I
AE
S In
t
er
na
t
io
na
l J
o
urna
l o
f
Art
if
icia
l In
t
ellig
ence
(
I
J
-
AI
)
Vo
l.
1
5
,
No
.
5
,
Octo
b
er
2
0
2
6
,
p
p
.
4
2
1
3
~
4
2
2
3
I
SS
N:
2
2
5
2
-
8
9
3
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijai.v
15
.i
5
.
p
p
4
2
1
3
-
4
2
2
3
4213
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
a
i
.
ia
esco
r
e.
co
m
M
a
tchIA:
a
sema
ntic
a
rti
ficial in
tel
lig
ence so
lution
for
interopera
bili
ty i
n schema
ma
tch
i
ng
M
o
ha
m
ed
Ra
o
ui,
M
o
ula
y
H
a
f
id E
l Y
a
zidi,
Ahm
ed
Z
el
lo
u
S
o
f
t
w
a
r
e
P
r
o
j
e
c
t
M
a
n
a
g
e
me
n
t
R
e
s
e
a
r
c
h
Te
a
m,
Éc
o
l
e
N
a
t
i
o
n
a
l
e
S
u
p
é
r
i
e
u
r
e
d
’
I
n
f
o
r
mat
i
q
u
e
e
t
d
’
A
n
a
l
y
se
d
e
s
S
y
s
t
è
mes
,
M
o
h
a
mm
e
d
V
U
n
i
v
e
r
s
i
t
y
i
n
R
a
b
a
t
,
R
a
b
a
t
,
M
o
r
o
c
c
o
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
u
n
5
,
2
0
2
5
R
ev
is
ed
J
u
l 1
4
,
2
0
2
6
Acc
ep
ted
Au
g
1
2
,
2
0
2
6
S
c
h
e
m
a
m
a
tch
in
g
p
la
y
s
a
c
ru
c
ial
ro
le
in
d
a
ta
in
te
g
ra
ti
o
n
b
y
a
li
g
n
i
n
g
a
tt
rib
u
tes
fro
m
h
e
tero
g
e
n
e
o
u
s
so
u
rc
e
s.
Trad
it
i
o
n
a
l
ru
le
-
b
a
se
d
a
n
d
sta
ti
stica
l
tec
h
n
iq
u
e
s
o
ften
lac
k
th
e
fle
x
ib
i
li
ty
t
o
a
d
a
p
t
to
d
i
v
e
rse
sc
h
e
m
a
stru
c
tu
re
s,
re
q
u
iri
n
g
e
x
te
n
siv
e
m
a
n
u
a
l
e
ffo
r
t.
To
a
d
d
re
ss
th
e
se
c
h
a
ll
e
n
g
e
s,
th
is
p
a
p
e
r
in
tro
d
u
c
e
s
M
a
tch
IA,
a
m
a
c
h
in
e
lea
rn
in
g
so
lu
ti
o
n
th
a
t
c
o
m
b
i
n
e
s
wo
rd
e
m
b
e
d
d
in
g
s
a
n
d
ra
n
d
o
m
fo
re
st
to
e
n
h
a
n
c
e
th
e
a
c
c
u
ra
c
y
o
f
sc
h
e
m
a
m
a
tch
in
g
.
Th
e
a
p
p
ro
a
c
h
a
c
c
o
u
n
ts
fo
r
b
o
th
str
u
c
tu
ra
l
d
e
p
e
n
d
e
n
c
ies
a
n
d
se
m
a
n
ti
c
re
latio
n
sh
i
p
s
b
e
twe
e
n
a
tt
rib
u
tes
,
e
n
a
b
li
n
g
m
o
re
a
u
to
m
a
ted
,
a
n
d
re
li
a
b
le
c
o
rre
sp
o
n
d
e
n
c
e
i
d
e
n
ti
fica
ti
o
n
.
Un
li
k
e
tra
d
it
i
o
n
a
l
m
e
th
o
d
s,
M
a
tch
IA
lev
e
ra
g
e
s
p
re
train
e
d
e
m
b
e
d
d
i
n
g
s
to
c
a
p
t
u
re
c
o
n
te
x
tu
a
l
sim
il
a
r
it
ies
a
n
d
in
teg
ra
tes
lea
rn
e
d
p
a
tt
e
rn
s
t
o
g
e
n
e
ra
li
z
e
a
c
ro
ss
v
a
rio
u
s
d
o
m
a
in
s.
Ex
p
e
rime
n
tal
e
v
a
lu
a
ti
o
n
s
o
n
sta
n
d
a
rd
d
a
tas
e
ts
d
e
m
o
n
stra
te
t
h
a
t
M
a
tch
IA
a
c
h
iev
e
s
a
p
re
c
isi
o
n
o
f
0
.
9
4
,
a
re
c
a
ll
o
f
0
.
9
2
,
a
n
d
a
n
o
v
e
ra
ll
m
a
tch
in
g
a
c
c
u
ra
c
y
o
f
0
.
9
3
,
si
g
n
ifi
c
a
n
tl
y
o
u
tp
e
rfo
rm
in
g
sta
te
-
of
-
t
h
e
-
a
rt
m
e
th
o
d
s.
T
h
e
se
re
su
lt
s
h
ig
h
li
g
h
t
t
h
e
p
o
ten
ti
a
l
o
f
M
a
tch
IA
fo
r
re
a
l
-
wo
rl
d
a
p
p
li
c
a
ti
o
n
s
re
q
u
iri
n
g
sc
a
lab
le an
d
a
u
t
o
m
a
ted
d
a
ta
in
ter
o
p
e
ra
b
il
it
y
.
K
ey
w
o
r
d
s
:
Data
in
teg
r
atio
n
Ma
ch
in
e
lear
n
in
g
R
an
d
o
m
f
o
r
est
Sch
em
a
m
atch
in
g
W
o
r
d
em
b
ed
d
in
g
s
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
:
Mo
h
am
ed
R
ao
u
i
So
f
twar
e
Pro
ject
Ma
n
ag
em
e
n
t Res
ea
r
ch
T
ea
m
É
co
le
Natio
n
ale
Su
p
ér
ieu
r
e
d
’
I
n
f
o
r
m
atiq
u
e
et
d
’
An
aly
s
e
d
es
Sy
s
tèm
es
Mo
h
am
m
ed
V
U
n
iv
er
s
ity
in
R
ab
at
Av
en
u
e
Mo
h
am
m
ed
B
en
Ab
d
ellah
R
eg
r
ag
u
i,
Ma
d
in
at
Al
I
r
f
an
e,
B
P 7
1
3
,
Ag
d
al
R
ab
at,
Mo
r
o
cc
o
E
m
ail: m
o
h
am
ed
_
r
ao
u
i@
u
m
5
.
ac
.
m
a
1.
I
NT
RO
D
UCT
I
O
N
Sch
em
a
m
atch
in
g
is
a
cr
u
cial
s
tep
in
an
y
d
ata
in
teg
r
atio
n
p
r
o
ce
s
s
.
I
t
aim
s
to
id
en
tify
attr
i
b
u
tes
th
at
ca
r
r
y
th
e
s
am
e
m
ea
n
in
g
ac
r
o
s
s
m
u
ltip
le,
o
f
ten
h
eter
o
g
e
n
e
o
u
s
,
an
d
d
ata
s
o
u
r
ce
s
[
1
]
.
T
h
is
task
p
lay
s
a
v
ital
r
o
le
in
s
ce
n
ar
io
s
s
u
ch
as
d
ata
b
ase
m
er
g
in
g
,
s
y
s
tem
m
ig
r
atio
n
,
an
d
th
e
co
n
s
tr
u
ctio
n
o
f
k
n
o
wled
g
e
g
r
ap
h
s
[
2
]
.
W
h
en
d
o
n
e
ac
cu
r
atel
y
,
it
e
n
s
u
r
es
s
em
an
tic
co
n
s
is
ten
cy
b
etw
ee
n
s
y
s
tem
s
,
th
er
eb
y
en
h
an
cin
g
th
e
r
eliab
ilit
y
o
f
s
u
b
s
eq
u
en
t
d
ata
an
al
y
s
is
.
C
o
n
v
er
s
ely
,
p
o
o
r
alig
n
m
en
t
ca
n
l
ea
d
to
s
em
an
tic
in
c
o
n
s
is
ten
cies
an
d
d
im
in
is
h
t
h
e
q
u
ality
o
f
t
h
e
in
teg
r
ate
d
d
ata.
T
r
ad
itio
n
ally
,
h
e
u
r
is
tic
ap
p
r
o
ac
h
es
[
3
]
−
[
6
]
h
a
v
e
b
ee
n
wid
ely
ad
o
p
ted
f
o
r
s
ch
em
a
m
atch
in
g
,
p
r
im
ar
ily
b
ec
au
s
e
o
f
th
eir
s
im
p
licity
an
d
ef
f
ec
tiv
en
ess
in
we
ll
-
d
ef
in
ed
e
n
v
ir
o
n
m
en
ts
.
T
h
ese
m
eth
o
d
s
a
r
e
b
u
ilt
o
n
em
p
ir
ical
r
u
les
th
at
co
m
p
ar
e
s
ch
em
a
elem
en
ts
u
s
in
g
f
ac
to
r
s
lik
e
n
am
e
s
im
ilar
ity
,
s
tr
u
ctu
r
al
p
atter
n
s
,
o
r
attr
ib
u
te
ty
p
es.
T
o
o
ls
s
u
ch
as
C
OM
A+
+
[
7
]
an
d
C
u
p
id
[
8
]
ex
em
p
lif
y
h
e
u
r
is
tic
-
b
ased
s
o
lu
tio
n
s
,
lev
er
ag
i
n
g
tech
n
iq
u
es
lik
e
s
tr
in
g
s
im
ilar
i
ty
o
r
o
n
to
lo
g
y
alig
n
m
e
n
t
to
i
d
en
tify
p
o
ten
tial
m
atch
es
ac
r
o
s
s
s
ch
em
as.
T
h
ey
ten
d
to
p
er
f
o
r
m
well
in
co
n
t
ex
ts
wh
er
e
d
ata
is
r
elativ
el
y
s
tab
le
an
d
f
o
llo
ws
a
clea
r
s
tr
u
ctu
r
e,
s
u
c
h
as
in
co
n
v
en
tio
n
al
r
elatio
n
al
d
atab
ases
.
Ho
wev
er
,
th
eir
ef
f
ec
tiv
en
ess
d
r
o
p
s
s
ig
n
if
ican
tl
y
in
m
o
r
e
c
o
m
p
lex
o
r
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
1
5
,
No
.
5
,
Octo
b
er
2
0
2
6
:
4
2
1
3
-
4
2
2
3
4214
d
y
n
am
ic
s
ce
n
ar
io
s
.
I
n
s
u
c
h
c
ases
,
h
eu
r
is
tics
o
f
ten
s
tr
u
g
g
le
to
u
n
co
v
er
s
u
b
tle
o
r
n
o
n
-
o
b
v
io
u
s
r
elatio
n
s
h
ip
s
b
etwe
en
attr
ib
u
tes
p
ar
ticu
lar
ly
wh
en
d
ea
lin
g
with
h
eter
o
g
en
eo
u
s
o
r
ev
o
lv
in
g
s
ch
em
as.
Fu
r
th
er
m
o
r
e,
h
e
u
r
is
tic
r
u
les
[
9
]
,
[
1
0
]
ten
d
to
b
e
r
ig
id
an
d
c
h
allen
g
in
g
to
ad
a
p
t
wh
e
n
d
ea
lin
g
with
n
ew
o
r
ev
o
l
v
in
g
s
ch
em
as,
wh
ich
lim
its
th
eir
ef
f
ec
tiv
en
ess
in
d
y
n
am
ic
o
r
la
r
g
e
-
s
ca
le
d
ata
en
v
ir
o
n
m
e
n
ts
.
