
ep
o
s
ito
r
ies,
th
er
eb
y
o
p
tim
izin
g
tim
e
an
d
ef
f
o
r
t.
2.
Dec
is
io
n
m
ak
in
g
:
I
n
v
ar
io
u
s
s
ec
to
r
s
,
f
r
o
m
h
ea
lth
ca
r
e
to
b
u
s
in
ess
,
tim
ely
an
d
ac
cu
r
ate
in
f
o
r
m
atio
n
r
etr
iev
al
f
ac
ilit
ates in
f
o
r
m
ed
d
ec
is
io
n
-
m
ak
in
g
p
r
o
ce
s
s
es.
3.
Kn
o
wled
g
e
d
is
co
v
er
y
:
I
R
s
y
s
tem
s
ca
n
aid
r
esear
ch
er
s
a
n
d
p
r
o
f
ess
io
n
als
in
d
is
co
v
er
i
n
g
n
ew
in
s
ig
h
ts
,
tr
en
d
s
,
an
d
p
atter
n
s
with
in
lar
g
e
d
atasets
,
f
o
s
ter
in
g
in
n
o
v
ati
o
n
an
d
d
is
co
v
er
y
.
4.
E
n
h
a
n
c
e
d
u
s
e
r
e
x
p
e
r
i
e
n
c
e
:
I
n
t
h
e
d
i
g
i
t
a
l
a
g
e
,
u
s
e
r
e
x
p
e
r
i
e
n
c
e
h
i
n
g
e
s
o
n
t
h
e
s
e
a
m
l
e
s
s
r
e
t
r
i
e
v
a
l
o
f
i
n
f
o
r
m
a
t
i
o
n
,
m
a
k
i
n
g
I
R
s
y
s
t
e
m
s
i
n
d
i
s
p
e
n
s
a
b
l
e
f
o
r
p
l
a
t
f
o
r
m
s
r
a
n
g
i
n
g
f
r
o
m
s
e
a
r
c
h
e
n
g
i
n
e
s
t
o
e
-
c
o
m
m
e
r
c
e
s
i
t
e
s
.
T
h
er
e
ar
e
m
a
n
y
a
p
p
licatio
n
s
o
f
in
f
o
r
m
atio
n
r
etr
ie
v
al
[
4
]
:
1.
Per
s
o
n
alize
d
r
ec
o
m
m
e
n
d
atio
n
s
y
s
tem
s
:
Platfo
r
m
s
lik
e
Netf
lix
an
d
Am
az
o
n
u
tili
ze
I
R
tech
n
iq
u
es
to
o
f
f
e
r
p
er
s
o
n
alize
d
co
n
ten
t a
n
d
p
r
o
d
u
ct
r
ec
o
m
m
e
n
d
atio
n
s
to
u
s
er
s
.
2.
L
eg
al
an
d
r
e
g
u
lato
r
y
co
m
p
lia
n
ce
:
I
n
th
e
le
g
al
s
ec
to
r
,
I
R
s
y
s
tem
s
aid
p
r
o
f
ess
io
n
als
in
r
etr
iev
in
g
p
er
tin
en
t
ca
s
e
laws,
s
tatu
te
s
,
an
d
r
eg
u
lat
o
r
y
g
u
id
elin
es.
3.
C
o
n
ten
t
m
an
ag
em
e
n
t
s
y
s
tem
s
:
I
R
p
lay
s
a
cr
u
cial
r
o
le
in
c
o
n
ten
t
m
an
ag
e
m
en
t
p
latf
o
r
m
s
,
f
ac
ilit
atin
g
th
e
ef
f
icien
t
o
r
g
a
n
izatio
n
,
r
etr
iev
a
l,
an
d
d
is
s
em
in
atio
n
o
f
d
ig
ital
co
n
ten
t.
4.
So
cial
m
ed
ia
an
aly
s
is
:
I
R
tech
n
iq
u
es
ar
e
e
m
p
lo
y
ed
to
a
n
a
ly
ze
an
d
r
etr
iev
e
r
ele
v
an
t
in
f
o
r
m
atio
n
f
r
o
m
s
o
cial
m
ed
ia
p
latf
o
r
m
s
,
aid
i
n
g
b
u
s
in
ess
es in
m
ar
k
et
an
aly
s
is
,
s
en
tim
en
t a
n
aly
s
is
,
an
d
tr
en
d
f
o
r
ec
asti
n
g
.
Hav
in
g
estab
lis
h
ed
th
e
im
p
o
r
tan
ce
o
f
I
n
f
o
r
m
atio
n
R
etr
iev
al,
it is
also
im
p
o
r
tan
t to
n
o
te
th
a
t th
er
e
ar
e
m
an
y
ch
allen
g
es
th
at
m
ak
e
t
h
e
p
r
o
ce
s
s
o
f
in
f
o
r
m
atio
n
r
etr
ie
v
al
a
b
ig
c
h
allen
g
e
[
5
]
:
1.
I
n
f
o
r
m
atio
n
o
v
er
lo
a
d
:
T
h
e
ex
p
o
n
e
n
tial
g
r
o
wth
o
f
d
ig
it
al
d
ata
h
as
ex
ac
e
r
b
ated
th
e
ch
allen
g
e
o
f
in
f
o
r
m
atio
n
o
v
e
r
lo
ad
,
n
ec
ess
itatin
g
m
o
r
e
r
ef
in
ed
r
etr
iev
al
te
ch
n
iq
u
es.
2.
Am
b
ig
u
ity
an
d
co
n
tex
t
s
en
s
itiv
ity
:
L
an
g
u
ag
e
is
in
h
er
e
n
tly
am
b
ig
u
o
u
s
,
an
d
I
R
s
y
s
tem
s
m
u
s
t
g
r
ap
p
le
with
th
e
n
u
an
ce
d
m
ea
n
i
n
g
s
an
d
c
o
n
tex
tu
al
v
ar
iatio
n
s
o
f
u
s
er
q
u
er
i
es.
3.
Dy
n
am
ic
n
atu
r
e
o
f
d
ata
:
T
h
e
r
ea
l
-
tim
e
an
d
d
y
n
am
ic
n
atu
r
e
o
f
m
an
y
d
atasets
p
o
s
es
ch
allen
g
es
in
en
s
u
r
in
g
th
e
r
elev
an
cy
an
d
ac
cu
r
ac
y
o
f
r
etr
iev
ed
in
f
o
r
m
atio
n
.
4.
Alg
o
r
ith
m
ic
B
iases
:
I
R
s
y
s
tem
s
ca
n
i
n
ad
v
er
te
n
tly
p
er
p
etu
ate
b
iases
p
r
esen
t
i
n
tr
ai
n
in
g
d
ata,
lead
in
g
t
o
s
k
ewe
d
o
r
u
n
f
air
in
f
o
r
m
atio
n
r
etr
iev
al
o
u
tco
m
es.
I
n
s
u
m
m
a
r
y
,
in
f
o
r
m
atio
n
r
etr
i
ev
al
s
tan
d
s
as
a
c
o
r
n
er
s
to
n
e
i
n
th
e
d
ig
ital
ec
o
s
y
s
tem
,
u
n
d
e
r
p
in
n
in
g
a
m
y
r
iad
o
f
ap
p
licatio
n
s
an
d
d
o
m
ain
s
[
6
]
,
[
7
]
.
W
h
ile
it
o
f
f
er
s
u
n
p
ar
alleled
b
en
ef
its
i
n
f
ac
ilit
atin
g
ac
ce
s
s
to
in
f
o
r
m
atio
n
an
d
d
r
i
v
in
g
in
n
o
v
atio
n
,
th
e
f
ield
also
p
r
esen
ts
in
tr
icate
ch
allen
g
es
th
at
n
ec
ess
itate
co
n
tin
u
o
u
s
r
esear
ch
,
r
ef
in
e
m
en
t,
an
d
eth
i
ca
l c
o
n
s
id
er
atio
n
s
[
8
]
,
[
9
]
.
B
y
d
elv
in
g
d
ee
p
in
to
th
e
m
et
h
o
d
o
lo
g
ies,
d
atasets
,
an
d
th
e
s
tatu
s
o
f
r
eten
tio
n
o
f
ta
b
les
an
d
p
ictu
r
es
f
r
o
m
th
e
o
r
ig
in
al
tex
t
a
n
d
f
in
d
in
g
s
o
f
ea
c
h
p
a
p
er
,
th
is
p
a
p
e
r
asp
ir
es
to
ac
h
iev
e
m
u
ltip
le
o
b
jectiv
es.
Firstl
y
,
it
aim
s
to
p
r
o
v
id
e
a
g
r
an
u
lar
u
n
d
er
s
tan
d
i
n
g
o
f
th
e
tec
h
n
o
l
o
g
ical
f
o
u
n
d
atio
n
s
th
at
u
n
d
e
r
p
in
co
n
tem
p
o
r
ar
y
in
f
o
r
m
atio
n
r
etr
ie
v
al
s
y
s
tem
s
.
Seco
n
d
ly
,
it
s
ee
k
s
to
el
u
cid
ate
th
e
d
o
m
ain
-
s
p
ec
if
ic
ap
p
licatio
n
s
a
n
d
ch
allen
g
es,
o
f
f
e
r
in
g
r
ea
d
er
s
a
n
u
an
ce
d
p
er
s
p
ec
tiv
e
o
n
th
e
p
r
ac
tical
im
p
licatio
n
s
o
f
th
ese
r
e
s
ea
r
ch
en
d
ea
v
o
u
r
s
.
Fu
r
th
er
m
o
r
e
,
b
y
s
y
n
th
esizin
g
in
s
ig
h
ts
f
r
o
m
th
ese
d
iv
er
s
e
s
t
u
d
ies,
th
is
s
u
r
v
ey
e
n
d
ea
v
o
u
r
s
to
id
en
tif
y
em
er
g
en
t
tr
en
d
s
,
p
o
ten
tial
r
e
s
ea
r
ch
g
ap
s
,
an
d
av
e
n
u
es
f
o
r
f
u
t
u
r
e
e
x
p
lo
r
atio
n
i
n
th
e
f
i
eld
o
f
in
f
o
r
m
atio
n
r
etr
iev
al.
2.
I
NF
O
RM
A
T
I
O
N
R
E
T
RI
E
V
AL
SYS
T
E
M
S
T
h
e
is
s
u
e
th
at
Pan
d
ey
an
d
B
h
at
[
1
0
]
id
en
tifie
d
in
n
atu
r
al
la
n
g
u
ag
e
p
r
o
ce
s
s
in
g
,
tex
t
-
b
ased
q
u
esti
o
n
an
s
wer
in
g
(
QA)
is
a
cr
u
cial
ac
tiv
ity
th
at
s
ee
k
s
to
d
eliv
er
p
r
ec
is
e
an
d
p
er
tin
en
t
r
esp
o
n
s
es
to
u
s
er
s
'
in
q
u
ir
ies.
C
o
n
v
en
tio
n
al
m
eth
o
d
s
o
f
q
u
ality
ass
u
r
an
ce
d
ep
en
d
ed
o
n
m
a
n
u
ally
d
esig
n
ed
f
ea
tu
r
es
an
d
r
u
le
-
b
ased
s
y
s
tem
s
.
On
th
e
o
th
er
h
a
n
d
,
cu
r
r
e
n
t
d
ev
elo
p
m
e
n
ts
in
d
ee
p
lear
n
i
n
g
a
n
d
i
n
f
o
r
m
atio
n
r
etr
iev
al
h
av
e
d
em
o
n
s
tr
ated
en
co
u
r
a
g
in
g
o
u
tco
m
es
in
en
h
an
cin
g
th
e
f
u
n
ctio
n
ality
o
f
Q
A
s
y
s
tem
s
.
T
h
e
p
er
f
o
r
m
a
n
ce
o
f
q
u
ality
ass
u
r
an
ce
h
as
s
ig
n
if
ican
tly
im
p
r
o
v
ed
as
a
r
esu
lt
o
f
th
e
in
teg
r
atio
n
o
f
d
ee
p
lear
n
in
g
tec
h
n
iq
u
es
with
I
R
.
T
h
e
a
u
th
o
r
s
in
ten
d
to
ca
p
italize
o
n
th
e
a
d
v
an
tag
es
o
f
b
o
th
I
R
an
d
d
ee
p
lear
n
i
n
g
m
o
d
els.
A
h
y
b
r
id
m
o
d
els
h
a
v
e
b
ee
n
d
ev
elo
p
e
d
,
s
u
ch
as th
e
b
i
-
en
co
d
er
an
d
tr
i
-
en
co
d
er
ar
c
h
itectu
r
es.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
7
7
6
I
n
t J I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
,
Vo
l.
1
5
,
No
.
2
,
J
u
n
e
20
2
6
:
4
5
6
-
4
6
4
458
T
h
e
au
th
o
r
s
ex
am
in
e
s
ev
er
al
s
u
g
g
ested
m
o
d
els
an
d
d
ata
s
ets
av
ailab
le
f
o
r
th
e
jo
b
,
a
s
s
es
s
th
eir
ef
f
ec
tiv
en
ess
u
s
in
g
p
er
f
o
r
m
an
ce
m
etr
ics,
an
d
g
i
v
e
a
b
r
ief
s
y
n
o
p
s
is
o
f
th
e
QA
s
y
s
tem
an
d
its
m
an
y
d
o
m
ain
s
an
d
s
u
b
d
o
m
ain
s
in
o
r
d
er
to
s
tu
d
y
tex
tu
al
q
u
esti
o
n
a
n
s
wer
in
g
.
T
h
e
a
u
th
o
r
s
d
o
n
o
t
d
iv
u
lg
e
wh
eth
er
t
h
e
p
r
o
p
o
s
ed
s
y
s
tem
is
ab
le
to
etr
iev
e
th
e
im
ag
es
o
r
th
e
tab
les
in
th
e
o
r
ig
in
al
d
ata
w
h
ile
an
s
wer
in
g
to
th
e
q
u
er
ies
p
o
s
ted
b
y
t
h
e
u
s
er
s
.
Als
o
,
th
e
p
ap
er
m
a
k
es
u
s
e
o
f
th
e
ex
is
tin
g
tech
n
o
l
o
g
ies.
Van
et
a
l.
[
11
]
p
lan
s
to
p
r
o
v
id
e
ef
f
ec
tiv
e
d
ee
p
lear
n
in
g
-
b
ased
tech
n
i
q
u
es
in
th
is
r
esear
ch
f
o
r
p
r
o
ce
s
s
in
g
leg
al
d
o
cu
m
en
ts
,
in
clu
d
in
g
task
s
r
elate
d
to
leg
al
d
o
cu
m
en
t
r
et
r
iev
al
an
d
leg
al
q
u
esti
o
n
an
s
wer
in
g
in
th
e
au
to
m
ated
l
eg
al
q
u
esti
o
n
an
s
wer
in
g
co
m
p
etitio
n
(
AL
QAC
2
0
2
2
)
.