R
ec
en
t
r
esear
ch
[
1
1
]
−
[
1
4
]
h
ig
h
lig
h
ts
h
o
w
th
ese
ap
p
r
o
ac
h
es o
f
te
n
f
a
il to
s
ca
le
w
ith
g
r
o
win
g
d
ata
v
o
lu
m
es o
r
to
ca
p
tu
r
e
n
u
an
ce
d
,
co
n
tex
t
-
d
ep
e
n
d
en
t
r
elatio
n
s
h
ip
s
b
etwe
en
s
ch
em
a
elem
en
ts
.
An
o
th
er
s
ig
n
if
ica
n
t
lim
itatio
n
is
th
eir
in
ab
ilit
y
to
h
an
d
le
s
ch
em
a
ev
o
lu
tio
n
o
v
er
tim
e,
m
ak
in
g
th
em
d
if
f
icu
lt
to
ap
p
ly
in
s
y
s
tem
s
th
at
ar
e
in
cr
ea
s
in
g
ly
o
p
en
an
d
s
u
b
ject
to
f
r
eq
u
e
n
t
ch
an
g
es
[
1
5
]
,
[
1
6
]
.
Desp
ite
th
ese
d
r
awb
ac
k
s
,
m
u
ch
o
f
th
e
ea
r
lier
wo
r
k
i
n
s
ch
em
a
m
atch
in
g
co
n
tin
u
ed
t
o
r
ely
o
n
th
ese
tr
ad
itio
n
al
m
eth
o
d
s
,
wh
ich
f
all
s
h
o
r
t
in
ad
d
r
ess
in
g
th
e
d
em
an
d
s
o
f
co
m
p
lex
o
r
co
n
s
tan
tly
ch
an
g
in
g
d
atab
ases
[
1
7
]
−
[
2
0
]
.
I
n
lig
h
t
o
f
th
ese
lim
itatio
n
s
,
th
is
p
ap
e
r
in
tr
o
d
u
ce
s
Ma
tch
I
A,
a
s
u
p
er
v
is
ed
s
ch
em
a
m
atch
in
g
f
r
am
ewo
r
k
th
at
in
teg
r
ates
s
e
m
an
tic
wo
r
d
em
b
ed
d
in
g
s
with
s
tr
u
ctu
r
al
in
d
icato
r
s
an
d
lev
er
ag
es
a
r
an
d
o
m
f
o
r
e
s
t
class
if
ier
f
o
r
co
r
r
esp
o
n
d
en
ce
id
en
tific
atio
n
.
T
h
e
p
r
o
p
o
s
ed
ap
p
r
o
ac
h
ca
p
tu
r
es
n
o
n
-
lin
ea
r
r
elatio
n
s
h
ip
s
b
etwe
en
s
ch
em
a
attr
ib
u
tes
an
d
g
en
e
r
alize
s
ac
r
o
s
s
h
eter
o
g
e
n
eo
u
s
s
ch
em
as
b
y
co
m
b
in
in
g
s
em
an
tic
p
r
o
x
im
ity
with
lear
n
ed
d
ec
is
io
n
p
atter
n
s
,
wh
ile
r
em
ai
n
in
g
in
ter
p
r
et
ab
le
an
d
co
m
p
u
tatio
n
ally
ef
f
icien
t.
Ma
tch
I
A
is
ev
alu
ated
o
n
b
e
n
ch
m
ar
k
d
at
asets
,
wh
er
e
it
d
em
o
n
s
tr
ates
co
n
s
is
ten
t
im
p
r
o
v
em
en
ts
o
v
er
h
eu
r
is
tic
-
b
ased
b
aselin
es in
ter
m
s
o
f
p
r
ec
is
io
n
,
r
ec
all,
an
d
o
v
er
all
m
atc
h
in
g
ac
cu
r
ac
y
.
T
h
e
r
est
o
f
t
h
is
p
ap
er
is
o
r
g
an
ized
as
f
o
llo
ws
.
S
ec
tio
n
2
d
escr
ib
es
th
e
p
r
o
p
o
s
ed
m
e
th
o
d
o
lo
g
y
.
Sectio
n
3
p
r
esen
ts
th
e
ex
p
er
i
m
en
tal
ev
alu
atio
n
an
d
an
al
y
s
is
.
Sectio
n
4
c
o
n
clu
d
es
t
h
e
s
tu
d
y
a
n
d
o
u
tlin
es
d
ir
ec
tio
n
s
f
o
r
f
u
tu
r
e
wo
r
k
.
2.
M
E
T
H
O
D
T
h
is
s
ec
tio
n
o
u
tlin
es
th
e
Ma
tch
I
A
m
eth
o
d
o
lo
g
y
d
ev
elo
p
e
d
f
o
r
s
ch
em
a
m
atch
i
n
g
.
I
t
d
etails
th
e
o
v
er
all
d
esig
n
o
f
th
e
ap
p
r
o
ac
h
,
ex
p
lain
s
ea
ch
s
tep
o
f
th
e
d
ata
p
r
o
ce
s
s
in
g
wo
r
k
f
l
o
w,
an
d
h
ig
h
lig
h
ts
th
e
k
e
y
m
eth
o
d
o
l
o
g
ical
d
ec
is
io
n
s
b
eh
in
d
th
e
p
r
o
p
o
s
ed
s
o
lu
tio
n
.
An
o
v
er
v
iew
o
f
th
e
s
ch
em
a
m
atch
in
g
p
r
o
b
lem
is
p
r
esen
ted
in
Fig
u
r
e
1
.
Sch
em
a
m
atch
in
g
r
e
p
r
esen
ts
a
m
ajo
r
ch
allen
g
e
in
in
f
o
r
m
atio
n
in
te
g
r
atio
n
,
p
ar
ticu
lar
ly
wh
en
it
co
m
es
to
id
en
tif
y
in
g
co
lu
m
n
s
th
at
s
h
ar
e
th
e
s
am
e
s
em
an
tic
m
ea
n
in
g
a
cr
o
s
s
d
iv
er
s
e
an
d
h
eter
o
g
en
e
o
u
s
d
ata
s
o
u
r
ce
s
.
T
h
e
m
ain
d
if
f
icu
lty
ar
is
es
f
r
o
m
th
e
f
ac
t
th
at
co
lu
m
n
s
with
s
im
ilar
m
ea
n
in
g
s
m
ig
h
t h
av
e
v
er
y
d
if
f
e
r
en
t n
am
es,
an
d
th
eir
ty
p
es o
r
s
tr
u
ctu
r
e
s
ca
n
v
ar
y
s
ig
n
if
ica
n
tly
.
Fig
u
r
e
1
.
Sch
em
a
m
atch
in
g
in
an
in
ter
o
p
e
r
ab
ilit
y
co
n
tex
t
2
.
1
.
Arc
hite
ct
ura
l
des
ig
n o
f
t
he
M
a
t
chI
A
s
y
s
t
em
f
o
r
s
chem
a
m
a
t
ching
T
h
e
Ma
tch
I
A
ar
ch
itectu
r
e
r
elies
o
n
co
m
b
in
in
g
s
em
an
tic
em
b
ed
d
in
g
s
with
a
r
an
d
o
m
f
o
r
est
class
if
ier
,
a
p
air
in
g
d
esig
n
ed
to
en
h
an
ce
s
ch
em
a
m
atch
in
g
p
er
f
o
r
m
a
n
c
e.
As
s
h
o
wn
in
Fig
u
r
e
2
,
th
e
s
y
s
tem
is
co
m
p
o
s
ed
o
f
s
ev
er
al
k
ey
c
o
m
p
o
n
en
ts
:
d
ata
p
r
ep
r
o
ce
s
s
in
g
,
s
em
an
tic
s
im
ilar
ity
co
m
p
u
tatio
n
,
f
ea
t
u
r
e
ex
tr
ac
tio
n
,
an
d
class
if
icatio
n
.
T
h
e
s
elec
tio
n
o
f
th
is
ar
c
h
itectu
r
e
is
d
r
iv
e
n
b
y
s
ev
er
al
m
eth
o
d
o
lo
g
ical
f
ac
t
o
r
s
.
First,
s
em
an
tic
em
b
ed
d
in
g
s
lik
e
th
o
s
e
em
p
l
o
y
ed
in
Ma
tc
h
I
A
ef
f
ec
tiv
ely
ca
p
tu
r
e
th
e
co
n
tex
tu
al
r
elatio
n
s
h
ip
s
b
etwe
en
c
o
l
u
m
n
s
f
r
o
m
d
i
f
f
e
r
e
n
t
s
c
h
e
m
a
s
,
a
c
r
u
c
i
a
l
a
s
p
ec
t
i
n
s
c
h
e
m
a
m
a
t
c
h
i
n
g
.
U
n
li
k
e
t
r
a
d
it
i
o
n
a
l
r
u
l
e
-
b
a
s
e
d
[
2
1
]
,
[
2
2
]
,
o
r
ex
ac
t
m
atch
i
n
g
m
eth
o
d
s
,
em
b
ed
d
i
n
g
s
p
r
o
v
id
e
g
r
ea
ter
f
lex
ib
ilit
y
b
y
i
d
en
tify
in
g
m
atch
es
ev
en
wh
en
co
lu
m
n
n
am
es
d
if
f
e
r
,
wh
ile
s
till
p
r
eser
v
in
g
th
eir
s
em
an
tic
m
ea
n
in
g
.
A
d
d
itio
n
ally
,
in
co
r
p
o
r
atin
g
s
u
p
e
r
v
is
ed
lear
n
in
g
v
ia
a
r
an
d
o
m
f
o
r
est
class
if
ier
en
ab
les
th
e
m
o
d
el
to
m
ak
e
th
e
b
est
u
s
e
o
f
th
e
f
e
atu
r
es
d
er
iv
ed
f
r
o
m
th
ese
em
b
ed
d
in
g
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
Ma
tch
I
A
:
a
s
ema
n
tic
a
r
tifi
cia
l in
tellig
en
ce
s
o
lu
tio
n
fo
r
in
ter
o
p
era
b
ilit
y
in
s
ch
ema
…
(
Mo
h
a
med
R
a
o
u
i
)
4215
R
an
d
o
m
f
o
r
est
is
esp
ec
ially
s
u
ited
f
o
r
th
is
task
d
u
e
to
its
ca
p
ac
ity
to
m
an
ag
e
co
m
p
lex
an
d
h
eter
o
g
en
e
o
u
s
d
ata,
alo
n
g
w
ith
its
r
o
b
u
s
tn
ess
to
in
p
u
t
v
ar
iatio
n
s
.
Ad
d
itio
n
ally
,
th
is
alg
o
r
ith
m
o
f
f
er
s
a
f
av
o
r
a
b
le
tr
ad
e
-
o
f
f
b
etwe
en
p
r
ed
ictiv
e
p
er
f
o
r
m
a
n
ce
an
d
i
n
ter
p
r
etab
ilit
y
wh
ile
r
em
ain
i
n
g
co
m
p
u
tatio
n
ally
ef
f
icien
t.
T
h
ese
c
o
m
b
in
e
d
s
tr
en
g
th
s
m
ak
e
it
well
s
u
i
ted
f
o
r
p
r
ac
tical
s
ch
em
a
m
atch
in
g
a
n
d
d
ata
in
ter
o
p
er
a
b
ilit
y
s
ce
n
ar
io
s
.
Fig
u
r
e
2
.
Sch
em
atic
r
ep
r
esen
t
atio
n
o
f
th
e
Ma
tch
I
A
m
atch
in
g
an
d
lear
n
in
g
p
r
o
ce
s
s
2
.
2
.
Wo
rd
e
m
bedd
ing
re
pre
s
ent
a
t
io
n
I
n
a
s
ch
em
a
m
atch
in
g
p
r
o
b
le
m
,
th
is
p
ap
er
co
n
s
id
er
two
d
at
ab
ase
s
ch
em
as:
1
co
n
tain
in
g
co
lu
m
n
s
an
d
2
co
n
tain
in
g
co
lu
m
n
s
.
T
h
e
s
e
s
ets ar
e
f
o
r
m
ally
d
ef
in
e
d
as
in
(
1
)
.
1
=
{
co
l
(
1
)
}
=
1
,
2
=
{
co
l
(
2
)
}
=
1
(
1
)
W
h
er
e
co
l
(
1
)
an
d
co
l
(
2
)
r
ep
r
esen
t
co
l
u
m
n
n
am
es
f
r
o
m
s
ch
em
as
1
an
d
2
,
r
esp
ec
tiv
ely
.
Sch
em
a
m
atch
in
g
aim
s
to
id
en
tify
co
r
r
esp
o
n
d
in
g
co
lu
m
n
s
b
etwe
en
1
an
d
2
,
en
a
b
lin
g
s
ea
m
less
d
ata
i
n
teg
r
atio
n
a
n
d
in
ter
o
p
er
a
b
ilit
y
b
etwe
en
d
if
f
er
en
t d
atab
ases
.
E
ac
h
co
lu
m
n
n
am
e
is
tr
an
s
f
o
r
m
ed
i
n
to
a
n
u
m
e
r
ical
v
ec
t
o
r
u
s
in
g
a
wo
r
d
em
b
ed
d
i
n
g
m
o
d
el.
I
n
Ma
tch
I
A,
th
is
p
ap
e
r
em
p
lo
y
th
e
s
p
aCy
lib
r
ar
y
’
s
en
_
co
r
e
_
web
_
m
d
m
o
d
el,
wh
ich
p
r
o
v
id
es
a
3
0
0
-
d
im
e
n
s
io
n
al
r
ep
r
esen
tatio
n
f
o
r
wo
r
d
s
.
Fo
r
m
ally
,
we
d
ef
in
e
t
h
e
em
b
e
d
d
i
n
g
tr
an
s
f
o
r
m
atio
n
f
u
n
ctio
n
f
a
s
in
(
2
)
.
(
1
)
=
(
co
l
(
1
)
)
∈
,
(
2
)
=
(
co
l
(
2
)
)
∈
(
2
)
W
h
er
e
m
ap
s
a
co
lu
m
n
n
am
e
to
a
3
0
0
-
d
im
en
s
io
n
al
wo
r
d
em
b
ed
d
in
g
v
ec
to
r
.
(
1
)
an
d
(
2
)
ca
p
tu
r
e
th
e
s
em
an
tic
m
ea
n
in
g
o
f
th
e
c
o
lu
m
n
n
am
es in
a
h
ig
h
d
im
en
s
io
n
al
s
p
ac
e.
B
y
u
s
in
g
wo
r
d
em
b
e
d
d
in
g
s
,
t
h
is
p
ap
er
ca
n
co
m
p
ar
e
c
o
lu
m
n
s
b
ased
o
n
th
eir
m
ea
n
in
g
s
r
ath
er
th
a
n
th
eir
ex
ac
t
tex
t
u
al
f
o
r
m
s
.
T
h
e
tr
an
s
f
o
r
m
atio
n
in
to
v
ec
to
r
s
all
o
ws
f
o
r
ca
p
tu
r
in
g
u
n
d
er
ly
in
g
s
em
an
tic
m
ea
n
in
g
s
in
co
lu
m
n
n
am
es.
Fo
r
ex
am
p
le,
co
lu
m
n
s
lik
e
‘
b
ir
th
d
a
y
’
an
d
‘
b
ir
th
_
d
ate
’
will
b
e
r
ep
r
esen
t
ed
b
y
v
ec
t
o
r
s
clo
s
e
to
ea
ch
o
th
e
r
in
th
e
e
m
b
ed
d
in
g
s
p
ac
e.
2
.
3
.
Co
s
ine
s
im
ila
rit
y
c
o
m
p
uta
t
io
n
I
n
th
e
Ma
tch
I
A
f
r
am
ewo
r
k
,
s
em
an
tic
s
im
ilar
ity
b
etwe
en
co
l
u
m
n
n
am
es
f
r
o
m
th
e
two
in
p
u
t
s
ch
em
as
is
m
ea
s
u
r
ed
u
s
in
g
th
e
co
s
in
e
s
im
ilar
ity
m
etr
ic.
T
h
is
t
ec
h
n
iq
u
e,
c
o
m
m
o
n
ly
u
s
ed
in
n
atu
r
al
lan
g
u
a
g
e
p
r
o
ce
s
s
in
g
,
q
u
a
n
tifie
s
h
o
w
clo
s
e
two
v
ec
to
r
s
ar
e
co
n
ce
p
tu
ally
with
in
a
h
ig
h
-
d
im
en
s
io
n
a
l
s
p
ac
e.
T
h
e
co
s
in
e
s
im
ilar
ity
is
co
m
p
u
ted
as (
3
)
.
(
(
1
)
,
(
2
)
)
=
(
1
)
⋅
(
2
)
|
(
1
)
|
|
(
2
)
|
(
3
)
W
h
e
r
e
(
1
)
⋅
(
2
)
i
s
t
h
e
d
o
t
p
r
o
d
u
c
t
o
f
th
e
v
e
c
t
o
r
s
a
n
d
|
|
(
1
)
|
|
a
n
d
|
|
(
2
)
|
|
a
r
e
t
h
e
m
a
g
n
i
t
u
d
e
s
o
f
t
h
e
v
ec
t
o
r
s
.
A
s
s
h
o
w
n
i
n
(
4
)
,
a
p
a
i
r
is
c
l
as
s
if
i
e
d
a
s
a
m
at
c
h
i
f
t
h
e
s
i
m
il
a
r
i
t
y
s
c
o
r
e
e
x
c
e
e
d
s
a
p
r
e
d
e
f
i
n
e
d
t
h
r
e
s
h
o
l
d
τ
.
{
}
=
{
1
,
(
{
(
1
)
}
,
{
(
2
)
}
)
≥
;
0
,
ℎ
}
(
4
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
1
5
,
No
.
5
,
Octo
b
er
2
0
2
6
:
4
2
1
3
-
4
2
2
3
4216
A
s
im
ilar
ity
s
co
r
es
clo
s
e
to
1
in
d
icate
s
a
s
tr
o
n
g
s
em
an
ti
c
m
atch
,
wh
er
ea
s
v
alu
es
n
ea
r
0
in
d
icate
wea
k
s
im
ilar
ity
.
Un
lik
e
tr
ad
itio
n
al
h
eu
r
is
tic
m
eth
o
d
s
[
2
3
]
,
[
2
4
]
,
co
s
in
e
s
im
ilar
ity
ca
p
tu
r
es
s
e
m
an
tic
r
elatio
n
s
h
ip
s
b
ey
o
n
d
lex
ical
v
ar
iatio
n
s
,
in
clu
d
in
g
s
y
n
o
n
y
m
s
an
d
a
b
b
r
ev
iatio
n
s
,
th
er
e
b
y
im
p
r
o
v
in
g
s
ch
em
a
m
atch
i
n
g
f
lex
ib
ilit
y
an
d
in
te
r
o
p
e
r
ab
ilit
y
ac
r
o
s
s
h
eter
o
g
e
n
eo
u
s
d
ata
s
tr
u
ctu
r
es.
2
.
4
.
T
ra
ini
ng
m
o
del i
m
plementa
t
io
n
As s
h
o
wn
in
(
5
)
,
b
ef
o
r
e
tr
ain
i
n
g
m
o
d
el,
we
n
o
r
m
alize
th
e
f
e
atu
r
e
v
ec
to
r
s
is
to
im
p
r
o
v
e
p
er
f
o
r
m
an
ce
.
̃
=
−
μ
σ
(
5
)
W
h
er
e
is
th
e
m
ea
n
o
f
all
f
e
atu
r
e
v
alu
es
an
d
is
th
e
s
tan
d
ar
d
d
ev
iatio
n
.
No
r
m
aliza
tio
n
en
s
u
r
es
th
at
th
e
f
ea
tu
r
e
v
alu
es h
a
v
e
a
m
ea
n
o
f
0
an
d
a
v
ar
ian
ce
o
f
1
,
h
elp
i
n
g
th
e
class
if
ier
lear
n
ef
f
ec
tiv
ely
.
As s
h
o
wn
in
(
6
)
,
th
is
p
ap
er
t
r
a
in
a
r
an
d
o
m
f
o
r
est cla
s
s
if
ier
to
p
r
ed
ict
wh
eth
e
r
two
co
lu
m
n
s
m
atch
.
̂
=
θ
(
)
=
∑
ℎ
(
)
=
1
(
6
)
W
h
er
e
is
th
e
tr
ain
ed
class
if
i
er
,
ℎ
(
)
is
th
e
-
th
d
ec
is
io
n
tr
ee
in
th
e
r
an
d
o
m
f
o
r
est,
is
th
e
weig
h
t
ass
ig
n
ed
to
tr
ee
ℎ
,
is
th
e
to
tal
n
u
m
b
er
o
f
tr
ee
s
.
T
h
e
m
o
d
el
is
t
r
ain
ed
o
n
a
d
ataset
(
,
)
wh
er
e
co
n
s
is
ts
o
f
f
ea
tu
r
e
v
ec
to
r
s
,
co
n
s
is
ts
o
f
b
in
ar
y
lab
els.
T
h
e
m
o
d
el
lear
n
s
p
atter
n
s
in
th
e
em
b
ed
d
in
g
s
to
class
if
y
co
lu
m
n
p
air
s
as
m
atch
in
g
1
o
r
non
-
m
atc
h
in
g
0
.
T
h
e
r
an
d
o
m
f
o
r
est
class
if
ier
was
im
p
lem
en
ted
u
s
in
g
Scik
it
-
lear
n
with
1
0
0
tr
ee
s
(
n
_
esti
m
ato
r
s
=
1
0
0
)
an
d
r
a
n
d
o
m
_
s
tate
=
4
2
;
all
o
th
er
p
a
r
am
eter
s
wer
e
k
e
p
t
at
t
h
eir
d
ef
au
lt
v
alu
es.
T
h
e
d
ataset
was
r
an
d
o
m
ly
s
p
lit
in
to
8
0
%
tr
ain
in
g
an
d
2
0
%
test
in
g
s
ets
f
o
r
m
o
d
el
tr
ain
in
g
a
n
d
ev
alu
atio
n
.
T
h
e
r
an
d
o
m
f
o
r
est
class
if
ier
im
p
r
o
v
es
in
ter
p
r
etab
ilit
y
b
y
lear
n
in
g
s
em
an
tic
d
ec
is
io
n
p
atter
n
s
f
r
o
m
th
e
em
b
e
d
d
in
g
r
ep
r
esen
tatio
n
s
.
I
ts
tr
ee
-
b
ased
s
tr
u
ctu
r
e
e
n
ab
les
tr
an
s
p
ar
e
n
t
class
if
icatio
n
o
f
m
atch
i
n
g
an
d
n
o
n
-
m
atch
in
g
s
ch
em
a
p
air
s
wh
ile
m
ain
tain
in
g
h
ig
h
p
r
ed
ictiv
e
p
er
f
o
r
m
an
ce
.
2
.
5
.
M
a
t
chI
A
a
lg
o
rit
h
m
T
h
e
m
eth
o
d
is
d
iv
id
ed
in
to
t
wo
k
ey
s
tag
es,
r
ep
r
esen
tin
g
a
n
o
tab
le
im
p
r
o
v
em
e
n
t
o
v
er
tr
ad
itio
n
al
h
eu
r
is
tic
-
b
ased
s
ch
em
a
m
atc
h
in
g
tech
n
i
q
u
e
[
2
5
]
.
Un
lik
e
r
u
le
b
ased
o
r
s
tr
in
g
s
im
ilar
ity
ap
p
r
o
ac
h
es,
th
e
ap
p
r
o
ac
h
tak
es
a
d
v
an
tag
e
o
f
r
ec
en
t
a
d
v
an
ce
s
i
n
n
at
u
r
al
l
an
g
u
ag
e
p
r
o
ce
s
s
in
g
an
d
s
u
p
e
r
v
is
ed
lear
n
in
g
to
d
is
co
v
er
d
ee
p
er
s
em
an
tic
co
n
n
ec
tio
n
s
b
etwe
en
s
ch
em
a
ele
m
en
ts
.