T
h
e
XL
M
-
R
o
B
E
R
T
a
m
o
d
el,
wh
ich
is
p
r
e
-
tr
ain
ed
f
r
o
m
a
s
izab
le
q
u
an
tity
o
f
u
n
lab
eled
co
r
p
u
s
b
ef
o
r
e
b
ein
g
f
in
e
-
tu
n
ed
to
th
e
p
ar
ticu
lar
task
s
,
is
th
e
b
asis
o
f
th
is
tech
n
iq
u
e.
T
h
e
p
r
o
ce
d
u
r
e
p
er
f
o
r
m
s
ef
f
ec
tiv
ely
in
leg
al
r
etr
iev
al
in
f
o
r
m
ati
o
n
task
s
with
a
litt
le
am
o
u
n
t
o
f
lab
eled
d
ata,
ac
c
o
r
d
in
g
to
th
e
ex
p
er
im
e
n
tal
r
esu
lts
.
Fu
r
th
er
m
o
r
e,
t
h
e
au
th
o
r
s
claim
th
at
v
ar
io
u
s
in
f
o
r
m
atio
n
r
etr
iev
al
task
s
in
lo
w
-
r
eso
u
r
ce
lan
g
u
ag
es
m
ay
b
e
ac
co
m
p
lis
h
ed
u
s
in
g
t
h
is
m
eth
o
d
o
lo
g
y
.
Ag
ain
,
th
e
au
th
o
r
s
d
o
n
o
t
d
i
v
u
lg
e
w
h
eth
er
th
e
y
ar
e
c
o
n
s
id
er
in
g
o
r
wo
r
k
in
g
with
th
e
im
ag
es
o
r
th
e
tab
les
in
t
h
e
o
r
ig
in
al
d
ata
wh
ile
a
n
s
wer
in
g
to
th
e
q
u
e
r
ies p
o
s
ted
b
y
th
e
u
s
er
s
.
Z
h
ao
et
a
l.
[
12
]
p
o
in
ted
o
u
t
t
h
at
th
e
p
r
o
b
lem
with
a
r
ec
o
m
m
en
d
atio
n
s
y
s
tem
'
s
o
v
e
r
all
o
p
er
atio
n
is
th
at
it
r
ec
eiv
es
ca
n
d
id
ate
ite
m
s
,
th
e
r
etr
iev
al
lay
er
f
ilter
s
a
s
m
all
n
u
m
b
er
o
f
item
s
th
at
u
s
er
s
m
ig
h
t
f
in
d
in
ter
esti
n
g
,
an
d
th
e
r
an
k
in
g
lay
er
p
e
r
f
o
r
m
s
m
o
r
e
p
r
ec
is
e
f
i
lter
in
g
to
p
r
o
d
u
ce
th
e
f
in
al
r
e
co
m
m
en
d
atio
n
lis
t.
T
h
e
r
etr
iev
al
lay
er
i
s
th
e
in
itial
s
tep
in
th
e
r
ec
o
m
m
en
d
atio
n
s
y
s
tem
,
an
d
its
ef
f
ec
tiv
en
ess
i
n
f
lu
en
ce
s
th
e
u
p
p
e
r
b
o
u
n
d
o
f
t
h
e
r
an
k
in
g
im
p
ac
t a
s
well
as h
o
w
r
ap
id
ly
th
e
s
y
s
tem
ca
n
f
ilter
in
f
o
r
m
atio
n
.
T
h
e
au
th
o
r
s
co
n
ce
n
tr
ate
o
n
d
ee
p
lear
n
in
g
tech
n
iq
u
es
f
r
eq
u
en
tly
em
p
lo
y
ed
in
th
e
r
et
r
iev
al
lay
er
to
ad
d
r
ess
th
e
s
ta
ted
is
s
u
e,
wh
ich
is
r
elev
an
t to
th
e
o
p
tim
izatio
n
o
f
r
ec
o
m
m
en
d
atio
n
s
y
s
tem
s
.
T
h
e
p
a
p
er
b
y
Ma
ts
iu
k
et
a
l.
[
13
]
d
elv
es
in
to
th
e
a
p
p
licatio
n
o
f
an
in
f
o
r
m
atio
n
r
etr
iev
al
t
h
esau
r
u
s
to
en
h
an
ce
in
f
o
r
m
atio
n
r
et
r
iev
al
tech
n
o
lo
g
ies
with
in
s
p
ec
if
ic
d
ata
d
o
m
ain
s
.
I
n
th
e
co
n
tex
t
o
f
th
e
ac
ce
ler
atin
g
g
r
o
wth
o
f
b
ig
d
ata
,
th
e
au
th
o
r
s
ex
p
lo
r
e
th
e
r
o
le
o
f
a
th
esau
r
u
s
in
r
ef
in
in
g
th
e
ef
f
icien
c
y
a
n
d
ef
f
ec
tiv
en
ess
o
f
in
f
o
r
m
atio
n
r
etr
iev
al
p
r
o
ce
s
s
es.
T
h
e
p
r
im
ar
y
o
b
jectiv
e
o
f
t
h
e
s
tu
d
y
is
to
d
em
o
n
s
tr
ate
th
e
p
r
ac
tical
im
p
lem
en
tatio
n
o
f
a
n
in
f
o
r
m
atio
n
r
etr
iev
al
th
esau
r
u
s
in
o
p
tim
izin
g
in
f
o
r
m
atio
n
r
etr
iev
al
tech
n
o
lo
g
ies.
T
h
e
f
o
cu
s
is
o
n
s
p
ec
if
ic
d
ata
d
o
m
a
in
s
,
s
u
g
g
esti
n
g
a
tar
g
eted
ap
p
r
o
ac
h
to
ad
d
r
ess
in
g
ch
allen
g
es
r
elate
d
to
d
o
m
ain
-
s
p
ec
if
ic
in
f
o
r
m
ati
o
n
o
r
g
an
izat
io
n
an
d
r
etr
iev
al.
T
h
e
au
th
o
r
s
em
p
lo
y
a
p
r
ac
tic
al
ap
p
r
o
ac
h
,
em
p
h
asizin
g
th
e
ap
p
licatio
n
o
f
an
in
f
o
r
m
atio
n
r
etr
iev
al
th
esau
r
u
s
.
T
h
e
s
tu
d
y
lik
ely
in
v
o
lv
es
th
e
d
ev
elo
p
m
e
n
t
an
d
im
p
lem
en
tatio
n
o
f
th
e
th
esau
r
u
s
with
in
a
d
ef
in
ed
d
ata
d
o
m
ai
n
.
T
h
e
m
eth
o
d
o
lo
g
y
is
ex
p
ec
ted
to
in
clu
d
e
p
r
o
ce
s
s
es
s
u
ch
as
lex
ica
l
s
y
s
tem
an
aly
s
is
,
ter
m
in
o
lo
g
ical
d
ata
class
if
icatio
n
,
an
d
t
h
e
in
teg
r
atio
n
o
f
t
h
e
th
esau
r
u
s
in
to
e
x
is
tin
g
in
f
o
r
m
atio
n
r
etr
iev
al
s
y
s
tem
s
.
T
h
e
p
ap
er
lik
ely
p
r
e
s
en
ts
f
in
d
in
g
s
r
eg
ar
d
in
g
th
e
ef
f
ec
tiv
en
ess
o
f
th
e
in
f
o
r
m
atio
n
r
etr
iev
al
th
esau
r
u
s
in
im
p
r
o
v
i
n
g
s
ea
r
ch
p
r
o
ce
s
s
es
with
in
s
p
ec
if
ic
d
ata
d
o
m
ain
s
.
T
h
is
m
ay
in
clu
d
e
in
s
ig
h
ts
in
t
o
en
h
an
ce
d
s
ea
r
ch
ac
cu
r
ac
y
,
r
ed
u
ce
d
in
f
o
r
m
atio
n
o
v
er
lo
a
d
,
an
d
th
e
alig
n
m
en
t
o
f
u
s
er
q
u
er
ies
with
d
o
c
u
m
en
t
co
n
ten
t,
lead
i
n
g
t
o
more
r
elev
a
n
t sear
ch
r
esu
lts
.
T
h
e
p
r
im
ar
y
o
b
jectiv
e
o
f
th
e
Sch
o
ltes
[
14
]
is
to
in
v
esti
g
ate
th
e
p
o
ten
tial
o
f
u
n
s
u
p
er
v
is
ed
lear
n
in
g
m
eth
o
d
o
l
o
g
ies
in
ad
d
r
ess
in
g
ch
allen
g
es
ass
o
ciate
d
with
in
f
o
r
m
atio
n
r
etr
iev
al.
Giv
en
th
e
co
m
p
lex
ities
an
d
in
tr
icac
ies
o
f
in
f
o
r
m
atio
n
r
etr
iev
al
s
y
s
tem
s
,
th
e
p
ap
er
d
elv
es
in
to
th
e
ap
p
licatio
n
o
f
n
e
u
r
al
n
etwo
r
k
-
b
ased
u
n
s
u
p
er
v
is
ed
lea
r
n
in
g
ap
p
r
o
ac
h
es a
s
a
m
ea
n
s
to
en
h
a
n
ce
r
etr
iev
al
ac
cu
r
ac
y
a
n
d
ef
f
icien
cy
.
T
h
e
p
a
p
er
lik
el
y
p
r
esen
ts
f
in
d
in
g
s
h
ig
h
lig
h
tin
g
th
e
e
f
f
icac
y
o
f
u
n
s
u
p
e
r
v
i
s
ed
lear
n
in
g
tec
h
n
iq
u
es
in
im
p
r
o
v
in
g
v
ar
io
u
s
f
ac
ets
o
f
in
f
o
r
m
atio
n
r
etr
iev
al,
s
u
ch
as
E
n
h
an
ce
d
r
etr
ie
v
al
ac
cu
r
a
cy
th
r
o
u
g
h
n
e
u
r
al
n
etwo
r
k
-
b
ased
m
o
d
els,
Po
te
n
tial
f
o
r
au
t
o
m
ated
f
ea
t
u
r
e
ex
tr
ac
tio
n
a
n
d
r
e
p
r
esen
tatio
n
lear
n
in
g
,
an
d
a
d
ap
tab
ilit
y
an
d
s
ca
lab
ilit
y
o
f
u
n
s
u
p
er
v
is
ed
lea
r
n
in
g
ap
p
r
o
ac
h
es in
d
iv
er
s
e
r
etr
iev
al
s
ce
n
a
r
io
s
.
B
en
ed
etto
et
a
l.
[
15
]
id
e
n
tif
y
th
e
b
u
r
g
eo
n
i
n
g
is
s
u
e
o
f
in
f
o
r
m
atio
n
o
v
e
r
lo
ad
with
in
ed
u
ca
tio
n
al
tech
n
o
lo
g
y
s
y
s
tem
s
,
wh
er
ein
lear
n
er
s
ar
e
in
u
n
d
ated
with
v
a
s
t
am
o
u
n
ts
o
f
co
n
ten
t,
o
f
ten
l
ea
d
in
g
to
co
g
n
itiv
e
o
v
er
wh
elm
an
d
r
e
d
u
ce
d
lear
n
in
g
ef
f
icac
y
.
T
h
e
au
th
o
r
s
h
ig
h
lig
h
t
th
e
in
h
er
en
t
co
m
p
le
x
ities
in
n
av
ig
atin
g
ex
p
an
s
iv
e
co
n
ten
t
r
ep
o
s
ito
r
ies,
em
p
h
asizin
g
th
e
n
ee
d
f
o
r
in
n
o
v
ativ
e
s
o
lu
tio
n
s
to
s
tr
e
am
lin
e
in
f
o
r
m
atio
n
d
eliv
er
y
an
d
p
r
o
m
o
te
e
f
f
ec
tiv
e
lea
r
n
in
g
.
T
o
ad
d
r
ess
th
e
af
o
r
em
e
n
tio
n
ed
ch
allen
g
es,
au
th
o
r
s
ad
v
o
ca
te
f
o
r
t
h
e
in
teg
r
atio
n
o
f
ad
v
an
ce
d
s
u
m
m
ar
izatio
n
tech
n
iq
u
es
with
in
ed
u
ca
tio
n
al
p
latf
o
r
m
s
.
T
h
e
au
th
o
r
s
p
r
o
p
o
s
e
th
e
d
ev
elo
p
m
e
n
t
an
d
im
p
lem
en
tatio
n
o
f
tailo
r
ed
s
u
m
m
ar
izatio
n
alg
o
r
ith
m
s
ca
p
a
b
le
o
f
d
is
till
in
g
co
m
p
lex
e
d
u
c
atio
n
al
co
n
ten
t
in
to
co
n
cise
an
d
d
ig
esti
b
le
s
u
m
m
ar
ies
with
o
u
t
co
m
p
r
o
m
is
in
g
ess
en
tial
in
f
o
r
m
atio
n
.
B
y
lev
er
ag
in
g
th
ese
s
u
m
m
ar
izatio
n
m
eth
o
d
o
lo
g
ies
,
th
e
au
th
o
r
s
co
n
ten
d
th
at
ed
u
ca
tio
n
al
tech
n
o
lo
g
y
s
y
s
tem
s
ca
n
f
ac
ilit
ate
m
o
r
e
ef
f
icien
t
co
n
ten
t
n
av
ig
atio
n
,
e
n
h
an
ce
u
s
er
e
n
g
ag
em
e
n
t,
an
d
f
o
s
ter
an
ad
ap
tiv
e
lea
r
n
in
g
e
n
v
ir
o
n
m
e
n
t
tailo
r
ed
to
d
iv
er
s
e
lear
n
e
r
n
ee
d
s
.
Ak
s
o
n
o
v
et
a
l.
[
16
]
h
i
g
h
lig
h
t
th
e
p
er
v
asiv
e
ch
allen
g
e
o
f
in
f
o
r
m
atio
n
o
v
er
lo
a
d
,
wh
er
ein
t
r
ad
itio
n
al
q
u
esti
o
n
-
an
s
wer
in
g
s
y
s
tem
s
g
r
ap
p
l
e
with
t
h
e
in
tr
icac
ies
o
f
p
r
o
ce
s
s
in
g
a
n
d
r
etr
iev
in
g
r
elev
an
t
in
f
o
r
m
atio
n
f
r
o
m
ex
p
a
n
s
iv
e
d
ata
r
ep
o
s
ito
r
ies.
T
h
e
au
th
o
r
s
id
en
tify
in
h
er
en
t
s
ca
lab
ilit
y
co
n
s
tr
ain
ts
with
in
ex
is
t
in
g
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
I
SS
N:
2252
-
8
7
7
6
A
crit
ica
l revie
w
o
f in
fo
r
ma
tio
n
r
etri
ev
a
l te
ch
n
iq
u
es:
cu
r
r
en
t tren
d
s
…
(
S
a
n
ke
t D
.
P
a
til
)
459
q
u
esti
o
n
-
an
s
wer
in
g
s
y
s
tem
s
,
em
p
h
asizin
g
th
e
lim
itatio
n
s
i
n
ef
f
icien
tly
p
r
o
ce
s
s
i
n
g
in
c
r
e
asin
g
d
ata
v
o
l
u
m
es
with
o
u
t
co
m
p
r
o
m
is
in
g
s
y
s
tem
p
er
f
o
r
m
an
ce
.