T
h
e
f
ir
s
t
s
tag
e,
o
u
tlin
ed
in
Alg
o
r
ith
m
1
in
v
o
lv
es
s
y
s
tem
atica
lly
cr
ea
tin
g
p
air
s
o
f
co
lu
m
n
s
f
r
o
m
th
e
in
p
u
t
s
ch
em
as
an
d
ass
ig
n
in
g
lab
els
to
in
d
icate
wh
eth
er
ea
ch
p
air
is
a
p
o
ten
tia
l
m
atch
.
T
h
is
s
tep
f
o
r
m
s
th
e
b
asis
f
o
r
th
e
s
u
b
s
eq
u
e
n
t
s
u
p
er
v
is
ed
lear
n
in
g
p
h
ase
b
y
g
en
er
atin
g
a
th
o
r
o
u
g
h
s
et
o
f
ca
n
d
id
ate
p
air
s
.
B
y
f
o
cu
s
in
g
o
n
r
elev
an
t
p
air
s
in
s
tead
o
f
co
n
s
id
er
in
g
all
p
o
s
s
ib
le
co
m
b
in
atio
n
s
,
th
is
p
r
o
ce
s
s
en
h
an
ce
s
b
o
th
t
h
e
ac
cu
r
ac
y
an
d
e
f
f
icien
cy
o
f
th
e
m
o
d
el.
Alg
o
r
ith
m
1
.
C
o
lu
m
n
p
air
g
en
er
atio
n
an
d
lab
elin
g
Input: df1, df2
Output: X, y
1
:
nlp ←
spacy.load(‘en_core_web_md’)
2
:
def get_vector(text):
2.1 return nlp(text).vector
3
:
columns1 ← columns(df1)
4
:
columns2 ← columns(df2)
5
:
pairs ← {(c1, c2) | c1
∈
columns1, c2
∈
co
lu
mn
s
2}
6
:
For each (c1, c2) in pairs:
a. v1 ← get_vector(c1)
b. v2 ← get_vector(c2)
c. X.append(v1
⨁
v2)
7
:
is_match(c1, c2) ← cosine_similarity(v1, v2) ≥ threshold
8
:
y ← [is_match(c1, c2) for (c1, c2) in pairs]
I
n
th
e
in
itial
p
h
ase,
we
co
n
s
tr
u
ct
all
p
o
ten
tial
p
air
s
o
f
co
lu
m
n
s
b
etwe
en
th
e
two
i
n
p
u
t
s
c
h
em
as.
E
ac
h
co
lu
m
n
n
am
e
is
tr
an
s
f
o
r
m
ed
in
to
a
s
em
an
tic
v
ec
to
r
u
s
in
g
a
p
r
etr
ain
ed
la
n
g
u
a
g
e
m
o
d
el,
s
u
ch
as
s
p
aCy
’
s
en
_
co
r
e
_
web
_
m
d
,
wh
ich
ca
p
tu
r
es
th
e
u
n
d
e
r
ly
in
g
m
ea
n
in
g
o
f
th
e
lab
els
b
ey
o
n
d
s
u
r
f
ac
e
-
lev
el
tex
t.
T
h
ese
v
ec
to
r
s
ar
e
th
en
c
o
m
b
in
e
d
t
y
p
ically
th
r
o
u
g
h
c
o
n
ca
ten
ati
o
n
to
f
o
r
m
a
jo
i
n
t
r
ep
r
esen
t
atio
n
f
o
r
ea
c
h
p
air
.
I
n
s
tead
o
f
r
ely
in
g
o
n
e
x
ac
t
s
tr
in
g
m
atch
es,
we
ass
ig
n
tr
ain
i
n
g
lab
els
b
ased
o
n
th
e
c
o
s
in
e
s
im
ilar
ity
b
etwe
en
th
e
v
ec
to
r
s
.
Pair
s
th
at
ex
h
ib
it
a
h
ig
h
d
e
g
r
ee
o
f
s
em
an
tic
clo
s
en
ess
,
as
m
ea
s
u
r
ed
b
y
th
is
s
im
ilar
ity
,
ar
e
tr
ea
ted
as
m
atch
es.
T
h
is
m
eth
o
d
o
f
f
er
s
a
m
o
r
e
f
lex
ib
le
an
d
in
tellig
en
t
alter
n
ativ
e
to
r
ig
id
r
u
le
-
b
ased
tech
n
iq
u
es
b
y
tak
in
g
in
to
ac
c
o
u
n
t t
h
e
co
n
te
x
tu
al
r
elatio
n
s
h
ip
s
b
etwe
en
ter
m
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
Ma
tch
I
A
:
a
s
ema
n
tic
a
r
tifi
cia
l in
tellig
en
ce
s
o
lu
tio
n
fo
r
in
ter
o
p
era
b
ilit
y
in
s
ch
ema
…
(
Mo
h
a
med
R
a
o
u
i
)
4217
T
h
e
s
ec
o
n
d
s
tag
e
Alg
o
r
ith
m
2
in
v
o
lv
es
tr
ain
in
g
a
s
u
p
e
r
v
i
s
ed
m
o
d
el,
s
p
ec
if
ically
a
r
a
n
d
o
m
f
o
r
est
class
if
ier
,
o
n
th
e
en
co
d
ed
c
o
l
u
m
n
p
air
s
.
T
h
is
e
n
ab
les
th
e
m
o
d
el
to
ca
p
tu
r
e
co
m
p
lex
d
e
cisi
o
n
b
o
u
n
d
ar
ies
b
y
lear
n
in
g
f
r
o
m
th
e
s
em
an
tic
s
im
ilar
ity
p
atter
n
s
p
r
esen
t
in
th
e
tr
ain
in
g
d
ata.
Af
ter
t
r
ain
in
g
,
t
h
e
m
o
d
el
is
ca
p
a
b
le
o
f
p
r
e
d
ictin
g
wh
eth
e
r
a
g
iv
e
n
co
lu
m
n
p
air
co
n
s
titu
tes a
v
alid
m
atch
.
Alg
o
r
ith
m
2
.
L
ea
r
n
in
g
an
d
s
ch
em
a
m
atch
in
g
Input: X, y, similarity_threshold
Output: matches
1
:
(X_train, X_test, y_train,
y_test) ← split(X, y)
2
:
model ← RandomForestClassifier()
3
:
model.fit(X_train, y_train)
4
:
y_pred ← model.predict(X_test)
5
:
accuracy ← evaluate(y_pred, y_test)
6
:
match_schemas(schema1, schema2):
a. Generate pairs from schema1, schema2
b. Compute vectors and predictions
c. matches ← {(c1, c2)
d. Return matches
A
p
r
o
b
ab
ilit
y
th
r
esh
o
ld
ca
n
b
e
ad
ju
s
ted
to
co
n
tr
o
l
th
e
s
en
s
itiv
ity
o
f
th
e
s
ch
em
a
m
atch
in
g
.
C
o
m
p
ar
ed
to
tr
ad
itio
n
al
m
eth
o
d
s
,
th
e
a
p
p
r
o
ac
h
o
f
f
er
s
s
ev
er
al
im
p
o
r
tan
t
ad
v
an
tag
es:
i)
Ad
ap
tab
ilit
y
:
th
e
m
o
d
el
lear
n
s
d
ir
ec
tly
f
r
o
m
th
e
d
ata,
en
a
b
lin
g
it
to
b
etter
ca
p
tu
r
e
th
e
u
n
iq
u
e
tr
aits
o
f
d
if
f
er
en
t sch
em
as.
ii)
Sem
an
tic
r
esil
ien
ce
:
v
ec
to
r
-
b
ased
r
ep
r
esen
tatio
n
s
ef
f
ec
tiv
ely
ca
p
tu
r
e
s
y
n
o
n
y
m
s
an
d
co
n
tex
t
u
al
m
ea
n
in
g
s
th
at
h
e
u
r
is
tic
r
u
les o
f
ten
o
v
e
r
lo
o
k
.
iii)
R
ed
u
ce
d
f
alse
p
o
s
itiv
es:
th
e
lear
n
in
g
-
b
ased
ap
p
r
o
ac
h
im
p
r
o
v
es
d
is
cr
im
in
atio
n
ev
en
wh
en
co
lu
m
n
n
am
es a
r
e
s
im
ilar
b
u
t sem
an
ti
ca
lly
d
is
tin
ct.
iv
)
Scalab
ilit
y
:
th
is
m
eth
o
d
is
s
u
i
tab
le
f
o
r
lar
g
e
-
s
ca
le
s
ch
em
a
m
atch
in
g
task
s
an
d
ca
n
b
e
ea
s
ily
in
teg
r
ated
in
to
au
to
m
ated
d
ata
wo
r
k
f
lo
w
s
.
I
n
s
h
o
r
t,
b
y
c
o
m
b
in
i
n
g
th
ese
t
wo
s
tag
es,
th
is
p
ap
er
p
r
o
v
id
es
a
r
o
b
u
s
t
an
d
m
o
d
er
n
s
o
lu
tio
n
th
at
ad
d
r
ess
es
b
o
th
s
tr
u
ctu
r
al
an
d
s
em
an
tic
c
h
allen
g
es
in
h
e
r
en
t
in
h
e
u
r
is
tic
-
d
r
iv
en
s
ch
em
a
m
atch
in
g
,
m
e
r
g
in
g
d
ee
p
s
em
an
tic
in
s
ig
h
t
with
d
ata
-
d
r
iv
en
d
ec
is
io
n
-
m
ak
i
n
g
.
B
ased
o
n
th
is
m
et
h
o
d
o
lo
g
ical
f
r
am
ewo
r
k
,
th
e
n
ex
t
s
ec
tio
n
p
r
esen
ts
th
e
ex
p
er
im
en
tal
s
etu
p
an
d
ev
alu
ates
th
e
p
er
f
o
r
m
a
n
ce
o
f
Ma
tch
I
A
in
co
m
p
ar
is
o
n
with
ex
is
tin
g
s
ch
em
a
m
atch
in
g
ap
p
r
o
ac
h
es.
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
3
.
1
.
Da
t
a
s
et
s
T
h
e
d
at
ase
t
u
s
e
d
i
n
o
u
r
ex
p
e
r
i
m
e
n
ts
is
d
e
r
i
v
e
d
f
r
o
m
S
c
h
e
m
a
.
o
r
g
,
a
c
o
ll
ab
o
r
at
iv
e
in
itia
ti
v
e
s
u
p
p
o
r
te
d
b
y
m
aj
o
r
s
e
a
r
c
h
en
g
i
n
es
t
o
s
ta
n
d
a
r
d
ize
s
t
r
u
ct
u
r
e
d
d
a
ta
o
n
t
h
e
we
b
.
T
h
e
Sc
h
em
a.
o
r
g
v
o
ca
b
u
lar
y
p
r
o
v
id
es a
r
i
ch
co
l
le
cti
o
n
o
f
e
n
t
it
y
t
y
p
es,
p
r
o
p
er
t
ies
,
a
n
d
s
em
a
n
ti
c
r
ela
ti
o
n
s
h
i
p
s
,
m
a
k
i
n
g
it
a
s
u
ita
b
l
e
b
e
n
c
h
m
a
r
k
f
o
r
e
v
al
u
ati
n
g
s
ch
em
a
m
atc
h
i
n
g
a
p
p
r
o
ac
h
es
.
T
o
ass
ess
th
e
g
e
n
e
r
a
liz
ati
o
n
ca
p
a
b
il
it
y
o
f
Ma
t
ch
I
A
,
t
h
is
p
a
p
e
r
co
n
s
t
r
u
ct
e
d
a
b
e
n
c
h
m
a
r
k
b
y
s
el
ec
ti
n
g
r
e
p
r
e
s
en
t
ati
v
e
cl
ass
es
f
r
o
m
d
i
f
f
e
r
e
n
t
ap
p
l
ica
ti
o
n
d
o
m
ai
n
s
,
in
cl
u
d
i
n
g
p
er
s
o
n
,
p
r
o
d
u
c
t,
o
r
g
an
iza
ti
o
n
,
ev
e
n
t,
p
lac
e,
o
f
f
er
,
a
n
d
C
r
ea
ti
v
eWo
r
k
.
Fo
r
ea
c
h
c
lass
,
t
h
e
ass
o
ci
ate
d
att
r
i
b
u
t
es
we
r
e
e
x
t
r
ac
te
d
t
o
g
e
n
e
r
a
te
h
et
er
o
g
e
n
eo
u
s
s
c
h
e
m
a
p
ai
r
s
wi
th
v
a
r
y
i
n
g
s
tr
u
c
tu
r
al
co
m
p
le
x
i
ty
.
T
h
e
r
es
u
l
ti
n
g
b
e
n
c
h
m
a
r
k
in
cl
u
d
es
s
ch
em
as
r
e
p
r
ese
n
t
e
d
i
n
J
a
v
aS
c
r
i
p
t
o
b
j
ec
t
n
o
tat
io
n
f
o
r
l
in
k
ed
d
at
a
(
J
SO
N
-
LD
)
,
r
es
o
u
r
c
e
d
es
cr
i
p
t
io
n
f
r
a
m
e
wo
r
k
in
att
r
i
b
u
tes
(
R
DF
a
)
,
a
n
d
Mi
cr
o
d
at
a
f
o
r
m
ats
,
en
a
b
li
n
g
t
h
e
e
v
alu
ati
o
n
o
f
t
h
e
p
r
o
p
o
s
ed
a
p
p
r
o
ac
h
a
cr
o
s
s
d
i
v
er
s
e
in
t
er
o
p
e
r
a
b
i
lit
y
s
ce
n
ar
i
o
s
.
T
a
b
le
1
p
r
es
e
n
ts
th
e
m
a
in
c
h
ar
ac
t
e
r
is
ti
cs
o
f
th
e
b
en
c
h
m
ar
k
d
atas
e
t.
T
ab
le
1
.
T
h
e
s
tr
u
ctu
r
ed
s
ch
em
a
d
ataset
u
s
ed
f
o
r
Ma
tch
I
A
ev
alu
atio
n
S
u
b
s
e
t
C
l
a
s
s
A
t
t
r
i
b
u
t
e
s
I
n
st
a
n
c
e
s
F
o
r
mat
La
n
g
u
a
g
e
A
n
n
o
t
a
t
i
o
n
t
y
p
e
U
sag
e
W
e
b
P
r
o
f
i
l
e
s
P
e
r
so
n
15
1
,
2
0
0
JS
O
N
-
LD
En
g
l
i
sh
M
a
n
u
a
l
+
H
e
u
r
i
st
i
c
Tr
a
i
n
i
n
g
M
a
r
k
e
t
p
l
a
c
e
P
r
o
d
u
c
t
18
2
,
5
0
0
R
D
F
a
En
g
l
i
sh
M
a
n
u
a
l
Ev
a
l
u
a
t
i
o
n
C
u
l
t
u
r
a
l
Ev
e
n
t
11
9
8
0
M
i
c
r
o
d
a
t
a
En
g
l
i
sh
H
e
u
r
i
s
t
i
c
Tr
a
i
n
i
n
g
O
r
g
R
e
g
i
s
t
r
y
O
r
g
a
n
i
z
a
t
i
o
n
13
1
,
0
5
0
JS
O
N
-
LD
En
g
l
i
sh
M
a
n
u
a
l
Ev
a
l
u
a
t
i
o
n
G
e
o
l
o
c
a
t
e
d
P
l
a
c
e
10
8
9
0
R
D
F
a
En
g
l
i
sh
M
a
n
u
a
l
+
H
e
u
r
i
st
i
c
Ev
a
l
u
a
t
i
o
n
C
o
mm
e
r
c
i
a
l
O
f
f
e
r
9
1
,
1
0
0
JS
O
N
-
LD
En
g
l
i
sh
H
e
u
r
i
s
t
i
c
V
a
l
i
d
a
t
i
o
n
D
i
g
i
t
a
l
W
o
r
k
s
C
r
e
a
t
i
v
e
W
o
r
k
14
1
,
4
5
0
M
i
c
r
o
d
a
t
a
En
g
l
i
sh
M
a
n
u
a
l
F
i
n
a
l
Te
st
i
n
g
3
.
2
.
E
v
a
lua
t
i
o
n m
et
rics
T
h
is
p
ap
er
ev
alu
ates
th
e
p
er
f
o
r
m
an
ce
o
f
o
u
r
ap
p
r
o
ac
h
u
s
in
g
s
tan
d
ar
d
m
etr
ics.
First,
co
m
p
u
te
th
e
p
r
ec
is
io
n
,
wh
ich
ass
ess
e
s
th
e
ac
cu
r
ac
y
o
f
th
e
p
r
e
d
ictio
n
s
b
y
m
ea
s
u
r
in
g
th
e
p
r
o
p
o
r
tio
n
o
f
co
r
r
ec
tly
p
r
ed
icted
m
atch
es a
m
o
n
g
all
p
r
ed
icted
m
atch
es.
I
t is d
ef
in
ed
as
in
(
7
)
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
1
5
,
No
.
5
,
Octo
b
er
2
0
2
6
:
4
2
1
3
-
4
2
2
3
4218
=
ℎ
ℎ
+
ℎ
(
7
)
Nex
t,
th
is
p
a
p
er
c
o
m
p
u
tes
th
e
r
ec
all
,
wh
ic
h
m
ea
s
u
r
es
th
e
alg
o
r
ith
m
’
s
ab
ilit
y
to
r
etr
ie
v
e
all
th
e
r
elev
a
n
t
s
ch
em
a
m
atch
in
g
th
at
s
h
o
u
ld
ex
is
t.
I
t is g
iv
en
b
y
(
8
)
.
=
ℎ
ℎ
+
ℎ
(
8
)
I
n
ad
d
itio
n
to
p
r
ec
is
io
n
an
d
r
ec
all,
we
also
r
ep
o
r
t
a
cc
u
r
a
cy
an
d
F1
-
s
co
r
e.
Acc
u
r
ac
y
i
s
co
m
p
u
ted
as
th
e
p
r
o
p
o
r
tio
n
o
f
co
r
r
ec
tly
p
r
ed
ict
ed
co
r
r
esp
o
n
d
e
n
ce
s
o
u
t o
f
all
ex
p
ec
ted
m
atch
es
,
as in
(
9
)
.
=
ℎ
ℎ
×
100
(
9
)
F1
-
s
co
r
e
co
m
b
i
n
es p
r
ec
is
io
n
a
n
d
r
ec
all
in
to
a
s
in
g
le
m
etr
ic
t
h
at
b
alan
ce
s
b
o
th
asp
ec
ts
,
as in
(
1
0
)
.
1
−
=
2
⋅
.
+
×
100
(
1
0
)
T
h
is
p
ap
er
d
e
f
in
es
th
e
o
v
er
all
s
co
r
e
as th
e
av
er
ag
e
b
etwe
en
t
h
e
ac
cu
r
ac
y
an
d
t
h
e
F1
-
s
co
r
e,
as
in
(
1
1
)
.
=
+
1
−
2
(
1
1
)
3
.
3
.
P
er
f
o
r
m
a
nce
a
na
ly
s
is
T
h
e
p
er
f
o
r
m
an
ce
o
f
Ma
tch
I
A
was
q
u
an
titativ
ely
ass
e
s
s
ed
u
s
in
g
m
u
ltip
le
m
etr
ics,
in
clu
d
in
g
ac
cu
r
ac
y
,
p
r
ec
is
io
n
,
r
ec
all,
an
d
F1
-
s
co
r
e,
ac
r
o
s
s
v
ar
y
i
n
g
s
ch
em
a
s
izes.
T
h
ese
ev
alu
atio
n
m
etr
ics
wer
e
ch
o
s
en
to
p
r
o
v
id
e
a
c
o
m
p
r
e
h
en
s
iv
e
u
n
d
er
s
tan
d
i
n
g
o
f
th
e
m
o
d
el
’
s
ef
f
ec
tiv
en
ess
in
d
if
f
er
e
n
t
m
atch
in
g
s
ce
n
a
r
io
s
.
Acc
u
r
ac
y
m
ea
s
u
r
es
th
e
o
v
er
al
l
co
r
r
ec
tn
ess
o
f
p
r
ed
ictio
n
s
,
w
h
ile
p
r
ec
is
io
n
r
e
f
lects
th
e
p
r
o
p
o
r
tio
n
o
f
c
o
r
r
ec
tl
y
id
en
tifie
d
m
atc
h
es
am
o
n
g
all
p
r
ed
icted
m
atch
es.
T
h
e
ev
alu
atio
n
f
o
cu
s
es
o
n
s
tan
d
ar
d
p
er
f
o
r
m
a
n
ce
m
etr
ics,
in
clu
d
in
g
p
r
ec
is
io
n
,
r
ec
all,
F1
-
s
co
r
e,
an
d
o
v
er
all
m
atch
in
g
ac
cu
r
ac
y
,
co
m
p
u
ted
co
n
s
is
ten
tly
ac
r
o
s
s
all
co
m
p
ar
ed
ap
p
r
o
ac
h
es.
All
m
eth
o
d
s
ar
e
ass
es
s
ed
u
n
d
er
th
e
s
am
e
ex
p
er
im
en
tal
co
n
d
itio
n
s
to
en
s
u
r
e
a
f
air
an
d
m
ea
n
in
g
f
u
l c
o
m
p
a
r
is
o
n
.
T
a
b
le
2
p
r
esen
ts
th
e
p
r
ec
is
io
n
,
r
ec
al
l,
an
d
ac
cu
r
ac
y
o
b
tain
ed
b
y
d
i
f
f
er
en
t m
eth
o
d
s
.
T
ab
le
2
.
Per
f
o
r
m
an
ce
m
etr
ics
o
f
Ma
tch
I
A
ac
r
o
s
s
v
ar
y
in
g
s
ch
em
a
s
izes
S
c
h
e
ma
s
i
z
e
A
c
c
u
r
a
c
y
(
%)
P
r
e
c
i
s
i
o
n
(
%)
R
e
c
a
l
l
(
%)
F1
-
s
c
o
r
e
(
%)
O
v
e
r
a
l
l
(
%)
1
0
c
o
l
u
m
n
s
92
9
3
.
0
9
1
.
2
9
2
.
1
9
2
.
0
5
2
0
c
o
l
u
m
n
s
93
9
4
.
2
9
2
.
7
9
3
.
4
9
3
.
2
0
5
0
c
o
l
u
m
n
s
94
9
5
.
1
9
3
.
5
9
4
.
3
9
4
.
1
5
T
h
e
lin
e
g
r
ap
h
in
Fig
u
r
e
3
illu
s
tr
ates
th
e
u
p
war
d
tr
en
d
in
ac
cu
r
ac
y
as
s
ch
em
a
s
ize
in
cr
ea
s
ed
,
co
n
f
ir
m
in
g
th
e
s
ca
lab
ilit
y
an
d
ad
ap
tab
ilit
y
o
f
th
e
m
o
d
el
ac
r
o
s
s
d
if
f
er
en
t
lev
els
o
f
s
ch
em
a
co
m
p
lex
ity
.
T
h
is
p
o
s
itiv
e
co
r
r
elatio
n
s
u
g
g
ests
th
at
Ma
tch
I
A
n
o
t
o
n
ly
h
an
d
les
s
m
all
an
d
m
o
d
er
at
ely
s
ized
s
ch
em
as
ef
f
ec
tiv
ely
b
u
t
also
b
en
e
f
its
f
r
o
m
ad
d
itio
n
al
co
n
tex
t
u
al
in
f
o
r
m
atio
n
av
ailab
le
in
lar
g
e
r
s
ch
em
as.
As
th
e
n
u
m
b
er
o
f
c
o
lu
m
n
s
g
r
o
ws,
t
h
e
m
o
d
el
is
ab
le
to
ca
p
tu
r
e
r
ich
er
s
em
an
tic
p
atter
n
s
,
le
ad
in
g
to
im
p
r
o
v
ed
m
atch
in
g
d
ec
is
io
n
s
.