Au
th
o
r
s
elu
cid
ate
th
e
co
m
p
lex
ities
ass
o
ciate
d
with
h
eter
o
g
en
e
o
u
s
d
ata
s
o
u
r
ce
s
an
d
f
o
r
m
ats,
u
n
d
e
r
s
co
r
in
g
t
h
e
c
h
allen
g
es
in
h
ar
m
o
n
izin
g
d
is
p
ar
ate
d
ata
elem
en
ts
to
f
ac
ilit
ate
co
h
er
en
t
q
u
esti
o
n
-
an
s
wer
in
g
p
r
o
ce
s
s
es.
T
h
e
r
e
s
e
a
r
c
h
c
o
n
d
u
c
t
e
d
b
y
t
h
e
a
u
t
h
o
r
s
o
f
f
e
r
s
a
s
e
m
i
n
a
l
c
o
n
t
r
i
b
u
t
i
o
n
t
o
t
h
e
d
is
c
o
u
r
s
e
o
n
q
u
e
s
t
i
o
n
-
a
n
s
w
e
r
i
n
g
s
y
s
te
m
s
a
n
d
b
i
g
d
a
t
a
a
n
a
l
y
ti
c
s
.
B
y
e
l
u
ci
d
a
t
i
n
g
t
h
e
c
h
a
l
l
e
n
g
es
o
f
i
n
f
o
r
m
a
t
i
o
n
o
v
e
r
l
o
a
d
,
s
y
s
t
e
m
s
c
a
l
a
b
i
l
it
y
,
a
n
d
d
a
t
a
c
o
m
p
l
e
x
i
t
y
,
a
n
d
p
r
o
p
o
s
i
n
g
i
n
n
o
v
a
t
i
v
e
s
o
l
u
t
i
o
n
s
g
r
o
u
n
d
e
d
i
n
a
d
v
a
n
c
e
d
a
n
a
l
y
t
i
cs
a
n
d
a
d
a
p
t
i
v
e
a
l
g
o
r
i
t
h
m
ic
d
e
s
i
g
n
,
t
h
e
a
u
t
h
o
r
s
p
r
o
v
i
d
e
a
c
o
m
p
r
e
h
e
n
s
i
v
e
f
r
a
m
e
w
o
r
k
f
o
r
h
a
r
n
e
s
s
i
n
g
t
h
e
t
r
a
n
s
f
o
r
m
a
t
i
v
e
p
o
t
e
n
t
i
a
l
o
f
b
i
g
d
a
t
a
i
n
r
e
d
e
f
i
n
in
g
t
h
e
c
a
p
a
b
i
l
i
ti
e
s
a
n
d
e
f
f
i
c
a
c
y
o
f
q
u
e
s
t
i
o
n
-
a
n
s
we
r
i
n
g
s
y
s
t
e
m
s
i
n
t
h
e
d
i
g
it
a
l
a
g
e
.
Xu
[
17
]
id
en
tifie
s
in
h
er
e
n
t
in
ef
f
icien
cies
in
tr
ad
itio
n
al
in
f
o
r
m
atio
n
r
etr
iev
al
m
ec
h
an
is
m
s
,
em
p
h
asizin
g
c
h
allen
g
es
in
p
r
io
r
itizin
g
an
d
r
a
n
k
in
g
in
f
o
r
m
atio
n
b
ased
o
n
r
elev
an
ce
an
d
s
ig
n
if
ican
ce
.
T
h
e
au
th
o
r
elu
cid
ates
th
e
ch
allen
g
es
p
o
s
ed
b
y
s
em
an
tic
am
b
ig
u
ities
an
d
co
n
tex
tu
al
v
ar
iab
ilit
y
with
in
tex
tu
al
d
ata,
h
ig
h
lig
h
tin
g
th
e
co
m
p
lex
ities
ass
o
ciate
d
with
d
ec
ip
h
er
in
g
a
n
d
in
ter
p
r
etin
g
in
f
o
r
m
atio
n
in
d
iv
er
s
e
co
n
tex
ts
.
T
o
ad
d
r
ess
th
e
id
e
n
tifie
d
c
h
allen
g
es,
au
th
o
r
ad
v
o
ca
tes
f
o
r
th
e
in
teg
r
atio
n
o
f
th
e
T
ex
tR
an
k
alg
o
r
ith
m
,
a
g
r
ap
h
-
b
ased
r
an
k
in
g
m
o
d
el
in
s
p
ir
ed
b
y
th
e
Pag
eRan
k
alg
o
r
ith
m
.
B
y
elu
cid
atin
g
th
e
ch
allen
g
es
ass
o
ciate
d
with
tr
ad
itio
n
al
r
etr
iev
al
m
ec
h
an
is
m
s
an
d
p
r
o
p
o
s
in
g
an
in
n
o
v
ativ
e
s
o
lu
tio
n
g
r
o
u
n
d
ed
in
g
r
ap
h
-
b
ased
r
a
n
k
in
g
an
d
s
em
an
tic
an
aly
s
is
,
th
e
au
th
o
r
p
r
o
v
id
es
a
c
o
m
p
r
e
h
en
s
iv
e
f
r
am
ewo
r
k
f
o
r
h
a
r
n
ess
in
g
th
e
tr
an
s
f
o
r
m
ativ
e
p
o
ten
tial o
f
T
e
x
tR
an
k
in
r
e
d
ef
in
in
g
th
e
lan
d
s
ca
p
e
o
f
in
f
o
r
m
a
tio
n
r
etr
iev
al
in
t
h
e
d
ig
ital a
g
e
.
T
h
e
p
r
o
b
lem
id
en
tifie
d
b
y
Kan
h
aiy
a
et
a
l.
[
18
]
u
n
d
er
s
c
o
r
es
th
e
m
u
ltifa
ce
ted
n
atu
r
e
o
f
leg
al
ju
d
g
m
en
ts
,
ch
ar
ac
ter
ize
d
b
y
in
tr
icate
leg
al
ter
m
in
o
lo
g
ies,
n
u
an
ce
d
in
ter
p
r
etatio
n
s
,
an
d
co
n
tex
tu
al
d
ep
en
d
e
n
cies.
T
h
e
au
th
o
r
s
h
i
g
h
lig
h
t
th
e
ch
allen
g
es
p
o
s
ed
b
y
th
e
in
h
er
e
n
t
co
m
p
lex
ities
o
f
leg
al
lan
g
u
ag
e
,
em
p
h
asizin
g
th
e
lim
itatio
n
s
o
f
tr
ad
itio
n
al
i
n
f
o
r
m
atio
n
r
et
r
iev
al
m
ec
h
an
is
m
s
in
ef
f
ec
ti
v
ely
n
av
i
g
atin
g
an
d
ex
tr
ac
tin
g
p
er
tin
e
n
t
in
f
o
r
m
atio
n
f
r
o
m
ju
d
g
em
e
n
ts
T
h
e
au
t
h
o
r
s
id
en
tify
in
h
er
en
t
in
ef
f
icien
cies
in
ex
is
tin
g
in
f
o
r
m
atio
n
r
etr
iev
al
s
y
s
tem
s
with
in
th
e
leg
al
d
o
m
ain
an
d
t
h
e
ch
allen
g
es
ar
is
in
g
f
r
o
m
s
e
m
an
tic
am
b
ig
u
ities
an
d
co
n
te
x
tu
al
v
ar
ia
b
ilit
y
in
h
er
en
t
in
leg
al
j
u
d
g
em
e
n
ts
,
u
n
d
er
s
co
r
i
n
g
th
e
c
o
m
p
lex
itie
s
ass
o
ciate
d
with
d
ec
ip
h
er
in
g
an
d
in
ter
p
r
eti
n
g
l
eg
al
lan
g
u
a
g
e
in
d
i
v
er
s
e
co
n
te
x
ts
.
T
o
ad
d
r
ess
th
e
id
en
tifie
d
ch
allen
g
es,
K
an
h
aiy
a
et
al.
p
r
o
p
o
s
e
th
e
d
ev
elo
p
m
en
t
o
f
an
A
I
-
en
ab
led
in
f
o
r
m
atio
n
r
etr
ie
v
al
en
g
i
n
e
(
AI
-
I
R
E
)
s
p
ec
if
ically
tailo
r
e
d
f
o
r
leg
al
s
er
v
ices.
T
h
e
au
th
o
r
s
d
elin
ea
te
t
h
e
ar
ch
itectu
r
e
an
d
f
u
n
ctio
n
alities
o
f
AI
-
I
R
E
,
em
p
h
asizin
g
its
ca
p
ab
ilit
y
to
in
teg
r
ate
ex
p
er
t
-
an
n
o
tated
n
at
u
r
al
lan
g
u
ag
e
p
r
o
ce
s
s
in
g
(
NL
P
)
te
ch
n
iq
u
es
with
ad
v
a
n
ce
d
m
ac
h
in
e
lear
n
in
g
alg
o
r
ith
m
s
to
f
ac
i
litate
ef
f
icien
t
an
d
co
n
tex
tu
ally
r
ele
v
an
t in
f
o
r
m
at
io
n
r
etr
iev
al
f
r
o
m
le
g
al
ju
d
g
e
m
en
ts
.
I
n
t
h
e
e
r
a
o
f
b
i
g
d
at
a
,
t
h
e
d
ev
e
l
o
p
m
e
n
t
o
f
r
o
b
u
s
t
a
n
d
s
c
ala
b
l
e
i
n
f
o
r
m
a
t
i
o
n
r
et
r
i
e
v
a
l
f
r
am
e
w
o
r
k
s
is
p
a
r
a
m
o
u
n
t
t
o
e
f
f
i
ci
e
n
t
l
y
n
a
v
i
g
a
t
e
a
n
d
e
x
t
r
a
c
t
m
e
a
n
i
n
g
f
u
l
i
n
s
ig
h
t
s
f
r
o
m
v
as
t
a
n
d
h
e
t
e
r
o
g
e
n
e
o
u
s
d
a
t
a
r
e
p
o
s
i
t
o
r
i
es
.
N
g
u
y
e
n
e
t
a
l
.
[
19
]
e
m
b
a
r
k
o
n
a
c
o
m
p
r
e
h
e
n
s
i
v
e
e
x
p
l
o
r
a
ti
o
n
i
n
t
o
t
h
e
i
n
t
r
i
c
a
c
i
es
o
f
c
r
a
f
ti
n
g
s
u
c
h
f
r
a
m
e
w
o
r
k
s
t
a
i
l
o
r
e
d
f
o
r
t
h
e
b
i
g
d
a
t
a
la
n
d
s
c
a
p
e
.
A
u
t
h
o
r
s
i
d
e
n
t
i
f
y
i
n
h
e
r
e
n
t
c
h
a
l
l
e
n
g
es
a
s
s
o
c
i
at
e
d
w
i
t
h
s
c
a
l
a
b
il
i
t
y
a
n
d
p
e
r
f
o
r
m
a
n
c
e
l
i
m
i
t
a
ti
o
n
s
w
it
h
i
n
e
x
i
s
t
i
n
g
i
n
f
o
r
m
a
t
i
o
n
r
e
t
r
i
e
v
a
l
f
r
a
m
e
w
o
r
k
s
,
p
a
r
t
i
c
u
la
r
l
y
i
n
t
h
e
c
o
n
t
e
x
t
o
f
b
i
g
d
a
t
a
.
T
h
e
c
o
m
p
l
e
x
i
t
i
es
a
r
i
s
i
n
g
f
r
o
m
t
h
e
h
e
t
e
r
o
g
e
n
e
i
t
y
a
n
d
i
n
h
e
r
en
t
v
a
r
i
a
b
i
l
it
y
o
f
b
i
g
d
a
t
a
e
m
p
h
a
s
i
z
e
c
h
a
l
l
e
n
g
es
i
n
h
a
r
m
o
n
i
z
i
n
g
d
i
v
e
r
s
e
d
a
t
a
t
y
p
e
s
,
s
t
r
u
c
t
u
r
es
,
a
n
d
f
o
r
m
a
t
s
w
i
t
h
in
t
r
a
d
i
t
i
o
n
a
l
r
e
t
r
i
e
v
a
l
f
r
a
m
e
w
o
r
k
s
.
T
h
e
c
h
a
l
l
e
n
g
e
s
p
o
s
e
d
b
y
e
n
s
u
r
i
n
g
r
o
b
u
s
t
n
e
s
s
a
n
d
r
e
l
i
a
b
i
l
i
t
y
wi
t
h
i
n
b
i
g
d
a
t
a
i
n
f
o
r
m
a
t
i
o
n
r
e
t
r
i
e
v
a
l
f
r
a
m
e
wo
r
k
s
,
p
a
r
t
i
c
u
l
a
r
l
y
i
n
m
i
t
i
g
a
ti
n
g
r
i
s
k
s
a
s
s
o
c
i
at
e
d
w
ith
d
a
t
a
i
n
c
o
n
s
is
t
e
n
ci
e
s
,
r
e
d
u
n
d
an
c
i
e
s
,
a
n
d
i
n
a
cc
u
r
a
c
i
es
.
T
o
ad
d
r
ess
th
e
id
en
tifie
d
c
h
allen
g
es,
th
e
au
th
o
r
s
p
r
o
p
o
s
e
t
h
e
d
ev
elo
p
m
en
t
o
f
a
r
o
b
u
s
t
in
f
o
r
m
atio
n
r
etr
iev
al
f
r
am
ew
o
r
k
tailo
r
ed
f
o
r
b
ig
d
ata
co
n
tex
ts
.
T
h
e
a
u
th
o
r
s
ad
v
o
ca
te
f
o
r
th
e
in
teg
r
atio
n
o
f
in
n
o
v
ativ
e
alg
o
r
ith
m
s
d
esig
n
ed
to
ad
d
r
ess
th
e
co
m
p
lex
ities
o
f
h
eter
o
g
en
eo
u
s
d
ata
p
r
o
ce
s
s
in
g
with
in
b
ig
d
ata
en
v
ir
o
n
m
en
ts
.
T
h
e
in
teg
r
atio
n
o
f
r
esil
ien
ce
an
d
tr
u
s
two
r
th
in
ess
m
ec
h
an
is
m
s
with
in
th
e
p
r
o
p
o
s
ed
f
r
am
ewo
r
k
aim
s
to
m
itig
ate
r
is
k
s
ass
o
c
iated
with
d
ata
in
co
n
s
is
ten
cies
an
d
in
ac
cu
r
ac
ies.
T
h
e
au
t
h
o
r
s
h
ig
h
lig
h
t
th
e
im
p
lem
en
tatio
n
o
f
ad
v
an
ce
d
v
alid
atio
n
,
v
er
if
icatio
n
,
an
d
e
r
r
o
r
-
c
o
r
r
ec
tio
n
m
ec
h
a
n
is
m
s
to
f
o
s
ter
co
n
s
is
ten
t,
ac
cu
r
ate,
an
d
r
eliab
le
r
etr
iev
a
l
o
u
tco
m
es,
th
er
eb
y
e
n
s
u
r
in
g
th
e
in
t
eg
r
ity
an
d
tr
u
s
two
r
th
i
n
ess
o
f
in
f
o
r
m
atio
n
ac
ce
s
s
ed
with
in
b
ig
d
ata
co
n
tex
ts
.