Fig
u
r
e
3
p
l
o
ts
s
ch
e
m
a
s
i
ze
s
(
1
0
,
2
0
,
a
n
d
5
0
co
lu
m
n
s
)
o
n
th
e
x
-
a
x
is
a
g
ai
n
s
t
a
cc
u
r
ac
y
(
%)
o
n
t
h
e
y
-
a
x
is
,
s
h
o
wc
asi
n
g
t
h
e
m
o
d
el
’
s
c
o
n
s
is
t
en
cy
.
Des
p
i
te
i
n
c
r
e
asi
n
g
s
ch
em
a
c
o
m
p
l
ex
it
y
,
t
h
e
ac
c
u
r
ac
y
r
em
ai
n
s
h
ig
h
an
d
s
t
a
b
le
,
d
e
m
o
n
s
tr
ati
n
g
t
h
a
t
Ma
t
ch
I
A
is
n
o
t
ad
v
e
r
s
el
y
a
f
f
ec
t
ed
b
y
th
e
g
r
o
w
in
g
n
u
m
b
er
o
f
a
tt
r
i
b
u
tes
.
T
h
is
s
tab
ilit
y
is
c
r
u
ci
al
in
r
e
al
-
wo
r
l
d
e
n
v
ir
o
n
m
en
ts
w
h
er
e
d
ata
h
et
er
o
g
e
n
ei
ty
a
n
d
v
o
l
u
m
e
o
f
t
en
i
n
c
r
e
ase
o
v
er
ti
m
e
.
T
o
f
u
r
th
er
an
aly
ze
th
e
m
o
d
el’
s
ef
f
icien
cy
,
its
r
u
n
tim
e
f
o
r
p
r
o
ce
s
s
in
g
s
ch
em
as
o
f
d
if
f
er
en
t
s
izes
wa
s
m
ea
s
u
r
ed
.
Fig
u
r
e
4
p
r
esen
ts
a
r
u
n
tim
e
v
s
.
s
ch
em
a
s
ize
g
r
ap
h
.
T
h
e
o
b
s
er
v
ed
lin
ea
r
i
n
cr
ea
s
e
in
r
u
n
tim
e
in
d
icate
s
th
at
Ma
tch
I
A
s
ca
les
p
r
ed
ictab
ly
with
s
ch
em
a
s
iz
e.
A
g
r
ap
h
p
lo
ttin
g
r
u
n
tim
e
(
in
s
ec
o
n
d
s
)
o
n
th
e
y
-
ax
is
ag
ain
s
t
s
ch
em
a
s
izes
(
1
0
,
2
0
,
an
d
5
0
co
l
u
m
n
s
)
o
n
th
e
x
-
ax
is
.
T
o
id
e
n
tify
p
o
ten
tial
lim
itatio
n
s
,
an
er
r
o
r
b
r
ea
k
d
o
wn
was
co
n
d
u
cted
.
T
h
e
co
n
f
u
s
io
n
m
atr
ix
as
s
h
o
wn
in
T
ab
le
3
,
p
r
o
v
id
es
a
d
etai
led
o
v
er
v
iew
o
f
t
h
e
class
if
icatio
n
o
u
tco
m
es
f
o
r
th
e
5
0
-
c
o
lu
m
n
s
ch
em
a.
Fro
m
th
e
co
n
f
u
s
io
n
m
atr
ix
Fig
u
r
e
5
,
t
h
e
m
o
d
el
ex
h
ib
ited
a
f
alse
p
o
s
itiv
e
r
ate
(
FP
R
)
o
f
6
.
5
%,
p
r
im
ar
ily
d
u
e
to
s
em
an
tically
s
im
ilar
co
lu
m
n
n
am
es
(
e.
g
.
,
“Ad
d
r
ess
_
L
in
e”
v
s
.
“Str
ee
t_
Ad
d
r
ess
”)
.
T
h
ese
f
alse
p
o
s
itiv
es
wer
e
an
aly
ze
d
to
id
en
ti
f
y
th
e
r
o
o
t
ca
u
s
es,
r
ev
ea
lin
g
th
at
e
m
b
ed
d
in
g
s
f
o
r
s
im
ilar
ter
m
s
o
f
ten
o
v
e
r
lap
wi
th
o
u
t stric
t c
o
n
tex
tu
al
d
if
f
er
e
n
tiatio
n
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
Ma
tch
I
A
:
a
s
ema
n
tic
a
r
tifi
cia
l in
tellig
en
ce
s
o
lu
tio
n
fo
r
in
ter
o
p
era
b
ilit
y
in
s
ch
ema
…
(
Mo
h
a
med
R
a
o
u
i
)
4219
Fig
u
r
e
3
.
Mo
d
el
ac
cu
r
ac
y
ac
r
o
s
s
s
ch
em
a
s
izes
Fig
u
r
e
4
.
R
u
n
tim
e
v
s
.
s
ch
em
a
s
ize
T
ab
le
3
.
Dis
tr
ib
u
tio
n
o
f
p
r
ed
ic
tio
n
o
u
tco
m
es
O
u
t
c
o
m
e
C
o
u
n
t
Tr
u
e
p
o
si
t
i
v
e
s
(
TP)
1
8
8
Tr
u
e
n
e
g
a
t
i
v
e
s
(
TN
)
1
7
2
F
a
l
se
p
o
si
t
i
v
e
s
(FP)
12
F
a
l
se
n
e
g
a
t
i
v
e
s
(FN)
8
Fig
u
r
e
5
.
C
o
n
f
u
s
io
n
m
atr
i
x
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
1
5
,
No
.
5
,
Octo
b
er
2
0
2
6
:
4
2
1
3
-
4
2
2
3
4220
A
h
ea
tm
ap
-
s
ty
le
v
is
u
aliza
tio
n
r
ep
r
esen
tin
g
T
P,
T
N,
FP
,
an
d
FN,
p
r
o
v
id
in
g
a
n
in
tu
itiv
e
u
n
d
er
s
tan
d
i
n
g
o
f
th
e
m
o
d
el
’
s
s
tr
en
g
th
s
an
d
wea
k
n
ess
es.
A
n
ad
d
itio
n
al
er
r
o
r
d
is
tr
ib
u
tio
n
g
r
ap
h
as
s
h
o
wn
in
Fig
u
r
e
6
h
ig
h
lig
h
ts
th
e
f
r
eq
u
e
n
cy
o
f
f
alse
p
o
s
itiv
es
an
d
f
alse
n
eg
ativ
es
ac
r
o
s
s
d
if
f
er
e
n
t
s
c
h
em
a
s
izes.
A
b
a
r
ch
ar
t d
is
p
lay
in
g
th
e
co
u
n
ts
o
f
FP
an
d
FN f
o
r
s
ch
em
as with
1
0
,
2
0
,
an
d
5
0
c
o
lu
m
n
s
.
Fig
u
r
e
6
.
E
r
r
o
r
d
is
tr
ib
u
tio
n
ac
r
o
s
s
s
ch
em
a
s
izes
3
.
4
.
Co
m
pa
riso
n
wit
h e
x
is
t
ing
m
et
ho
ds
T
o
ev
alu
ate
th
e
ef
f
ec
tiv
e
n
ess
o
f
Ma
tch
I
A,
we
c
o
n
d
u
cted
a
c
o
m
p
ar
ativ
e
s
tu
d
y
ag
ai
n
s
t
s
ev
er
al
wid
ely
r
ec
o
g
n
ized
h
eu
r
is
tic
-
b
ased
s
ch
em
a
m
atch
in
g
alg
o
r
ith
m
s
,
i
n
clu
d
in
g
C
OM
A+
+,
C
u
p
id
,
s
im
ilar
ity
f
lo
o
d
in
g
(
SF
)
.
T
h
e
co
m
p
ar
ativ
e
ev
al
u
atio
n
was
p
er
f
o
r
m
ed
o
n
m
u
ltip
le
b
en
ch
m
a
r
k
d
ataset
s
,
an
d
th
e
r
esu
lts
s
u
m
m
ar
ized
i
n
th
e
Fig
u
r
e
7
h
ig
h
lig
h
t
t
h
e
im
p
r
o
v
e
d
p
er
f
o
r
m
an
ce
o
f
Ma
tch
I
A
in
ter
m
s
o
f
b
o
th
p
r
ec
is
io
n
an
d
F1
-
s
co
r
e.
Sp
ec
if
ically
,
Ma
tch
I
A
ac
h
iev
ed
an
av
er
a
g
e
F1
-
s
co
r
e
im
p
r
o
v
em
en
t
o
f
u
p
to
1
2
%
co
m
p
ar
e
d
to
tr
ad
itio
n
al
h
eu
r
is
tics
,
d
em
o
n
s
tr
atin
g
its
r
o
b
u
s
tn
ess
an
d
p
o
ten
tial f
o
r
r
ea
l
-
wo
r
l
d
s
ch
em
a
in
te
g
r
atio
n
task
s
.
Fig
u
r
e
7
.
Per
f
o
r
m
an
c
e
co
m
p
ar
is
o
n
o
f
Ma
tch
I
A
a
n
d
h
e
u
r
is
tic
-
b
ased
alg
o
r
ith
m
s
T
h
e
o
b
tain
e
d
r
esu
lts
ar
e
co
n
s
i
s
ten
t
with
r
ec
en
t
s
ch
em
a
m
atch
in
g
s
tu
d
ies
h
i
g
h
lig
h
tin
g
th
e
l
im
itatio
n
s
o
f
h
e
u
r
is
tic
ap
p
r
o
ac
h
es
f
o
r
h
et
er
o
g
en
e
o
u
s
s
ch
em
as.
As
s
h
o
wn
in
Fig
u
r
e
7
,
C
OM
A+
+,
C
u
p
id
,
an
d
SF
ac
h
iev
e
lo
wer
p
r
ec
is
io
n
an
d
F1
-
s
co
r
e
t
h
an
Ma
tch
I
A.
R
ec
en
t
s
tu
d
ies
[
2
6
]
,
[
1
2
]
s
im
ilar
ly
d
em
o
n
s
tr
ate
th
e
ef
f
ec
tiv
en
ess
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J Ar
tif
I
n
tell
I
SS
N:
2252
-
8
9
3
8
Ma
tch
I
A
:
a
s
ema
n
tic
a
r
tifi
cia
l in
tellig
en
ce
s
o
lu
tio
n
fo
r
in
ter
o
p
era
b
ilit
y
in
s
ch
ema
…
(
Mo
h
a
med
R
a
o
u
i
)
4221
o
f
lear
n
in
g
-
b
ased
an
d
h
y
b
r
id
s
em
an
tic
ap
p
r
o
ac
h
es.
Acc
o
r
d
in
g
ly
,
Ma
tch
I
A
p
r
o
v
i
d
es
h
ig
h
er
ac
cu
r
ac
y
wh
ile
r
em
ain
in
g
lig
h
tweig
h
t,
in
ter
p
r
etab
le,
an
d
s
u
itab
le
f
o
r
p
r
ac
tical
in
ter
o
p
er
a
b
ilit
y
s
ce
n
ar
io
s
.
T
h
e
o
b
s
er
v
ed
im
p
r
o
v
e
m
en
ts
ar
e
co
n
s
is
ten
tly
r
ef
lecte
d
ac
r
o
s
s
all
ev
alu
atio
n
m
etr
ics
an
d
b
en
ch
m
ar
k
d
atasets
,
in
d
icatin
g
th
e
r
o
b
u
s
tn
ess
o
f
th
e
p
r
o
p
o
s
ed
a
p
p
r
o
ac
h
.
T
h
e
ag
r
ee
m
en
t
b
etwe
e
n
p
r
ec
is
io
n
,
r
ec
all
,
F1
-
s
co
r
e,
an
d
ac
cu
r
ac
y
f
u
r
th
er
s
u
p
p
o
r
ts
th
e
r
eliab
ilit
y
o
f
th
e
o
b
tain
ed
r
esu
lts
.