I
n
th
e
d
o
m
ai
n
o
f
in
f
o
r
m
atio
n
r
etr
iev
al
s
y
s
tem
s
,
th
e
g
en
er
a
tio
n
o
f
h
ig
h
-
q
u
ality
,
r
elev
an
t
ju
d
g
m
en
ts
s
tan
d
s
as
a
cr
itical
co
m
p
o
n
en
t
in
ev
alu
atin
g
s
y
s
tem
ef
f
icac
y
an
d
p
er
f
o
r
m
an
ce
.
J
o
s
ep
h
a
n
d
R
av
an
a
[
20
]
d
elv
e
in
to
th
e
in
tr
icac
ies
o
f
en
h
an
c
in
g
th
e
ev
alu
atio
n
p
r
o
ce
s
s
b
y
lev
er
ag
in
g
d
o
cu
m
e
n
t
s
im
ilar
ity
an
d
d
o
cu
m
en
t
p
o
o
lin
g
tec
h
n
iq
u
es.
Au
t
h
o
r
s
id
en
tify
in
h
e
r
en
t
lim
itatio
n
s
ass
o
ciate
d
with
co
n
v
en
tio
n
al
ev
alu
atio
n
m
etr
ics
u
tili
ze
d
in
ass
ess
i
n
g
in
f
o
r
m
atio
n
r
etr
iev
al
s
y
s
tem
s
,
ch
allen
g
es
s
tem
m
in
g
f
r
o
m
am
b
ig
u
ities
an
d
in
co
n
s
is
ten
cies
p
r
ev
alen
t
in
m
an
u
al
r
elev
an
ce
j
u
d
g
m
e
n
ts
,
an
d
th
e
n
ec
ess
ity
f
o
r
a
d
v
an
cin
g
ev
alu
atio
n
m
eth
o
d
o
l
o
g
ies to
f
o
s
ter
e
n
h
an
ce
d
ef
f
icac
y
,
in
s
ig
h
tf
u
ln
ess
,
a
n
d
ac
tio
n
a
b
le
in
s
ig
h
t
s.
T
o
ad
d
r
ess
th
e
id
e
n
tifie
d
ch
all
en
g
es,
th
e
au
th
o
r
s
ad
v
o
ca
te
f
o
r
th
e
in
teg
r
atio
n
o
f
d
o
cu
m
e
n
t
s
im
ilar
ity
tech
n
iq
u
es
with
in
th
e
ev
alu
at
io
n
f
r
am
ewo
r
k
,
th
e
im
p
lem
en
tatio
n
o
f
d
o
cu
m
en
t
p
o
o
lin
g
te
ch
n
iq
u
es
aim
ed
at
en
h
an
cin
g
th
e
g
e
n
er
atio
n
o
f
r
elev
an
ce
ju
d
g
m
en
ts
,
an
d
th
e
d
ep
lo
y
m
e
n
t
o
f
d
o
cu
m
en
t
s
im
ilar
ity
an
d
p
o
o
li
ng
tech
n
iq
u
es
is
p
o
s
ited
to
ad
v
an
ce
ex
is
tin
g
ev
alu
atio
n
p
ar
ad
ig
m
s
b
y
f
o
s
ter
in
g
en
h
an
ce
d
g
r
a
n
u
lar
ity
,
ac
cu
r
ac
y
,
an
d
co
n
tex
tu
ality
in
r
elev
an
ce
ju
d
g
m
en
ts
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
7
7
6
I
n
t J I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
,
Vo
l.
1
5
,
No
.
2
,
J
u
n
e
20
2
6
:
4
5
6
-
4
6
4
460
Sriv
ar
s
h
a
an
d
Ma
n
ik
an
d
an
[
21
]
tack
led
th
e
ch
allen
g
e
o
f
c
o
n
ten
t
-
b
ased
im
ag
e
r
etr
ie
v
al
(
C
B
I
R
)
b
y
in
teg
r
at
in
g
te
x
tu
al
in
f
o
r
m
atio
n
.
R
ec
o
g
n
izin
g
th
e
in
h
e
r
en
t
li
m
itatio
n
s
o
f
c
o
n
v
e
n
tio
n
al
C
B
I
R
s
y
s
tem
s
th
at
r
ely
s
o
lely
o
n
v
is
u
al
f
ea
tu
r
es,
th
e
au
th
o
r
s
h
ig
h
lig
h
ted
th
e
p
o
ten
t
ial
o
f
tex
tu
al
d
ata
in
en
h
an
cin
g
r
etr
iev
al
ac
cu
r
ac
y
an
d
r
elev
an
ce
.
A
p
r
im
ar
y
p
r
o
b
lem
th
ey
ad
d
r
ess
ed
was
th
e
d
if
f
icu
lty
u
s
er
s
o
f
te
n
f
ac
e
wh
en
tr
y
i
n
g
to
r
etr
iev
e
s
p
ec
if
ic
im
ag
es b
ased
o
n
v
is
u
al
co
n
ten
t a
lo
n
e,
esp
ec
ially
wh
en
im
ag
es m
ig
h
t b
e
am
b
i
g
u
o
u
s
o
r
wh
en
s
em
an
ti
c
co
n
tex
t is cr
u
cial.
T
o
b
r
id
g
e
th
is
g
ap
,
th
e
a
u
th
o
r
s
in
tr
o
d
u
ce
d
a
n
o
v
el
s
ch
e
m
e
th
at
h
ar
n
ess
ed
tex
tu
al
in
f
o
r
m
atio
n
ass
o
ciate
d
with
im
ag
es.
B
y
l
ev
er
ag
in
g
tex
tu
al
m
etad
ata,
a
n
n
o
tatio
n
s
,
o
r
ac
c
o
m
p
a
n
y
in
g
d
escr
ip
tio
n
s
,
th
ei
r
s
ch
em
e
aim
ed
to
p
r
o
v
id
e
a
r
ic
h
er
,
co
n
te
x
tu
ally
r
elev
an
t
s
et
o
f
r
esu
lts
.
T
h
e
in
teg
r
atio
n
o
f
t
ex
tu
al
in
f
o
r
m
ati
o
n
o
f
f
er
ed
u
s
e
r
s
a
m
o
r
e
n
u
an
ce
d
an
d
p
r
e
cise
m
ec
h
an
is
m
to
r
etr
iev
e
im
ag
es,
esp
ec
ially
in
s
ce
n
ar
io
s
wh
er
e
v
is
u
al
cu
es
m
ig
h
t
b
e
in
s
u
f
f
icien
t
o
r
m
is
lead
in
g
.
Ov
er
all,
th
eir
r
e
s
ea
r
ch
u
n
d
er
s
co
r
e
d
th
e
s
y
n
er
g
is
tic
p
o
ten
tial
o
f
co
m
b
in
in
g
v
is
u
al
a
n
d
te
x
tu
al
d
ata
in
a
d
v
an
cin
g
th
e
c
ap
ab
ilit
ies
an
d
ac
cu
r
ac
y
o
f
c
o
n
ten
t
-
b
a
s
ed
im
ag
e
r
etr
ie
v
al
s
y
s
tem
s
.
Acc
o
r
d
in
g
to
Vek
ar
i
y
a
an
d
L
im
b
asiy
a
[
22
]
,
th
e
p
r
o
ce
s
s
in
g
o
f
q
u
esti
o
n
s
a
n
d
ex
ce
llen
t
r
esp
o
n
s
e
p
r
o
ce
s
s
in
g
is
th
e
m
ain
f
u
n
cti
o
n
o
f
th
e
q
u
esti
o
n
-
an
s
wer
in
g
s
y
s
tem
.
Ad
d
itio
n
ally
,
th
e
s
tu
d
y
co
n
ten
d
s
th
at
th
e
p
r
ec
is
e
r
an
g
e
o
f
q
u
esti
o
n
s
th
at
ex
ce
llen
t
r
esp
o
n
s
es
p
r
o
v
id
e
is
th
e
m
ai
n
is
s
u
e
with
q
u
esti
o
n
an
s
wer
in
g
.
Fu
r
th
er
m
o
r
e
,
b
y
u
s
in
g
th
is
,
i
t
o
u
g
h
t
to
tak
e
less
tim
e
to
f
in
d
a
s
im
ilar
q
u
er
y
an
d
an
ex
ce
llen
t
s
o
lu
tio
n
.
No
n
eth
eless
,
o
b
tain
in
g
ac
c
u
r
a
te
d
at
a
is
ess
en
tial.
T
h
er
ef
o
r
e
,
t
h
e
r
es
ea
r
c
h
s
u
g
g
es
ts
u
s
i
n
g
tw
o
d
is
t
in
ct
i
n
f
o
r
m
at
i
o
n
r
et
r
ie
v
a
l
s
t
r
at
eg
ies
i
n
o
r
d
er
t
o
o
b
tai
n
th
e
a
p
p
r
o
p
r
iat
e
an
d
h
i
g
h
l
y
ac
c
u
r
at
e
r
e
p
li
es.
T
h
e
s
t
u
d
y
s
u
g
g
es
ts
u
s
in
g
th
e
d
e
ep
l
o
n
g
s
h
o
r
t
-
te
r
m
m
e
m
o
r
y
m
et
h
o
d
wit
h
v
e
r
s
at
ile
g
lo
b
al
T
-
m
a
x
p
o
o
li
n
g
f
o
r
k
n
o
wle
d
g
e
r
et
r
ie
v
a
l
.
Usi
n
g
w
o
r
d
2
v
e
c
,
t
h
e
w
o
r
d
s
a
r
e
f
i
r
s
t
tr
a
n
s
f
o
r
m
ed
in
t
o
v
ec
t
o
r
s
.
Af
te
r
t
h
at
,
i
n
f
o
r
m
at
io
n
r
e
tr
ie
v
a
l
is
ac
c
o
m
p
lis
h
e
d
u
s
i
n
g
t
h
ese
tw
o
m
et
h
o
d
s
.
T
h
e
a
r
t
icl
e
t
h
en
s
u
g
g
ests
r
a
n
k
i
n
g
t
h
e
o
u
t
p
u
t
f
r
o
m
t
h
ese
tw
o
s
y
s
te
m
s
b
y
u
s
in
g
a
d
ee
p
f
a
ct
o
r
i
za
ti
o
n
m
ac
h
i
n
e
.
T
h
e
r
es
p
o
n
s
e
t
h
a
t
is
d
ee
m
e
d
t
o
b
e
th
e
m
o
s
t
e
f
f
ici
en
t
is
c
h
o
s
e
n
.
I
n
o
r
d
e
r
t
o
ass
es
s
th
e
e
f
f
ec
ti
v
e
n
ess
o
f
t
h
e
s
u
g
g
este
d
a
p
p
r
o
ac
h
,
t
h
e
r
es
ea
r
c
h
s
u
g
g
ests
u
s
i
n
g
t
h
r
ee
d
is
t
in
ct
d
atas
ets
.
B
e
f
o
r
e
test
in
g
th
e
s
y
s
t
em
,
th
e
p
ap
er
p
e
r
f
o
r
m
s
a
n
a
n
al
y
s
is
o
f
d
i
f
f
er
e
n
t
wo
r
d
em
b
ed
d
i
n
g
te
ch
n
i
q
u
es
o
n
t
h
e
t
h
r
ee
d
at
asets
i
d
en
t
if
ie
d
f
o
r
e
x
p
e
r
i
m
e
n
t
ati
o
n
.
T
h
e
p
u
b
licatio
n
s
tates
th
at
it
h
as
attain
ed
v
er
y
ex
ce
llen
t
ac
cu
r
ac
y
,
with
o
v
e
r
8
0
%
ac
cu
r
ac
y
.
Ho
wev
er
,
th
e
s
tu
d
y
o
m
its
to
d
escr
ib
e
th
e
s
y
s
tem
ar
ch
itectu
r
e
in
d
ep
th
.
I
n
o
th
e
r
wo
r
d
s
,
w
h
ile
th
e
p
u
b
licatio
n
n
o
tes
th
e
u
s
ag
e
o
f
d
ee
p
lo
n
g
s
h
o
r
t
-
ter
m
m
em
o
r
y
,
it
with
h
o
ld
s
in
f
o
r
m
atio
n
ab
o
u
t
th
e
n
etwo
r
k
'
s
p
r
ec
is
e
d
esig
n
,
in
clu
d
in
g
d
etails
ab
o
u
t
th
e
n
u
m
b
er
o
f
n
e
u
r
o
n
s
em
p
lo
y
e
d
an
d
th
e
n
etwo
r
k
'
s
d
ep
th
.
Fu
r
th
e
r
m
o
r
e,
t
h
e
r
elati
v
e
im
p
ac
t
o
f
th
e
p
o
o
lin
g
lay
er
i
n
th
e
f
in
al
class
if
icatio
n
is
u
n
clea
r
d
u
e
to
t
h
e
co
n
c
u
r
r
e
n
t
u
s
e
o
f
th
e
v
er
s
atile
g
lo
b
al
T
-
m
ax
p
o
o
lin
g
a
n
d
d
ee
p
lo
n
g
s
h
o
r
t
-
ter
m
m
em
o
r
y
ap
p
r
o
ac
h
es
.
T
h
e
p
a
p
er
d
o
es
n
o
t
d
is
cu
s
s
wh
eth
er
o
r
n
o
t ta
b
les an
d
im
a
g
es a
r
e
r
etai
n
ed
.
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
T
ab
le
1
p
r
o
v
id
es
th
e
an
aly
s
is
o
f
all
th
e
p
ap
er
s
r
ev
iewe
d
in
th
e
p
r
ev
io
u
s
s
ec
tio
n
.
T
h
e
s
aid
an
aly
s
is
h
as
b
ee
n
co
n
d
u
cted
o
n
th
e
f
o
llo
win
g
p
ar
am
eter
s
:
tech
n
o
l
o
g
y
u
s
ed
,
d
o
m
ai
n
o
f
s
tu
d
y
,
r
etr
iev
al
o
f
o
r
i
g
in
al
tab
le,
r
etr
iev
al
o
f
o
r
ig
in
al
p
i
ctu
r
es,
an
d
k
ey
f
in
d
in
g
s
o
f
th
e
p
ap
er
s
.
T
h
e
tab
le
p
r
o
v
i
d
e
s
a
co
m
p
r
eh
en
s
iv
e
s
u
m
m
ar
y
o
f
1
8
ac
ad
em
ic
p
ap
er
s
,
ea
ch
em
p
lo
y
in
g
d
if
f
e
r
en
t
tech
n
o
lo
g
ies
to
en
h
an
ce
in
f
o
r
m
atio
n
r
etr
iev
al
an
d
r
elate
d
p
r
o
ce
s
s
es
ac
r
o
s
s
v
ar
io
u
s
d
o
m
ain
s
.
T
h
e
k
ey
f
in
d
i
n
g
s
ar
e
g
r
o
u
p
e
d
ac
c
o
r
d
in
g
to
th
e
t
ec
h
n
o
lo
g
y
u
s
ed
an
d
th
e
s
p
ec
if
ic
d
o
m
ain
o
f
a
p
p
lica
tio
n
.