B
ey
o
n
d
th
e
q
u
an
titativ
e
im
p
r
o
v
em
e
n
ts
,
Ma
tch
I
A
ad
v
an
ce
s
th
e
s
tate
o
f
th
e
ar
t
b
y
co
m
b
in
i
n
g
s
em
an
tic
em
b
ed
d
in
g
s
with
an
in
ter
p
r
etab
le
m
ac
h
in
e
lear
n
in
g
m
o
d
el,
p
r
o
v
i
d
in
g
a
b
etter
b
a
lan
ce
b
etwe
en
m
atch
in
g
ac
cu
r
ac
y
,
co
m
p
u
tatio
n
a
l
ef
f
icien
cy
,
an
d
ex
p
lain
a
b
ilit
y
th
an
tr
ad
itio
n
al
h
e
u
r
is
tic
ap
p
r
o
ac
h
es.
T
h
ese
ch
ar
ac
ter
is
tics
m
ak
e
th
e
p
r
o
p
o
s
ed
m
eth
o
d
s
u
itab
le
f
o
r
p
r
ac
tical
ap
p
licatio
n
s
s
u
ch
as
en
ter
p
r
is
e
d
ata
in
teg
r
atio
n
,
d
atab
ase
m
ig
r
atio
n
,
an
d
s
em
an
tic
in
ter
o
p
er
ab
ilit
y
ac
r
o
s
s
h
eter
o
g
en
eo
u
s
in
f
o
r
m
atio
n
s
y
s
tem
s
.
T
o
f
u
r
th
e
r
co
n
te
x
tu
alize
Ma
tch
I
A
’
s
p
er
f
o
r
m
an
ce
,
its
p
r
ec
is
i
o
n
-
r
ec
all
cu
r
v
e
as sh
o
wn
in
Fi
g
u
r
e
8
was
an
aly
ze
d
.
T
h
e
ar
ea
u
n
d
e
r
th
e
cu
r
v
e
(
AUC)
o
f
0
.
9
2
f
o
r
M
atch
I
A
d
em
o
n
s
tr
ates
its
ab
ilit
y
to
m
ain
tain
h
ig
h
p
r
ec
is
io
n
an
d
r
ec
all
ev
e
n
u
n
d
er
ch
allen
g
in
g
s
ce
n
ar
io
s
with
o
v
er
lap
p
in
g
co
l
u
m
n
n
a
m
es.
A
p
r
ec
is
io
n
-
r
ec
all
cu
r
v
e
g
r
a
p
h
with
Ma
tch
I
A’
s
cu
r
v
e
p
lo
tted
ag
ai
n
s
t
b
aselin
es,
h
ig
h
lig
h
tin
g
its
s
u
p
er
io
r
p
er
f
o
r
m
an
ce
.
T
h
ese
ex
p
er
im
en
tal
f
in
d
in
g
s
p
r
o
v
id
e
in
s
ig
h
ts
in
to
th
e
e
f
f
ec
tiv
en
ess
o
f
th
e
p
r
o
p
o
s
ed
a
p
p
r
o
ac
h
an
d
m
o
tiv
ate
th
e
co
n
clu
d
in
g
d
is
cu
s
s
io
n
p
r
esen
t
ed
in
th
e
n
ex
t sectio
n
.
Fig
u
r
e
8
.
Pre
cisi
o
n
-
r
ec
all
cu
r
v
e
f
o
r
Ma
tch
I
A
4.
CO
NCLU
SI
O
N
T
h
is
wo
r
k
i
n
tr
o
d
u
ce
s
Ma
tch
I
A,
a
s
u
p
er
v
is
ed
s
em
an
tic
s
ch
em
a
m
atch
in
g
f
r
a
m
ewo
r
k
th
a
t
co
m
b
in
es
s
em
an
tic
em
b
ed
d
in
g
s
with
a
r
an
d
o
m
f
o
r
est
class
if
ier
to
p
r
o
v
id
e
an
ef
f
ec
tiv
e,
in
ter
p
r
e
tab
le,
an
d
s
ca
lab
le
s
o
lu
tio
n
f
o
r
d
ata
in
ter
o
p
er
ab
ilit
y
.
T
h
e
ex
p
er
im
e
n
tal
ev
al
u
atio
n
h
ig
h
lig
h
ts
co
n
s
is
ten
t
im
p
r
o
v
em
e
n
ts
o
v
er
tr
ad
itio
n
al
h
eu
r
is
tic
m
eth
o
d
s
,
p
ar
ticu
lar
ly
in
ter
m
s
o
f
p
r
ec
is
io
n
an
d
r
ec
all,
wh
ich
co
n
f
ir
m
s
th
e
ab
ilit
y
o
f
th
e
ap
p
r
o
ac
h
to
id
en
tify
r
elev
a
n
t
s
em
an
tic
r
elatio
n
s
h
ip
s
b
etw
ee
n
h
eter
o
g
e
n
eo
u
s
s
ch
em
a
elem
en
ts
.
T
h
e
m
ain
co
n
tr
ib
u
tio
n
o
f
th
is
s
tu
d
y
lies
in
th
e
in
teg
r
atio
n
o
f
lin
g
u
is
tic
r
ep
r
esen
tatio
n
s
with
well
-
estab
lis
h
ed
m
ac
h
in
e
lear
n
in
g
tec
h
n
iq
u
es,
r
esu
ltin
g
in
a
s
o
lu
tio
n
th
at
is
b
o
th
i
n
ter
p
r
etab
le
an
d
ad
a
p
tab
le
to
v
ar
y
in
g
d
ata
v
o
lu
m
es.
Mo
r
eo
v
er
,
th
e
o
b
tain
e
d
r
esu
l
ts
s
u
g
g
est
th
at
th
e
p
r
o
p
o
s
ed
ap
p
r
o
ac
h
ca
n
b
e
e
f
f
ec
tiv
ely
ap
p
lied
in
p
r
ac
tical
s
ettin
g
s
s
u
ch
as
en
ter
p
r
is
e
d
ata
in
teg
r
atio
n
,
d
o
m
ain
-
s
p
ec
if
ic
d
atasets
,
an
d
clo
u
d
-
b
ased
d
ata
p
latf
o
r
m
s
,
th
er
e
b
y
s
u
p
p
o
r
tin
g
r
ea
l
-
wo
r
l
d
in
ter
o
p
e
r
ab
ilit
y
r
eq
u
ir
e
m
en
ts
.
F
UNDING
I
NF
O
R
M
A
T
I
O
N
Au
th
o
r
s
s
tate
n
o
f
u
n
d
in
g
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
t
r
ib
u
to
r
R
o
les
T
a
x
o
n
o
m
y
(
C
R
ed
iT)
to
r
ec
o
g
n
ize
in
d
iv
i
d
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
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8
9
3
8
I
n
t J Ar
tif
I
n
tell
,
Vo
l.
1
5
,
No
.
5
,
Octo
b
er
2
0
2
6
:
4
2
1
3
-
4
2
2
3
4222
Na
m
e
o
f
Aut
ho
r
C
M
So
Va
Fo
I
R
D
O
E
Vi
Su
P
Fu
Mo
h
am
ed
R
ao
u
i
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
✓
Mo
u
lay
Haf
id
E
l Y
az
id
i
✓
✓
✓
✓
✓
✓
✓
Ah
m
ed
Z
ello
u
✓
✓
✓
✓
✓
✓
✓
✓
C
:
C
o
n
c
e
p
t
u
a
l
i
z
a
t
i
o
n
M
:
M
e
t
h
o
d
o
l
o
g
y
So
:
So
f
t
w
a
r
e
Va
:
Va
l
i
d
a
t
i
o
n
Fo
:
Fo
r
mal
a
n
a
l
y
s
i
s
I
:
I
n
v
e
s
t
i
g
a
t
i
o
n
R
:
R
e
so
u
r
c
e
s
D
:
D
a
t
a
C
u
r
a
t
i
o
n
O
:
W
r
i
t
i
n
g
-
O
r
i
g
i
n
a
l
D
r
a
f
t
E
:
W
r
i
t
i
n
g
-
R
e
v
i
e
w
&
E
d
i
t
i
n
g
Vi
:
Vi
su
a
l
i
z
a
t
i
o
n
Su
:
Su
p
e
r
v
i
s
i
o
n
P
:
P
r
o
j
e
c
t
a
d
mi
n
i
st
r
a
t
i
o
n
Fu
:
Fu
n
d
i
n
g
a
c
q
u
i
si
t
i
o
n
CO
NF
L
I
C
T
O
F
I
N
T
E
R
E
S
T
ST
A
T
E
M
E
NT
Au
th
o
r
s
s
tate
n
o
co
n
f
lict o
f
in
t
er
est.
DATA AV
AI
L
AB
I
L
I
T
Y
T
h
e
b
en
ch
m
a
r
k
d
ataset
was
d
er
iv
ed
f
r
o
m
th
e
p
u
b
licly
av
ailab
le
Sch
em
a.
o
r
g
v
o
ca
b
u
lar
y
.
T
h
e
p
r
o
ce
s
s
ed
d
ata
s
u
p
p
o
r
tin
g
t
h
e
f
in
d
in
g
s
o
f
th
is
s
tu
d
y
ar
e
a
v
ailab
le
f
r
o
m
t
h
e
co
r
r
esp
o
n
d
i
n
g
a
u
th
o
r
,
[
MR],
u
p
o
n
r
ea
s
o
n
ab
le
r
eq
u
est.
RE
F
E
R
E
NC
E
S
[
1
]
E.
R
a
h
m
a
n
d
E
.
P
e
u
k
e
r
t
,
“
H
o
l
i
s
t
i
c
sc
h
e
m
a
m
a
t
c
h
i
n
g
,
”
i
n
En
c
y
c
l
o
p
e
d
i
a
o
f
Bi
g
D
a
t
a
T
e
c
h
n
o
l
o
g
i
e
s
,
C
h
a
m:
S
p
r
i
n
g
e
r
I
n
t
e
r
n
a
t
i
o
n
a
l
P
u
b
l
i
s
h
i
n
g
,
2
0
1
9
,
p
p
.
9
6
0
–
9
6
5
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
3
-
3
1
9
-
7
7
5
2
5
-
8
_
1
2
.
[
2
]
E.
R
a
h
m
a
n
d
E.
P
e
u
k
e
r
t
,
“
L
a
r
g
e
-
s
c
a
l
e
sc
h
e
m
a
ma
t
c
h
i
n
g
,
”
i
n
E
n
c
y
c
l
o
p
e
d
i
a
o
f
Bi
g
D
a
t
a
T
e
c
h
n
o
l
o
g
i
e
s
,
C
h
a
m:
S
p
r
i
n
g
e
r
I
n
t
e
r
n
a
t
i
o
n
a
l
P
u
b
l
i
s
h
i
n
g
,
2
0
1
9
,
p
p
.
1
1
0
5
–
1
1
1
0
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
3
-
3
1
9
-
7
7
5
2
5
-
8
_
3
3
0
.
[
3
]
J.
K
ö
p
k
e
,
“
A
n
n
o
t
a
t
i
o
n
p
a
t
h
s
f
o
r
ma
t
c
h
i
n
g
X
M
L
-
S
c
h
e
mas
,
”
D
a
t
a
&
K
n
o
w
l
e
d
g
e
E
n
g
i
n
e
e
r
i
n
g
,
v
o
l
.
1
2
2
,
p
p
.
2
5
–
5
4
,
Ju
l
.
2
0
1
9
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
d
a
t
a
k
.
2
0
1
7
.
1
2
.
0
0
2
.
[
4
]
P
.
R
o
u
ssi
l
l
e
,
I
.
M
e
g
d
i
c
h
e
,
O
.
T
e
st
e
,
a
n
d
C
.
Tr
o
j
a
h
n
,
“
B
o
o
s
t
i
n
g
h
o
l
i
s
t
i
c
o
n
t
o
l
o
g
y
ma
t
c
h
i
n
g
:
g
e
n
e
r
a
t
i
n
g
g
r
a
p
h
c
l
i
q
u
e
-
b
a
se
d
r
e
l
a
x
e
d
r
e
f
e
r
e
n
c
e
a
l
i
g
n
m
e
n
t
s f
o
r
h
o
l
i
s
t
i
c
e
v
a
l
u
a
t
i
o
n
,
”
2
0
1
8
,
p
p
.