Firstl
y
,
p
ap
er
s
u
tili
zin
g
c
o
s
in
e
Similar
ity
r
ep
o
r
t
s
ig
n
i
f
ican
t
a
d
v
an
ce
m
e
n
ts
.
I
n
th
e
d
o
m
ai
n
o
f
QA,
th
e
in
teg
r
atio
n
o
f
in
f
o
r
m
atio
n
r
e
tr
iev
al
with
d
ee
p
lear
n
in
g
tech
n
iq
u
es
h
as
s
h
o
wn
to
s
ig
n
i
f
ican
tly
b
o
o
s
t
th
e
p
er
f
o
r
m
an
ce
o
f
QA
s
y
s
tem
s
.
Similar
ly
,
in
th
e
f
ield
o
f
e
d
u
ca
tio
n
,
th
e
u
s
e
o
f
s
u
m
m
ar
izat
io
n
tech
n
iq
u
es
h
as
b
ee
n
f
o
u
n
d
to
en
h
an
ce
ed
u
ca
tio
n
al
tech
n
o
lo
g
y
s
y
s
tem
s
.
R
ec
u
r
r
en
t
n
eu
r
al
n
etwo
r
k
s
(
R
NN)
h
av
e
b
ee
n
ap
p
lied
in
th
e
leg
al
QA
d
o
m
ain
,
wh
er
e
th
e
im
p
lem
en
tatio
n
o
f
d
ee
p
lear
n
in
g
m
eth
o
d
s
h
as
im
p
r
o
v
e
d
th
e
ac
cu
r
ac
y
o
f
leg
al
q
u
esti
o
n
-
an
s
wer
in
g
s
y
s
tem
s
.
T
h
is
h
ig
h
lig
h
ts
th
e
p
o
ten
tial o
f
R
NNs in
h
an
d
lin
g
co
m
p
lex
l
eg
al
tex
ts
an
d
p
r
o
v
id
i
n
g
p
r
ec
is
e
an
s
wer
s
.
Sev
er
al
p
ap
er
s
f
o
cu
s
o
n
th
e
u
s
e
o
f
lo
n
g
s
h
o
r
t
-
ter
m
m
e
m
o
r
y
(
L
STM
)
n
etwo
r
k
s
.
I
n
R
ec
o
m
m
en
d
atio
n
Sy
s
tem
s
,
L
STM
h
as
en
h
an
ce
d
r
etr
iev
al
alg
o
r
ith
m
s
,
lead
in
g
to
b
etter
r
ec
o
m
m
en
d
atio
n
s
.
W
ith
in
QA
s
y
s
tem
s
,
b
ig
d
ata
an
aly
s
is
h
as
f
ac
ilit
ated
th
e
d
ev
el
o
p
m
en
t
o
f
m
o
r
e
ef
f
ec
tiv
e
QA
f
r
am
ewo
r
k
s
.
Fu
r
t
h
er
m
o
r
e,
a
p
r
o
p
o
s
ed
f
r
am
ewo
r
k
f
o
r
s
ca
lab
le
in
f
o
r
m
atio
n
r
etr
iev
al
in
b
ig
d
ata
c
o
n
tex
ts
an
d
an
o
t
h
er
ap
p
licatio
n
in
co
n
te
n
t
-
b
ased
im
ag
e
r
etr
iev
al
u
n
d
er
s
co
r
e
th
e
v
er
s
atility
an
d
ef
f
ec
tiv
e
n
ess
o
f
L
STM
in
v
ar
io
u
s
r
etr
iev
al
ta
s
k
s
.
T
h
e
u
s
e
o
f
t
h
esau
r
u
s
g
en
er
a
tio
n
in
s
ea
r
ch
e
n
g
in
es
h
as
d
em
o
n
s
tr
ated
im
p
r
o
v
e
m
en
ts
i
n
r
etr
iev
al
tech
n
o
lo
g
ies
with
in
s
p
ec
if
ic
d
ata
d
o
m
ain
s
.
T
h
is
s
u
g
g
ests
th
a
t
th
esau
r
u
s
-
b
ased
ap
p
r
o
ac
h
es c
an
en
h
an
ce
s
ea
r
ch
p
r
ec
is
io
n
an
d
r
elev
an
ce
.
Ne
u
r
al
n
etwo
r
k
s
h
av
e
b
ee
n
ap
p
lied
to
f
r
ee
tex
t
d
ata
b
ase
s
ea
r
ch
,
wh
er
e
u
n
s
u
p
e
r
v
i
s
ed
lear
n
in
g
tec
h
n
iq
u
es
h
av
e
ad
d
r
ess
ed
k
ey
c
h
allen
g
es
in
in
f
o
r
m
atio
n
r
etr
ie
v
al.
T
h
is
in
d
icat
es
th
e
p
o
ten
tial
f
o
r
n
eu
r
al
n
etwo
r
k
s
to
m
an
a
g
e
an
d
in
ter
p
r
et
v
ast am
o
u
n
ts
o
f
u
n
s
tr
u
ctu
r
ed
d
ata.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
I
SS
N:
2252
-
8
7
7
6
A
crit
ica
l revie
w
o
f in
fo
r
ma
tio
n
r
etri
ev
a
l te
ch
n
iq
u
es:
cu
r
r
en
t tren
d
s
…
(
S
a
n
ke
t D
.
P
a
til
)
461
T
h
e
T
ex
tR
an
k
a
lg
o
r
ith
m
h
as
b
ee
n
em
p
l
o
y
ed
in
s
ea
r
ch
e
n
g
in
es
,
im
p
r
o
v
i
n
g
in
f
o
r
m
atio
n
r
etr
iev
a
l
th
r
o
u
g
h
ad
v
an
ce
d
r
an
k
in
g
alg
o
r
ith
m
s
.
T
h
is
s
h
o
ws
th
e
ef
f
icac
y
o
f
T
ex
tR
an
k
in
en
h
a
n
cin
g
s
ea
r
ch
e
n
g
in
e
p
er
f
o
r
m
an
ce
b
y
b
etter
r
an
k
in
g
r
elev
an
t d
o
cu
m
en
ts
.
NL
P
tech
n
iq
u
es,
wh
en
an
n
o
ta
ted
b
y
ex
p
er
ts
,
h
av
e
b
ee
n
s
h
o
wn
to
s
ig
n
if
ican
tly
en
h
a
n
c
e
A
I
-
en
ab
led
in
f
o
r
m
atio
n
r
etr
iev
al
in
leg
al
s
er
v
ices
.
T
h
is
h
ig
h
lig
h
ts
th
e
im
p
o
r
tan
ce
o
f
ex
p
er
t
in
v
o
l
v
em
en
t
in
r
ef
in
in
g
NL
P
m
o
d
els f
o
r
s
p
ec
ialized
d
o
m
ain
s
.
Fin
ally
,
d
o
c
u
m
en
t
-
lev
el
s
im
ilar
ity
tech
n
i
q
u
es
in
th
e
l
eg
al
d
o
m
ain
h
av
e
b
ee
n
s
h
o
wn
to
i
m
p
r
o
v
e
th
e
q
u
al
ity
o
f
r
elev
a
n
ce
ju
d
g
m
en
t
s
in
in
f
o
r
m
atio
n
r
etr
iev
al
s
y
s
tem
s
.
T
h
is
in
v
o
lv
es
u
s
in
g
d
o
cu
m
en
t
s
im
ilar
ity
an
d
p
o
o
lin
g
tech
n
iq
u
es
to
b
etter
ju
d
g
e
th
e
r
elev
a
n
ce
o
f
leg
al
d
o
cu
m
e
n
ts
.
Dee
p
L
STM
tec
h
n
iq
u
es
ap
p
lied
to
q
u
esti
o
n
an
s
wer
in
g
d
em
o
n
s
tr
ate
ef
f
ec
tiv
e
in
f
o
r
m
ati
o
n
r
etr
iev
al
ca
p
ab
ilit
ies,
r
ein
f
o
r
cin
g
th
e
v
alu
e
o
f
d
ee
p
lear
n
in
g
in
e
n
h
an
ci
n
g
QA
s
y
s
tem
s
.
T
ab
le
1
.
Ov
e
r
v
iew
o
f
e
x
is
tin
g
in
f
o
r
m
atio
n
r
etr
iev
al
f
r
am
ewo
r
k
,
tech
n
o
lo
g
ies,
d
o
m
ain
a
n
d
k
ey
f
in
d
in
g
s
P
a
p
e
r
Te
c
h
n
o
l
o
g
y
u
se
d
D
o
ma
i
n
o
f
s
t
u
d
y
R
e
t
r
i
e
v
a
l
w
o
r
k
i
n
g
w
i
t
h
t
a
b
l
e
s
R
e
t
r
i
e
v
a
l
/
w
o
r
k
i
n
g
w
i
t
h
t
a
b
l
e
s
K
e
y
f
i
n
d
i
n
g
s
[
10
]
C
o
s
i
n
e
S
i
mi
l
a
r
i
t
y
Q
u
e
st
i
o
n
a
n
sw
e
r
i
n
g
No
No
I
n
t
e
g
r
a
t
i
o
n
o
f
i
n
f
o
r
m
a
t
i
o
n
r
e
t
r
i
e
v
a
l
a
n
d
d
e
e
p
l
e
a
r
n
i
n
g
e
n
h
a
n
c
e
s
t
e
x
t
u
a
l
q
u
e
st
i
o
n
a
n
sw
e
r
i
n
g
sy
s
t
e
ms
[
11
]
R
N
N
Le
g
a
l
q
u
e
s
t
i
o
n
a
n
sw
e
r
i
n
g
No
No
D
e
e
p
l
e
a
r
n
i
n
g
i
m
p
r
o
v
e
s
a
c
c
u
r
a
c
y
i
n
l
e
g
a
l
q
u
e
st
i
o
n
a
n
sw
e
r
i
n
g
.
[
12
]
LSTM
R
e
c
o
mm
e
n
d
a
t
i
o
n
sy
st
e
m
No
No
D
e
e
p
l
e
a
r
n
i
n
g
e
n
h
a
n
c
e
s
r
e
t
r
i
e
v
a
l
a
l
g
o
r
i
t
h
ms
i
n
r
e
c
o
mm
e
n
d
a
t
i
o
n
sy
st
e
ms.
[
13
]
Th
e
s
a
u
r
u
s
g
e
n
e
r
a
t
i
o
n
S
e
a
r
c
h
e
n
g
i
n
e
No
No
Th
e
s
a
u
r
u
s
i
m
p
r
o
v
e
s
r
e
t
r
i
e
v
a
l
t
e
c
h
n
o
l
o
g
i
e
s
i
n
s
p
e
c
i
f
i
c
d
a
t
a
d
o
mai
n
s
.
[
14
]
N
e
u
r
a
l
n
e
t
w
o
r
k
F
r
e
e
t
e
x
t
d
a
t
a
b
a
s
e
sea
r
c
h
No
No
U
n
su
p
e
r
v
i
s
e
d
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
s
a
d
d
r
e
ss
i
n
f
o
r
ma
t
i
o
n
r
e
t
r
i
e
v
a
l
c
h
a
l
l
e
n
g
e
s.
[
15
]
C
o
s
i
n
e
s
i
mi
l
a
r
i
t
y
Ed
u
c
a
t
i
o
n
No
No
S
u
mm
a
r
i
z
a
t
i
o
n
t
e
c
h
n
i
q
u
e
s
i
mp
r
o
v
e
e
d
u
c
a
t
i
o
n
a
l
t
e
c
h
n
o
l
o
g
y
s
y
st
e
ms.
[
16
]
LSTM
Q
u
e
st
i
o
n
a
n
sw
e
r
i
n
g
No
No
B
i
g
d
a
t
a
a
n
a
l
y
si
s
e
n
h
a
n
c
e
s
d
e
v
e
l
o
p
me
n
t
o
f
q
u
e
st
i
o
n
-
a
n
sw
e
r
i
n
g
sy
st
e
ms.
[
17
]
Te
x
t
R
a
n
k
a
l
g
o
r
i
t
h
m
S
e
a
r
c
h
e
n
g
i
n
e
No
No
Te
x
t
R
a
n
k
-
b
a
se
d
a
l
g
o
r
i
t
h
ms
i
m
p
r
o
v
e
i
n
f
o
r
mat
i
o
n
r
e
t
r
i
e
v
a
l
.
[
18
]
N
LP
Le
g
a
l
No
No
Ex
p
e
r
t
-
a
n
n
o
t
a
t
e
d
N
LP
e
n
h
a
n
c
e
s
A
I
-
e
n
a
b
l
e
d
i
n
f
o
r
mat
i
o
n
r
e
t
r
i
e
v
a
l
i
n
l
e
g
a
l
serv
i
c
e
s
.
[
19
]
LSTM
N
o
t
s
p
e
c
i
f
i
e
d
No
No
P
r
o
p
o
se
d
f
r
a
m
e
w
o
r
k
a
i
ms
a
t
r
o
b
u
st
a
n
d
s
c
a
l
a
b
l
e
i
n
f
o
r
m
a
t
i
o
n
r
e
t
r
i
e
v
a
l
i
n
b
i
g
d
a
t
a
c
o
n
t
e
x
t
s
.
[
20
]
D
o
c
u
me
n
t
l
e
v
e
l
si
mi
l
a
r
i
t
y
Le
g
a
l
No
No
D
o
c
u
me
n
t
si
m
i
l
a
r
i
t
y
a
n
d
p
o
o
l
i
n
g
t
e
c
h
n
i
q
u
e
s
e
n
h
a
n
c
e
t
h
e
q
u
a
l
i
t
y
o
f
r
e
l
e
v
a
n
c
e
j
u
d
g
me
n
t
s
i
n
i
n
f
o
r
mat
i
o
n
r
e
t
r
i
e
v
a
l
s
y
st
e
ms.
[
21
]
LSTM
G
e
n
e
r
a
l
No
No
I
n
t
e
g
r
a
t
i
n
g
t
e
x
t
u
a
l
i
n
f
o
r
m
a
t
i
o
n
i
mp
r
o
v
e
s
c
o
n
t
e
n
t
-
b
a
se
d
i
ma
g
e
r
e
t
r
i
e
v
a
l
.
[
22
]
D
e
e
p
-
LS
TM
Q
u
e
st
i
o
n
a
n
sw
e
r
i
n
g
No
No
G
o
o
d
i
n
f
o
r
ma
t
i
o
n
r
e
t
r
i
e
v
a
l
u
si
n
g
d
e
e
p
LSTM
Ov
er
all,
th
ese
p
ap
er
s
co
llectiv
ely
u
n
d
er
s
co
r
e
th
e
s
ig
n
if
ica
n
t
ad
v
an
ce
m
e
n
ts
m
ad
e
p
o
s
s
ib
le
th
r
o
u
g
h
th
e
ap
p
licatio
n
o
f
d
ee
p
lea
r
n
in
g
an
d
NL
P
tech
n
iq
u
es
in
im
p
r
o
v
in
g
in
f
o
r
m
atio
n
r
etr
i
ev
al
ac
r
o
s
s
v
ar
io
u
s
d
o
m
ain
s
,
alth
o
u
g
h
n
o
n
e
s
p
ec
if
ically
f
o
cu
s
ed
o
n
r
etr
iev
al
o
r
wo
r
k
in
g
with
ta
b
les.
Hav
in
g
s
aid
th
at,
th
e
r
ev
ie
w
id
en
tifie
s
s
ig
n
if
ican
t
r
esea
r
ch
g
ap
s
,
esp
ec
ially
in
p
r
o
c
ess
in
g
an
d
r
etr
iev
in
g
im
ag
es
an
d
tab
les
alo
n
g
s
id
e
tex
t
s
u
m
m
ar
izatio
n
.
No
n
e
o
f
th
e
s
tu
d
ies
ad
d
r
ess
es
th
e
in
teg
r
atio
n
o
f
m
u
ltime
d
ia
co
n
ten
t,
wh
ich
is
cr
u
cial
f
o
r
co
m
p
r
eh
en
s
iv
e
in
f
o
r
m
atio
n
r
etr
ie
v
al
s
y
s
tem
s
.
C
u
r
r
en
t
ap
p
r
o
ac
h
es
f
o
cu
s
m
ain
ly
o
n
tex
t,
n
e
g
lec
tin
g
th
e
ef
f
ec
tiv
e
s
u
m
m
ar
iza
tio
n
an
d
in
teg
r
atio
n
o
f
v
is
u
a
l
d
ata
[
2
3
]
,
[
2
4
]
.
Fu
r
th
er
m
o
r
e
,
wh
ile
s
o
m
e
p
a
p
er
s
m
en
tio
n
e
d
u
ca
tio
n
al
tec
h
n
o
lo
g
y
,
th
er
e
is
a
lack
o
f
f
o
cu
s
o
n
en
h
an
cin
g
s
tu
d
en
t
lear
n
in
g
s
p
ec
if
ically
.
R
esear
c
h
s
h
o
u
ld
ex
p
lo
r
e
ad
a
p
tiv
e
lear
n
in
g
s
y
s
tem
s
th
at
in
c
o
r
p
o
r
ate
m
u
ltime
d
ia
elem
en
ts
to
cr
ea
te
en
g
ag
in
g
a
n
d
ef
f
ec
tiv
e
ed
u
ca
tio
n
al
ex
p
er
ien
ce
s
.
Per
s
o
n
alizin
g
co
n
ten
t
b
ased
o
n
in
d
iv
i
d
u
al
s
tu
d
en
t
p
r
o
g
r
ess
an
d
p
r
ef
er
e
n
ce
s
is
also
u
n
d
er
ex
p
lo
r
ed
[
2
5
]
.
Ad
v
an
ce
d
d
ee
p
l
ea
r
n
in
g
m
o
d
els
t
h
at
h
a
n
d
le
m
u
ltimo
d
al
d
ata,
co
m
b
in
in
g
NL
P
with
co
m
p
u
te
r
v
is
io
n
,
a
r
e
n
ee
d
e
d
b
u
t
u
n
d
er
r
ep
r
esen
t
ed
in
t
h
e
liter
atu
r
e.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
7
7
6
I
n
t J I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
,
Vo
l.
1
5
,
No
.
2
,
J
u
n
e
20
2
6
:
4
5
6
-
4
6
4
462
T
h
er
e
is
also
a
s
h
o
r
tag
e
o
f
p
r
ac
tical
im
p
lem
en
tatio
n
s
,
r
ea
l
-
wo
r
ld
ca
s
e
s
tu
d
ies,
an
d
r
esear
ch
in
to
u
s
er
in
ter
ac
tio
n
an
d
ex
p
e
r
i
en
ce
with
m
u
ltime
d
ia
r
etr
ie
v
al
s
y
s
tem
s
[
2
6
]
,
[
2
7
]
.
So
,
it
h
as
to
b
e
s
aid
t
h
at
d
esp
ite
ad
v
an
ce
m
e
n
ts
in
tex
t
-
b
ased
r
etr
iev
al,
th
er
e
is
a
cl
ea
r
g
ap
in
in
teg
r
atin
g
m
u
ltime
d
ia
elem
en
ts
an
d
en
h
an
ci
n
g
s
tu
d
en
t
lea
r
n
in
g
.
Ad
d
r
ess
in
g
th
ese
g
ap
s
co
u
ld
lead
to
m
o
r
e
co
m
p
r
eh
e
n
s
iv
e
an
d
ef
f
ec
tiv
e
i
n
f
o
r
m
atio
n
r
etr
iev
al
s
y
s
tem
s
.
4.
CO
NCLU
SI
O
N
I
n
s
y
n
th
esizin
g
th
e
ex
p
an
s
iv
e
in
s
ig
h
ts
g
ar
n
er
ed
f
r
o
m
th
e
d
etailed
liter
atu
r
e
s
u
r
v
ey
,
it
b
ec
o
m
es
u
n
eq
u
i
v
o
ca
lly
clea
r
th
at
t
h
e
d
o
m
ain
o
f
in
f
o
r
m
atio
n
r
etr
ie
v
al
is
at
a
cr
itical
ju
n
ctu
r
e,
ch
ar
ac
ter
ized
b
y
a
d
y
n
am
ic
in
ter
p
lay
o
f
tech
n
o
lo
g
ical
in
n
o
v
atio
n
s
,
m
eth
o
d
o
lo
g
ical
ad
v
a
n
ce
m
en
ts
,
an
d
in
ter
d
is
cip
lin
ar
y
co
llab
o
r
atio
n
s
.
C
en
tr
al
to
t
h
is
ev
o
lu
tio
n
is
th
e
p
e
r
v
asiv
e
in
teg
r
atio
n
a
n
d
a
p
p
licatio
n
o
f
d
ee
p
lear
n
in
g
f
r
am
ewo
r
k
s
,
wh
ich
h
av
e
s
u
b
s
t
an
tially
au
g
m
e
n
ted
th
e
p
r
ec
is
io
n
,
s
ca
lab
ilit
y
,
an
d
ad
a
p
tab
ilit
y
o
f
co
n
tem
p
o
r
ar
y
r
etr
iev
al
s
y
s
tem
s
.
T
h
ese
ad
v
an
ce
m
en
ts
,
h
o
wev
er
,
ar
e
n
o
t w
ith
o
u
t th
eir
c
o
m
p
lex
ities
an
d
ch
allen
g
es.
T
h
e
r
ev
iew
illu
m
in
ates
s
ev
er
al
n
u
an
ce
d
d
im
en
s
io
n
s
,
in
clu
d
in
g
th
e
in
tr
i
n
s
ic
alg
o
r
ith
m
ic
b
iases
th
at
ca
n
in
f
lu
en
ce
r
etr
ie
v
al
o
u
tco
m
es,
th
e
d
o
m
ain
-
s
p
ec
if
ic
in
tr
i
ca
cies
th
at
n
ec
ess
i
tate
tailo
r
ed
m
eth
o
d
o
lo
g
ies,
an
d
th
e
o
v
er
ar
c
h
in
g
im
p
e
r
ativ
e
o
f
s
ca
lab
ilit
y
in
an
er
a
o
f
b
u
r
g
eo
n
in
g
d
ata
v
o
l
u
m
es.
Fu
r
t
h
er
m
o
r
e
,
th
e
p
ap
er
u
n
d
er
s
co
r
es
th
e
tr
an
s
f
o
r
m
at
iv
e
p
o
ten
tial
o
f
in
ter
d
is
cip
lin
ar
y
s
y
n
er
g
ies,
wh
er
ein
th
e
co
n
v
er
g
en
ce
o
f
d
iv
er
s
e
d
o
m
ain
s
an
d
ex
p
er
tis
e
ca
taly
ze
s
n
o
v
el
in
s
ig
h
ts
a
n
d
in
n
o
v
a
tiv
e
s
o
lu
tio
n
s
.
T
h
e
p
ap
e
r
h
i
g
h
lig
h
ts
th
e
f
ac
t
t
h
at
m
an
y
r
esear
ch
wo
r
k
s
f
o
cu
s
o
n
s
tan
d
ar
d
d
atasets
an
d
d
o
n
o
t
wo
r
k
o
n
t
h
e
r
ea
l
wo
r
ld
d
ata.
R
etr
iev
al
o
r
wo
r
k
i
n
g
with
th
e
tab
les
an
d
im
ag
es
p
r
esen
t
in
th
e
o
r
ig
in
al
d
ata
is
an
im
p
o
r
tan
t
s
o
u
r
ce
o
f
in
f
o
r
m
ati
o
n
,
b
u
t
n
o
n
e
o
f
th
e
in
f
o
r
m
atio
n
r
etr
iev
al
p
ap
er
s
id
en
tify
th
is
an
d
wo
r
k
o
n
it.
So
,
in
co
n
clu
s
io
n
,
th
er
e
is
a
r
eq
u
ir
em
en
t
f
o
r
a
s
y
s
tem
th
at
wo
r
k
s
with
th
is
im
p
o
r
tan
t in
f
o
r
m
atio
n
.
C
o
llectiv
ely
,
th
e
c
o
m
p
r
e
h
en
s
iv
e
ex
p
lo
r
atio
n
o
f
f
er
ed
b
y
t
h
e
r
ev
iew
o
f
th
e
liter
atu
r
e
el
u
cid
ates
th
e
m
u
ltifa
ce
ted
n
atu
r
e
o
f
m
o
d
e
r
n
in
f
o
r
m
atio
n
r
etr
iev
al,
h
ig
h
lig
h
tin
g
th
e
r
em
ar
k
ab
le
s
tr
id
es
m
ad
e,
th
e
ch
al
len
g
es
y
et
to
b
e
s
u
r
m
o
u
n
ted
,
an
d
th
e
p
r
o
m
is
in
g
av
en
u
es
f
o
r
f
u
t
u
r
e
r
esear
ch
an
d
in
n
o
v
atio
n
in
th
is
d
y
n
am
ic
an
d
p
iv
o
tal
d
o
m
ain
.
ACK
NO
WL
E
DG
M
E
N
T
S
T
h
e
au
th
o
r
s
s
in
ce
r
ely
a
p
p
r
ec
iate
th
e
s
u
p
p
o
r
t
p
r
o
v
id
e
d
b
y
th
e
m
an
a
g
em
en
t
o
f
T
h
ak
u
r
C
o
lleg
e
o
f
E
n
g
in
ee
r
in
g
an
d
T
ec
h
n
o
lo
g
y
.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
T
h
e
au
th
o
r
s
s
tate
n
o
f
u
n
d
in
g
is
in
v
o
lv
ed
.
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
San
k
et
D.
Patil
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
Z
ah
ir
Aala
m
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
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
e
au
th
o
r
s
s
tate
n
o
co
n
f
lict o
f
in
ter
est.
DATA AV
AI
L
AB
I
L
I
T
Y
T
h
e
d
ata
th
at
s
u
p
p
o
r
t
th
e
f
in
d
in
g
s
o
f
th
is
s
tu
d
y
ar
e
o
p
en
l
y
av
ailab
le
at
h
ttp
://d
o
i.o
r
g
/
m
e
n
tio
n
ed
in
all
th
e
r
ef
er
en
ce
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
I
SS
N:
2252
-
8
7
7
6
A
crit
ica
l revie
w
o
f in
fo
r
ma
tio
n
r
etri
ev
a
l te
ch
n
iq
u
es:
cu
r
r
en
t tren
d
s
…
(
S
a
n
ke
t D
.
P
a
til
)
463
RE
F
E
R
E
NC
E
S
[
1
]
T.
P
.
N
a
g
a
r
h
a
l
l
i
,
A
.
M
.
S
a
v
e
,
a
n
d
N
.
M
.
S
h
e
k
o
k
a
r
,
Fu
n
d
a
m
e
n
t
a
l
m
o
d
e
l
s
i
n
m
a
c
h
i
n
e
l
e
a
r
n
i
n
g
a
n
d
d
e
e
p
l
e
a
rn
i
n
g
.
D
e
si
g
n
o
f
I
n
t
e
l
l
i
g
e
n
t
a
p
p
l
i
c
a
t
i
o
n
s
u
s
i
n
g
mac
h
i
n
e
l
e
a
r
n
i
n
g
a
n
d
d
e
e
p
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
s
,
2
0
2
1
.
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
s
:
/
/
w
w
w
.
t
a
y
l
o
r
f
r
a
n
c
i
s.c
o
m
/
c
h
a
p
t
e
r
s/
e
d
i
t
/
1
0
.
1
2
0
1
/
9
7
8
1
0
0
3
1
3
3
6
8
1
-
2
/
f
u
n
d
a
m
e
n
t
a
l
-
mo
d
e
l
s
-
ma
c
h
i
n
e
-
l
e
a
r
n
i
n
g
-
d
e
e
p
-
l
e
a
r
n
i
n
g
-
t
a
t
w
a
d
a
r
sh
i
-
n
a
g
a
r
h
a
l
l
i
-
a
s
h
w
i
n
i
-
s
a
v
e
-
n
a
r
e
n
d
r
a
-
s
h
e
k
o
k
a
r
[
2
]
“
W
h
a
t
i
s
i
n
f
o
r
ma
t
i
o
n
r
e
t
r
i
e
v
a
l
?
”
A
c
c
e
ss
e
d
:
D
e
c
.
2
9
,
2
0
2
3
.
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
s
:
/
/
w
w
w
.
g
e
e
k
sf
o
r
g
e
e
k
s.
o
r
g
/
w
h
a
t
-
is
-
i
n
f
o
r
mat
i
o
n
-
r
e
t
r
i
e
v
a
l
/
[
3
]
S.
P
r
a
k
a
s
h
,
H
.
R
.
S
h
a
sh
i
d
h
a
r
a
,
a
n
d
G
.
T
.
R
a
j
u
,
“
T
h
e
r
o
l
e
o
f
a
n
i
n
f
o
r
ma
t
i
o
n
r
e
t
r
i
e
v
a
l
i
n
t
h
e
c
u
r
r
e
n
t
e
r
a
o
f
v
a
s
t
c
o
mp
u
t
e
r
sc
i
e
n
c
e
st
r
e
a
m
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
S
o
f
t
C
o
m
p
u
t
i
n
g
a
n
d
En
g
i
n
e
e
ri
n
g
(
I
J
S
C
E)
,
v
o
l
.
3
,
n
o
.
3
,
p
.
1
3
9
,
2
0
1
3
,
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
s
:
/
/
w
w
w
.
r
e
se
a
r
c
h
g
a
t
e
.
n
e
t
/
p
u
b
l
i
c
a
t
i
o
n
/
3
0
5
2
0
9
0
8
2
[
4
]
O
.
A
.
A
b
a
ss
a
n
d
O
.
A
.
A
r
o
w
o
l
o
,
“
I
n
f
o
r
mat
i
o
n
r
e
t
r
i
e
v
a
l
m
o
d
e
l
s,
t
e
c
h
n
i
q
u
e
s
a
n
d
a
p
p
l
i
c
a
t
i
o
n
s
,”
I
n
t
e
r
n
a
t
i
o
n
a
l
Re
s
e
a
rc
h
J
o
u
r
n
a
l
o
f
Ad
v
a
n
c
e
d
En
g
i
n
e
e
r
i
n
g
a
n
d
S
c
i
e
n
c
e
,
v
o
l
.
2
,
n
o
.
2
,
p
p
.
1
9
7
-
2
0
2
,
2
0
1
7
.
[
5
]
“
I
ss
u
e
s
i
n
i
n
f
o
r
ma
t
i
o
n
r
e
t
r
i
e
v
a
l
,
”
A
c
c
e
s
s
e
d
:
D
e
c
.
2
9
,
2
0
2
3
.
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
s
:
/
/
w
w
w
.
g
e
e
k
sf
o
r
g
e
e
k
s
.
o
r
g
/
w
h
a
t
-
is
-
i
n
f
o
r
m
a
t
i
o
n
-
r
e
t
r
i
e
v
a
l
/
[
6
]
K
.
S
u
b
r
ma
n
i
a
n
,
G
.
T
h
a
n
g
a
r
a
s
u
,
Z.
Y
a
n
y
a
n
,
a
n
d
K
.
N
.
K
a
n
n
a
n
,
“
D
e
e
p
l
e
a
r
n
i
n
g
b
a
se
d
a
l
g
o
r
i
t
h
m
f
o
r
e
f
f
i
c
i
e
n
t
i
n
f
o
r
mat
i
o
n
r
e
t
r
i
e
v
a
l
i
n
b
l
o
c
k
c
h
a
i
n
t
r
a
n
s
a
c
t
i
o
n
s
,
”
i
n
2
0
2
4
6
t
h
I
EEE
S
y
m
p
o
si
u
m
o
n
C
o
m
p
u
t
e
rs
a
n
d
I
n
f
o
rm
a
t
i
c
s
,
I
S
C
I
2
0
2
4
,
I
EEE,
A
u
g
.
2
0
2
4
,
p
p
.
2
6
4
-
2
6
9
.
d
o
i
:
1
0
.
1
1
0
9
/
I
S
C
I
6
2
7
8
7
.
2
0
2
4
.
1
0
6
6
7
7
1
2
.
[
7
]
S
.
M
e
n
g
me
n
g
,
L
.
Z
h
i
b
i
n
,
W
.
Q
i
n
g
w
e
i
,
H
.
M
a
n
,
a
n
d
X
.
F
e
i
y
a
n
g
,
“
A
n
e
f
f
e
c
t
i
v
e
r
e
t
r
i
e
v
a
l
m
e
t
h
o
d
t
o
i
m
p
r
o
v
e
R
A
G
p
e
r
f
o
r
m
a
n
c
e
,
”
i
n
Pro
c
e
e
d
i
n
g
s
-
2
0
2
4
7
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
D
a
t
a
S
c
i
e
n
c
e
a
n
d
I
n
f
o
rm
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
,
D
S
I
T
2
0
2
4
,
I
EEE,
D
e
c
.
2
0
2
4
,
p
p
.
1
–
5
.
d
o
i
:
1
0
.
1
1
0
9
/
D
S
I
T6
1
3
7
4
.
2
0
2
4
.
1
0
8
8
1
3
8
0
.
[
8
]
L
.
S
t
a
n
e
s
c
u
a
n
d
B
.
S
a
v
u
,
“
A
u
t
o
m
a
t
i
c
a
s
s
e
s
s
m
e
n
t
o
f
n
a
r
r
a
t
i
v
e
a
n
s
w
e
r
s
u
s
i
n
g
i
n
f
o
r
m
a
t
i
o
n
r
e
t
r
i
e
v
a
l
t
e
c
h
n
i
q
u
e
s
,
”
i
n
P
r
o
c
e
e
d
i
n
g
s
o
f
t
h
e
2
0
1
9
F
e
d
e
r
a
t
e
d
C
o
n
f
e
r
e
n
c
e
o
n
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
I
n
f
o
r
m
a
t
i
o
n
S
y
s
t
e
m
s
,
F
e
d
C
S
I
S
2
0
1
9
,
S
e
p
.
2
0
1
9
,
p
p
.
3
5
5
-
3
5
8
.
d
o
i
:
1
0
.
1
5
4
3
9
/
2
0
1
9
F
9
6
.
[
9
]
V
.
A
.
M
i
sh
r
a
,
M
.
S
r
i
v
a
s
t
a
v
a
,
M
.
S
.
N
i
t
h
y
a
,
S
.
M
i
sh
r
a
,
S
.
K
a
n
n
i
m
u
t
h
u
,
a
n
d
N
.
D
i
v
y
a
,
“
E
v
a
l
u
a
t
i
n
g
a
u
t
o
m
a
t
e
d
i
n
f
o
r
mat
i
o
n
r
e
t
r
i
e
v
a
l
t
e
c
h
n
i
q
u
e
s
f
o
r
i
m
p
r
o
v
e
d
d
a
t
a
a
c
c
e
s
si
b
i
l
i
t
y
,
”
i
n
Pro
c
e
e
d
i
n
g
s
-
2
0
2
3
I
E
EE
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
P
a
ra
d
i
g
m
S
h
i
f
t
i
n
I
n
f
o
rm
a
t
i
o
n
T
e
c
h
n
o
l
o
g
i
e
s
w
i
t
h
I
n
n
o
v
a
t
i
v
e
Ap
p
l
i
c
a
t
i
o
n
s
i
n
G
l
o
b
a
l
S
c
e
n
a
ri
o
,
I
C
PS
I
T
I
AG
S
2
0
2
3
,
I
EEE,
D
e
c
.
2
0
2
3
,
p
p
.
1
6
3
-
1
6
7
.
d
o
i
:
1
0
.
1
1
0
9
/
I
C
P
S
I
T
I
A
G
S
5
9
2
1
3
.
2
0
2
3
.
1
0
5
2
7
5
2
9
.
[
1
0
]
A
.
P
a
n
d
e
y
a
n
d
A
.
B
h
a
t
,
“
A
r
e
v
i
e
w
o
n
t
e
x
t
u
a
l
q
u
e
st
i
o
n
a
n
sw
e
r
i
n
g
w
i
t
h
i
n
f
o
r
ma
t
i
o
n
r
e
t
r
i
e
v
a
l
a
n
d
d
e
e
p
l
e
a
r
n
i
n
g
a
s
p
e
c
t
,
”
i
n
Pro
c
e
e
d
i
n
g
s
o
f
t
h
e
7
t
h
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
I
n
t
e
l
l
i
g
e
n
t
C
o
m
p
u
t
i
n
g
a
n
d
C
o
n
t
ro
l
S
y
s
t
e
m
s,
I
C
I
C
C
S
2
0
2
3
,
2
0
2
3
,
p
p
.
2
2
4
-
2
2
9
.
d
o
i
:
1
0
.
1
1
0
9
/
I
C
I
C
C
S
5
6
9
6
7
.
2
0
2
3
.
1
0
1
4
2
7
2
9
[
1
1
]
H
.
N
.
V
a
n
,
D
.
N
g
u
y
e
n
,
P
.
M
.
N
g
u
y
e
n
,
a
n
d
M
.
Le
N
g
u
y
e
n
,
“
M
i
k
o
T
e
a
m
:
d
e
e
p
l
e
a
r
n
i
n
g
a
p
p
r
o
a
c
h
f
o
r
l
e
g
a
l
q
u
e
s
t
i
o
n
a
n
sw
e
r
i
n
g
i
n
A
LQ
A
C
2
0
2
2
,
”
i
n
Pr
o
c
e
e
d
i
n
g
s
-
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
K
n
o
w
l
e
d
g
e
a
n
d
S
y
s
t
e
m
s
E
n
g
i
n
e
e
r
i
n
g
,
K
S
E
,
I
EEE,
O
c
t
.
2
0
2
2
,
p
p
.
1
–
5
.
d
o
i
:
1
0
.
1
1
0
9
/
K
S
E
5
6
0
6
3
.
2
0
2
2
.
9
9
5
3
7
8
0
.
[
1
2
]
S
.
Z
h
a
o
,
Z.
H
u
a
n
g
,
H
.
G
u
o
,
X
.
X
i
a
o
,
a
n
d
R
.
Y
e
,
“
D
e
e
p
l
e
a
r
n
i
n
g
-
b
a
se
d
r
e
t
r
i
e
v
a
l
a
l
g
o
r
i
t
h
ms
f
o
r
r
e
c
o
m
me
n
d
a
t
i
o
n
s
y
st
e
ms,
”
i
n
2
0
2
3
I
EEE
3
rd
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
Po
w
e
r
,
El
e
c
t
ro
n
i
c
s
a
n
d
C
o
m
p
u
t
e
r
A
p
p
l
i
c
a
t
i
o
n
s,
I
C
PE
C
A
2
0
2
3
,
I
EEE,
Jan
.
2
0
2
3
,
p
p
.
1
1
5
5
-
1
1
6
0
.
d
o
i
:
1
0
.
1
1
0
9
/
I
C
P
EC
A
5
6
7
0
6
.
2
0
2
3
.
1
0
0
7
6
1
0
2
.
[
1
3
]
H
.
M
a
t
s
i
u
k
,
L
.
D
z
h
y
d
z
h
o
r
a
,
N
.
K
u
n
a
n
e
t
s,
a
n
d
O
.
M
a
t
s
i
u
k
,
“
A
p
p
l
i
c
a
t
i
o
n
o
f
i
n
f
o
r
m
a
t
i
o
n
r
e
t
r
i
e
v
a
l
t
h
e
s
a
u
r
u
s
f
o
r
t
h
e
i
mp
r
o
v
e
me
n
t
o
f
i
n
f
o
r
mat
i
o
n
r
e
t
r
i
e
v
a
l
t
e
c
h
n
o
l
o
g
i
e
s
i
n
sp
e
c
i
f
i
c
d
a
t
a
d
o
ma
i
n
,
”
i
n
I
n
t
e
r
n
a
t
i
o
n
a
l
S
c
i
e
n
t
i
f
i
c
a
n
d
T
e
c
h
n
i
c
a
l
C
o
n
f
e
r
e
n
c
e
o
n
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
s
a
n
d
I
n
f
o
rm
a
t
i
o
n
T
e
c
h
n
o
l
o
g
i
e
s
,
I
EEE,
S
e
p
.
2
0
2
1
,
p
p
.
4
3
7
-
4
4
0
.
d
o
i
:
1
0
.
1
1
0
9
/
C
S
I
T5
2
7
0
0
.
2
0
2
1
.
9
6
4
8
7
2
9
.
[
1
4
]
J.
C
.
S
c
h
o
l
t
e
s
,
“
U
n
su
p
e
r
v
i
s
e
d
l
e
a
r
n
i
n
g
a
n
d
t
h
e
i
n
f
o
r
mat
i
o
n
r
e
t
r
i
e
v
a
l
p
r
o
b
l
e
m,”
i
n
1
9
9
1
I
EE
E
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
i
n
t
C
o
n
f
e
re
n
c
e
o
n
N
e
u
ra
l
N
e
t
w
o
rks
,
I
EEE,
1
9
9
2
,
p
p
.
9
5
-
1
0
0
.
d
o
i
:
1
0
.
1
1
0
9
/
i
j
c
n
n
.
1
9
9
1
.
1
7
0
3
8
7
.
[
1
5
]
I
.
B
e
n
e
d
e
t
t
o
,
L
.
C
a
n
a
l
e
,
L.
F
a
r
i
n
e
t
t
i
,
L.
C
a
g
l
i
e
r
o
,
a
n
d
M
.
L
a
Q
u
a
t
r
a
,
“
Le
v
e
r
a
g
i
n
g
s
u
mm
a
r
i
z
a
t
i
o
n
t
e
c
h
n
i
q
u
e
s
i
n
e
d
u
c
a
t
i
o
n
a
l
t
e
c
h
n
o
l
o
g
y
s
y
st
e
ms,
”
i
n
Pr
o
c
e
e
d
i
n
g
s
-
2
0
2
2
I
EEE
4
6
t
h
An
n
u
a
l
C
o
m
p
u
t
e
r
s,
S
o
f
t
w
a
r
e
,
a
n
d
A
p
p
l
i
c
a
t
i
o
n
s
C
o
n
f
e
r
e
n
c
e
,
C
O
M
PS
A
C
2
0
2
2
,
I
EEE,
Ju
n
.
2
0
2
2
,
p
p
.
4
1
5
-
4
1
6
.
d
o
i
:
1
0
.
1
1
0
9
/
C
O
M
P
S
A
C
5
4
2
3
6
.
2
0
2
2
.
0
0
0
6
8
.
[
1
6
]
D
.
A
k
s
o
n
o
v
,
A
.
G
o
z
h
y
j
,
I
.
K
a
l
i
n
i
n
a
,
a
n
d
V
.
V
y
s
o
t
s
k
a
,
“
Q
u
e
st
i
o
n
-
a
n
sw
e
r
i
n
g
s
y
st
e
ms
d
e
v
e
l
o
p
m
e
n
t
b
a
se
d
o
n
b
i
g
d
a
t
a
a
n
a
l
y
s
i
s,
”
i
n
I
n
t
e
rn
a
t
i
o
n
a
l
S
c
i
e
n
t
i
f
i
c
a
n
d
T
e
c
h
n
i
c
a
l
C
o
n
f
e
r
e
n
c
e
o
n
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
s
a
n
d
I
n
f
o
rm
a
t
i
o
n
T
e
c
h
n
o
l
o
g
i
e
s
,
I
EEE,
S
e
p
.
2
0
2
1
,
p
p
.
1
1
3
-
1
1
8
.
d
o
i
:
1
0
.
1
1
0
9
/
C
S
I
T5
2
7
0
0
.
2
0
2
1
.
9
6
4
8
6
3
1
.
[
1
7
]
C
.
X
u
,
“
R
e
s
e
a
r
c
h
o
n
i
n
f
o
r
m
a
t
i
o
n
r
e
t
r
i
e
v
a
l
a
l
g
o
r
i
t
h
m
b
a
s
e
d
o
n
t
e
x
t
R
a
n
k
,
”
i
n
Pro
c
e
e
d
i
n
g
s
-
2
0
1
9
3
4
r
d
Y
o
u
t
h
Ac
a
d
e
m
i
c
An
n
u
a
l
C
o
n
f
e
re
n
c
e
o
f
C
h
i
n
e
s
e
Ass
o
c
i
a
t
i
o
n
o
f
Au
t
o
m
a
t
i
o
n
,
Y
AC
2
0
1
9
,
I
EEE,
J
u
n
.
2
0
1
9
,
p
p
.
1
8
0
–
1
8
3
.
d
o
i
:
1
0
.
1
1
0
9
/
Y
A
C
.
2
0
1
9
.
8
7
8
7
6
1
5
.
[
1
8
]
K
.
K
a
n
h
a
i
y
a
,
N
a
v
e
e
n
,
A
.
K
.
S
h
a
r
m
a
,
K
.
G
a
u
t
a
m,
a
n
d
P
.
S
.
R
a
t
h
o
r
e
,
“
A
I
e
n
a
b
l
e
d
-
i
n
f
o
r
m
a
t
i
o
n
r
e
t
r
i
v
a
l
e
n
g
i
n
e
(
A
I
-
I
R
E)
i
n
l
e
g
a
l
serv
i
c
e
s
:
a
n
e
x
p
e
r
t
-
a
n
n
o
t
a
t
e
d
N
LP
f
o
r
l
e
g
a
l
j
u
d
g
e
me
n
t
s,”
i
n
Pr
o
c
e
e
d
i
n
g
s o
f
t
h
e
2
0
2
3
2
n
d
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
A
u
g
m
e
n
t
e
d
I
n
t
e
l
l
i
g
e
n
c
e
a
n
d
S
u
s
t
a
i
n
a
b
l
e
S
y
s
t
e
m
s,
I
C
AI
S
S
2
0
2
3
,
I
EEE,
A
u
g
.
2
0
2
3
,
p
p
.
2
0
6
-
2
1
0
.
d
o
i
:
1
0
.
1
1
0
9
/
I
C
A
I
S
S
5
8
4
8
7
.
2
0
2
3
.
1
0
2
5
0
7
3
3
.
[
1
9
]
H
.
L
.
N
g
u
y
e
n
,
T.
N
.
Tr
i
n
h
-
H
u
y
n
h
,
a
n
d
K
.
H
.
L
e
,
“
To
w
a
r
d
s
a
r
o
b
u
s
t
a
n
d
sca
l
a
b
l
e
i
n
f
o
r
mat
i
o
n
r
e
t
r
i
e
v
a
l
f
r
a
me
w
o
r
k
i
n
b
i
g
d
a
t
a
c
o
n
t
e
x
t
,
”
i
n
Pr
o
c
e
e
d
i
n
g
s
-
2
0
2
2
9
t
h
N
AFO
S
T
ED
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
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
N
I
C
S
2
0
2
2
,
I
EEE,
O
c
t
.
2
0
2
2
,
p
p
.
2
1
1
-
2
1
6
.
d
o
i
:
1
0
.
1
1
0
9
/
N
I
C
S
5
6
9
1
5
.
2
0
2
2
.
1
0
0
1
3
4
4
6
.
[
2
0
]
M
.
H
.
Jo
s
e
p
h
a
n
d
S
.
D
.
R
a
v
a
n
a
,
“
G
e
n
e
r
a
t
i
o
n
o
f
h
i
g
h
-
q
u
a
l
i
t
y
r
e
l
e
v
a
n
t
j
u
d
g
m
e
n
t
s
t
h
r
o
u
g
h
d
o
c
u
m
e
n
t
si
m
i
l
a
r
i
t
y
a
n
d
d
o
c
u
me
n
t
p
o
o
l
i
n
g
f
o
r
t
h
e
e
v
a
l
u
a
t
i
o
n
o
f
i
n
f
o
r
mat
i
o
n
r
e
t
r
i
e
v
a
l
s
y
st
e
ms,”
i
n
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
S
o
f
t
w
a
re
,
K
n
o
w
l
e
d
g
e
I
n
f
o
rm
a
t
i
o
n
,
I
n
d
u
st
r
i
a
l
Ma
n
a
g
e
m
e
n
t
a
n
d
A
p
p
l
i
c
a
t
i
o
n
s
,
S
K
I
MA
,
I
EEE,
D
e
c
.
2
0
2
2
,
p
p
.
2
6
1
-
2
6
5
.
d
o
i
:
1
0
.
1
1
0
9
/
S
K
I
M
A
5
7
1
4
5
.
2
0
2
2
.
1
0
0
2
9
4
5
9
.
[
2
1
]
Y
.
S
r
i
v
a
r
sh
a
a
n
d
V
.
M
.
M
a
n
i
k
a
n
d
a
n
,
“
A
n
o
v
e
l
c
o
n
t
e
n
t
-
b
a
se
d
i
ma
g
e
r
e
t
r
i
e
v
a
l
s
c
h
e
me
b
a
se
d
o
n
t
e
x
t
u
a
l
i
n
f
o
r
mat
i
o
n
,
”
i
n
2
0
2
1
1
2
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
m
p
u
t
i
n
g
C
o
m
m
u
n
i
c
a
t
i
o
n
a
n
d
N
e
t
w
o
rk
i
n
g
T
e
c
h
n
o
l
o
g
i
e
s,
I
C
C
C
N
T
2
0
2
1
,
I
EEE,
J
u
l
.
2
0
2
1
,
p
p
.
1
-
4
.
d
o
i
:
1
0
.
1
1
0
9
/
I
C
C
C
N
T
5
1
5
2
5
.
2
0
2
1
.
9
5
7
9
4
7
8
.
[
2
2
]
D
.
V
.
V
e
k
a
r
i
y
a
a
n
d
N
.
R
.
L
i
m
b
a
si
y
a
,
“
A
n
o
v
e
l
a
p
p
r
o
a
c
h
f
o
r
sem
a
n
t
i
c
si
mi
l
a
r
i
t
y
m
e
a
s
u
r
e
m
e
n
t
f
o
r
h
i
g
h
q
u
a
l
i
t
y
a
n
sw
e
r
sel
e
c
t
i
o
n
i
n
q
u
e
st
i
o
n
a
n
sw
e
r
i
n
g
u
si
n
g
d
e
e
p
l
e
a
r
n
i
n
g
me
t
h
o
d
s,”
i
n
2
0
2
0
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
A
d
v
a
n
c
e
d
C
o
m
p
u
t
i
n
g
a
n
d
C
o
m
m
u
n
i
c
a
t
i
o
n
S
y
st
e
m
s
,
I
C
AC
C
S
2
0
2
0
,
I
EEE,
M
a
r
.
2
0
2
0
,
p
p
.
5
1
8
-
5
2
2
.
d
o
i
:
1
0
.
1
1
0
9
/
I
C
A
C
C
S
4
8
7
0
5
.
2
0
2
0
.
9
0
7
4
4
7
1
.
[
2
3
]
A
.
A
a
r
a
b
,
A
.
O
u
s
s
o
u
s
,
a
n
d
M
.
S
a
d
d
o
u
n
e
,
“
O
p
t
i
m
i
z
i
n
g
a
r
a
b
i
c
i
n
f
o
r
m
a
t
i
o
n
r
e
t
r
i
e
v
a
l
:
a
c
o
m
p
r
e
h
e
n
s
i
v
e
e
v
a
l
u
a
t
i
o
n
o
f
p
r
e
p
r
o
c
e
s
s
i
n
g
t
e
c
h
n
i
q
u
e
s
,
”
i
n
2
0
2
4
I
E
EE
1
2
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
S
y
m
p
o
si
u
m
o
n
S
i
g
n
a
l
,
I
m
a
g
e
,
V
i
d
e
o
a
n
d
C
o
m
m
u
n
i
c
a
t
i
o
n
s
(
I
S
I
V
C
)
,
I
EE
E
,
M
a
y
2
0
2
4
,
p
p
.
1
-
4
.
d
o
i
:
1
0
.
1
1
0
9
/
I
S
I
V
C
6
1
3
5
0
.
2
0
2
4
.
1
0
5
7
7
8
2
7
.
[
2
4
]
D
.
M
a
h
a
p
a
t
r
a
,
C
.
M
a
h
a
r
a
n
a
,
S
.
P
.
P
a
n
d
a
,
J.
P
.
M
o
h
a
n
t
y
,
A
.
T
a
l
i
b
,
a
n
d
A
.
M
a
n
g
a
r
a
j
,
“
A
f
u
z
z
y
-
c
l
u
st
e
r
b
a
s
e
d
s
e
man
t
i
c
i
n
f
o
r
ma
t
i
o
n
r
e
t
r
i
e
v
a
l
s
y
st
e
m,
”
i
n
Pr
o
c
e
e
d
i
n
g
s
o
f
t
h
e
4
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
i
n
g
Me
t
h
o
d
o
l
o
g
i
e
s
a
n
d
C
o
m
m
u
n
i
c
a
t
i
o
n
,
I
C
C
M
C
2
0
2
0
,
I
EEE,
M
a
r
.
2
0
2
0
,
p
p
.
6
7
5
-
6
7
8
.
d
o
i
:
1
0
.
1
1
0
9
/
I
C
C
M
C
4
8
0
9
2
.
2
0
2
0
.
I
C
C
M
C
-
0
0
0
1
2
5
.
[
2
5
]
Y
.
P
e
n
g
a
n
d
Y
.
Y
a
n
g
,
“
Le
a
r
n
i
n
g
t
o
r
a
n
k
f
o
r
b
i
o
me
d
i
c
a
l
i
n
f
o
r
ma
t
i
o
n
r
e
t
r
i
e
v
a
l
,
”
i
n
Pro
c
e
e
d
i
n
g
s
-
2
0
2
1
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
I
n
t
e
l
l
i
g
e
n
t
T
ra
n
s
p
o
r
t
a
t
i
o
n
,
B
i
g
D
a
t
a
a
n
d
S
m
a
rt
C
i
t
y
,
I
C
I
T
BS
2
0
2
1
,
I
EEE,
M
a
r
.
2
0
2
1
,
p
p
.
5
6
2
-
5
6
6
.
d
o
i
:
1
0
.
1
1
0
9
/
I
C
I
TB
S
5
3
1
2
9
.
2
0
2
1
.
0
0
1
4
3
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
7
7
6
I
n
t J I
n
f
&
C
o
m
m
u
n
T
ec
h
n
o
l
,
Vo
l.
1
5
,
No
.
2
,
J
u
n
e
20
2
6
:
4
5
6
-
4
6
4
464
[
2
6
]
R
.
R
.
D
e
s
h
m
u
k
h
a
n
d
A
.
B
.
R
a
u
t
,
“
O
n
t
o
l
o
g
y
b
a
s
e
d
sem
a
n
t
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
u
si
n
g
d
a
t
a
r
a
n
k
i
n
g
,
”
i
n
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
S
e
l
f
S
u
s
t
a
i
n
a
b
l
e
Ar
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
S
y
st
e
m
s,
I
C
S
S
A
S
2
0
2
3
-
Pr
o
c
e
e
d
i
n
g
s
,
I
EEE,
O
c
t
.
2
0
2
3
,
p
p
.
1
0
3
2
-
1
0
3
8
.
d
o
i
:
1
0
.
1
1
0
9
/
I
C
S
S
A
S
5
7
9
1
8
.
2
0
2
3
.
1
0
3
3
1
8
7
3
.
[
2
7
]
D
.
K
u
m
a
r
,
D
.
S
.
Y
a
d
a
v
,
a
n
d
D
.
Y
a
d
a
v
,
“
W
a
v
e
l
e
t
t
r
e
e
a
p
p
r
o
a
c
h
f
o
r
se
a
r
c
h
i
n
g
a
n
d
i
n
d
e
x
i
n
g
i
n
g
e
o
g
r
a
p
h
i
c
a
l
i
n
f
o
r
mat
i
o
n
r
e
t
r
i
e
v
a
l
,
”
i
n
1
st
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
Ad
v
a
n
c
e
s
i
n
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
E
l
e
c
t
ri
c
a
l
,
E
l
e
c
t
r
o
n
i
c
s
,
a
n
d
C
o
m
m
u
n
i
c
a
t
i
o
n
T
e
c
h
n
o
l
o
g
i
e
s,
C
E2
C
T
2
0
2
5
,
I
EEE,
F
e
b
.
2
0
2
5
,
p
p
.
5
8
-
6
1
.
d
o
i
:
1
0
.
1
1
0
9
/
C
E2
C
T
6
4
0
1
1
.
2
0
2
5
.
1
0
9
3
9
6
7
7
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
S
a
n
k
e
t
D.
Pa
ti
l
is
a
n
As
sista
n
t
P
ro
fe
ss
o
r
a
n
d
Train
i
n
g
a
n
d
P
lac
e
m
e
n
t
Offic
e
r
a
t
Vid
y
a
v
a
rd
h
i
n
i’s
Co
ll
e
g
e
o
f
En
g
i
n
e
e
rin
g
a
n
d
Tec
h
n
o
lo
g
y
.
He
h
o
l
d
s
a
m
a
ste
r’s
d
e
g
re
e
in
c
o
m
p
u
ter
e
n
g
i
n
e
e
rin
g
fro
m
th
e
Un
iv
e
rsity
o
f
M
u
m
b
a
i
,
a
n
d
h
a
s
o
v
e
r
1
0
y
e
a
rs
o
f
e
x
p
e
rien
c
e
in
b
o
th
tea
c
h
i
n
g
a
n
d
in
d
u
stry
.
S
a
n
k
e
t
h
a
s
p
u
b
l
ish
e
d
se
v
e
ra
l
p
a
p
e
rs
in
re
p
u
ted
jo
u
r
n
a
ls
a
n
d
c
o
n
fe
re
n
c
e
s,
fo
c
u
si
n
g
o
n
d
a
ta
p
re
p
ro
c
e
ss
in
g
a
n
d
se
n
ti
m
e
n
t
a
n
a
ly
sis.
His
i
n
d
u
stry
e
x
p
e
rien
c
e
in
c
lu
d
e
s
se
rv
in
g
a
s
a
Ch
ief
Tec
h
n
ica
l
An
a
ly
st
a
t
Tec
h
5
S
o
lu
ti
o
n
s,
w
h
e
re
h
e
sp
e
c
ialize
d
in
s
y
ste
m
d
e
sig
n
a
n
d
p
ro
jec
t
m
a
n
a
g
e
m
e
n
t
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
sa
n
k
e
tp
a
ti
l
7
@g
m
a
il
.
c
o
m
.
Dr
.
Za
h
ir
A
a
l
a
m
c
u
rre
n
tl
y
se
r
v
in
g
a
s
th
e
d
e
a
n
o
f
train
i
n
g
a
n
d
p
lac
e
m
e
n
t,
h
o
ld
s
a
P
h
.
D.
i
n
En
g
i
n
e
e
rin
g
.
Wi
th
o
v
e
r
1
9
y
e
a
rs
o
f
tea
c
h
i
n
g
e
x
p
e
rien
c
e
,
h
e
h
a
s
e
sta
b
li
sh
e
d
e
x
p
e
rti
se
in
t
h
e
field
s
o
f
e
m
b
e
d
d
e
d
sy
ste
m
s,
wire
les
s
n
e
two
rk
s,
m
a
c
h
i
n
e
lea
rn
in
g
,
d
e
e
p
lea
rn
i
n
g
a
n
d
se
n
so
r
n
e
two
r
k
s.
His
e
x
ten
si
v
e
b
a
c
k
g
ro
u
n
d
in
b
o
th
a
c
a
d
e
m
ia
a
n
d
sp
e
c
ialize
d
tec
h
n
i
c
a
l
a
re
a
s
h
a
s
b
e
e
n
i
n
stru
m
e
n
tal
in
s
h
a
p
i
n
g
h
is
lea
d
e
rsh
i
p
r
o
le
i
n
trai
n
in
g
a
n
d
p
lac
e
m
e
n
t
a
c
ti
v
it
ies
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
z
a
h
ir.
a
a
lam
@th
a
k
u
re
d
u
c
a
ti
o
n
.
o
rg
.
Evaluation Warning : The document was created with Spire.PDF for Python.