3
5
5
–
3
6
9
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
3
-
030
-
0
3
6
6
7
-
6
_
2
3
.
[
5
]
J.
P
o
r
t
i
s
c
h
,
M
.
H
l
a
d
i
k
,
a
n
d
H
.
P
a
u
l
h
e
i
m,
“
B
a
c
k
g
r
o
u
n
d
k
n
o
w
l
e
d
g
e
i
n
o
n
t
o
l
o
g
y
ma
t
c
h
i
n
g
:
a
su
r
v
e
y
,
”
S
e
m
a
n
t
i
c
We
b
,
p
p
.
1
–
5
5
,
S
e
p
.
2
0
2
2
,
d
o
i
:
1
0
.
3
2
3
3
/
S
W
-
2
2
3
0
8
5
.
[
6
]
I
.
M
.
P
u
t
r
a
ma
a
n
d
P
.
M
a
r
t
i
n
e
k
,
“
H
e
t
e
r
o
g
e
n
e
o
u
s
d
a
t
a
i
n
t
e
g
r
a
t
i
o
n
:
c
h
a
l
l
e
n
g
e
s
a
n
d
o
p
p
o
r
t
u
n
i
t
i
e
s
,
”
D
a
t
a
i
n
Br
i
e
f
,
v
o
l
.
5
6
,
O
c
t
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
d
i
b
.
2
0
2
4
.
1
1
0
8
5
3
.
[
7
]
K
.
R
a
m
a
r
,
R
.
A
p
p
o
v
o
o
,
H
.
S
h
a
n
mu
g
a
su
n
d
a
r
a
m
,
a
n
d
B
.
A
,
“
S
e
m
a
n
t
i
c
h
e
t
e
r
o
g
e
n
e
i
t
y
m
a
n
a
g
e
me
n
t
b
e
t
w
e
e
n
w
e
a
t
h
e
r
s
y
st
e
ms
u
s
i
n
g
o
n
t
o
l
o
g
y
ma
p
p
i
n
g
,
”
i
n
2
0
2
2
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
D
i
sru
p
t
i
v
e
T
e
c
h
n
o
l
o
g
i
e
s
f
o
r
Mu
l
t
i
-
D
i
sc
i
p
l
i
n
a
ry
Re
se
a
r
c
h
a
n
d
Ap
p
l
i
c
a
t
i
o
n
s (
C
EN
T
C
O
N
)
,
D
e
c
.
2
0
2
2
,
p
p
.
5
2
–
57
,
d
o
i
:
1
0
.
1
1
0
9
/
C
EN
T
C
O
N
5
6
6
1
0
.
2
0
2
2
.
1
0
0
5
1
4
8
4
.
[
8
]
C
.
K
o
u
t
r
a
s
e
t
a
l
.
,
“
V
a
l
e
n
t
i
n
e
:
e
v
a
l
u
a
t
i
n
g
ma
t
c
h
i
n
g
t
e
c
h
n
i
q
u
e
s
f
o
r
d
a
t
a
s
e
t
d
i
sco
v
e
r
y
,
”
i
n
2
0
2
1
I
EEE
3
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
D
a
t
a
E
n
g
i
n
e
e
r
i
n
g
(
I
C
D
E)
,
A
p
r
.
2
0
2
1
,
p
p
.
4
6
8
–
479
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
D
E5
1
3
9
9
.
2
0
2
1
.
0
0
0
4
7
.
[
9
]
A
.
B
e
r
r
o
,
I
.
M
e
g
d
i
c
h
e
,
a
n
d
O
.
Te
s
t
e
,
“
A
l
i
n
e
a
r
p
r
o
g
r
a
m
f
o
r
h
o
l
i
st
i
c
mat
c
h
i
n
g
:
a
ssess
me
n
t
o
n
s
c
h
e
ma
ma
t
c
h
i
n
g
b
e
n
c
h
mar
k
,
”
i
n
D
a
t
a
b
a
se
a
n
d
E
x
p
e
rt
S
y
st
e
m
s A
p
p
l
i
c
a
t
i
o
n
s
,
C
h
a
m:
S
p
r
i
n
g
e
r
,
2
0
1
5
,
p
p
.
3
8
3
–
3
9
8
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
3
-
3
1
9
-
2
2
8
5
2
-
5
_
3
3
.
[
1
0
]
K
.
R
a
m
a
r
,
“
H
e
t
e
r
o
g
e
n
e
i
t
y
ma
n
a
g
e
m
e
n
t
u
s
i
n
g
O
A
EI
b
e
n
c
h
mark
d
a
t
a
s
e
t
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
E
n
g
i
n
e
e
r
i
n
g
&
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
7
,
n
o
.
3
.
1
2
,
Ju
l
.
2
0
1
8
,
d
o
i
:
1
0
.
1
4
4
1
9
/
i
j
e
t
.
v
7
i
3
.
1
2
.
1
6
1
6
3
.
[
1
1
]
E.
R
a
h
m
,
“
T
o
w
a
r
d
s l
a
r
g
e
-
s
c
a
l
e
sc
h
e
m
a
a
n
d
o
n
t
o
l
o
g
y
m
a
t
c
h
i
n
g
,
”
i
n
S
c
h
e
m
a
Ma
t
c
h
i
n
g
a
n
d
M
a
p
p
i
n
g
,
B
e
r
l
i
n
,
H
e
i
d
e
l
b
e
r
g
:
S
p
r
i
n
g
e
r
,
2
0
1
1
,
p
p
.
3
–
27
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
3
-
6
4
2
-
1
6
5
1
8
-
4
_
1
.
[
1
2
]
M
.
A
.
-
U
.
-
R
a
h
ma
n
e
t
a
l
.
,
“
A
sem
i
-
a
u
t
o
ma
t
e
d
h
y
b
r
i
d
sc
h
e
m
a
ma
t
c
h
i
n
g
f
r
a
m
e
w
o
r
k
f
o
r
v
e
g
e
t
a
t
i
o
n
d
a
t
a
i
n
t
e
g
r
a
t
i
o
n
,
”
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
.
2
2
9
,
N
o
v
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
e
sw
a
.
2
0
2
3
.
1
2
0
4
0
5
.
[
1
3
]
B.
V
i
l
l
á
n
y
i
a
n
d
P
.
M
a
r
t
i
n
e
k
,
“
A
u
t
o
m
a
t
i
o
n
o
f
s
c
e
n
a
r
i
o
-
b
a
se
d
sc
h
e
m
a
m
a
t
c
h
e
r
o
p
t
i
mi
z
a
t
i
o
n
,
”
Ac
t
a
E
l
e
c
t
r
o
t
e
c
h
n
i
c
a
e
t
I
n
f
o
rm
a
t
i
c
a
,
v
o
l
.
1
6
,
n
o
.
1
,
p
p
.
3
–
1
0
,
M
a
r
.
2
0
1
6
,
d
o
i
:
1
0
.
1
5
5
4
6
/
a
e
e
i
-
2
0
1
6
-
0
0
0
1
.
[
1
4
]
A
.
G
u
d
a
l
a
,
L.
Z.
L
i
,
D
.
K
a
r
,
A
.
M
.
M
a
h
d
y
,
a
n
d
M
.
X
i
a
o
,
“
A
h
o
l
i
s
t
i
c
s
c
h
e
ma
ma
t
c
h
e
r
,”
A
d
v
a
n
c
e
d
M
a
t
e
ri
a
l
s
Re
se
a
r
c
h
,
v
o
l
.
2
2
5
–
2
2
6
,
p
p
.
1
2
4
2
–
1
2
4
5
,
A
p
r
.
2
0
1
1
,
d
o
i
:
1
0
.
4
0
2
8
/
w
w
w
.
s
c
i
e
n
t
i
f
i
c
.
n
e
t
/
A
M
R
.
2
2
5
-
2
2
6
.
1
2
4
2
.
[
1
5
]
M
.
M
o
h
a
mm
a
d
i
,
W
.
H
o
f
ma
n
,
a
n
d
Y
.
-
H
.
T
a
n
,
“
S
A
N
O
M
-
H
O
B
B
I
T:
si
m
u
l
a
t
e
d
a
n
n
e
a
l
i
n
g
-
b
a
s
e
d
o
n
t
o
l
o
g
y
ma
t
c
h
i
n
g
o
n
H
O
B
B
I
T
p
l
a
t
f
o
r
m
,
”
T
h
e
K
n
o
w
l
e
d
g
e
E
n
g
i
n
e
e
ri
n
g
R
e
v
i
e
w
,
v
o
l
.
3
5
,
M
a
r
.
2
0
2
0
,
d
o
i
:
1
0
.
1
0
1
7
/
S
0
2
6
9
8
8
8
9
2
0
0
0
0
1
7
X
.
[
1
6
]
T.
T.
A
.
N
g
u
y
e
n
a
n
d
S
.
C
o
n
r
a
d
,
“
O
n
t
o
l
o
g
y
m
a
t
c
h
i
n
g
u
s
i
n
g
m
u
l
t
i
p
l
e
s
i
mi
l
a
r
i
t
y
m
e
a
s
u
r
e
s
,
”
i
n
2
0
1
5
7
t
h
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
K
n
o
w
l
e
d
g
e
D
i
s
c
o
v
e
ry,
K
n
o
w
l
e
d
g
e
E
n
g
i
n
e
e
r
i
n
g
a
n
d
K
n
o
w
l
e
d
g
e
M
a
n
a
g
e
m
e
n
t
(
I
C
3
K
)
,
2
0
1
5
,
p
p
.
6
0
3
–
6
1
1
,
d
o
i
:
1
0
.
5
2
2
0
/
0
0
0
5
6
1
5
6
0
6
0
3
0
6
1
1
.
[
1
7
]
M
.
M
o
h
a
mm
a
d
i
,
W
.
H
o
f
m
a
n
,
a
n
d
Y
.
-
H
.
Ta
n
,
“
S
i
m
u
l
a
t
e
d
a
n
n
e
a
l
i
n
g
-
b
a
s
e
d
o
n
t
o
l
o
g
y
ma
t
c
h
i
n
g
,
”
AC
M
T
ra
n
s
a
c
t
i
o
n
s
o
n
Ma
n
a
g
e
m
e
n
t
I
n
f
o
rm
a
t
i
o
n
S
y
s
t
e
m
s
,
v
o
l
.
1
0
,
n
o
.
1
,
p
p
.
1
–
2
4
,
M
a
r
.
2
0
1
9
,
d
o
i
:
1
0
.
1
1
4
5
/
3
3
1
4
9
4
8
.
[
1
8
]
S
.
U
.
P
i
l
a
p
i
t
i
y
a
,
“
I
O
n
t
o
-
o
n
t
o
l
o
g
y
d
r
i
v
e
n
a
p
p
r
o
a
c
h
f
o
r
se
l
e
c
t
i
n
g
a
p
p
r
o
p
r
i
a
t
e
o
n
t
o
l
o
g
y
m
a
t
c
h
i
n
g
a
l
g
o
r
i
t
h
m
,
”
i
n
2
0
1
7
I
n
t
e
rn
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
Re
s
e
a
rc
h
a
n
d
I
n
n
o
v
a
t
i
o
n
i
n
I
n
f
o
rm
a
t
i
o
n
S
y
s
t
e
m
s
,
Ju
l
.
2
0
1
7
,
p
p
.
1
–
6
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
R
I
I
S
.
2
0
1
7
.
8
0
0
2
4
3
8
.
[
1
9
]
J.
K
i
m,
Y
.
P
e
n
g
,
N
.
I
v
e
z
i
c
,
a
n
d
J
.
S
h
i
n
,
“
A
n
o
p
t
i
m
i
z
a
t
i
o
n
a
p
p
r
o
a
c
h
f
o
r
s
e
ma
n
t
i
c
-
b
a
se
d
X
M
L
s
c
h
e
m
a
m
a
t
c
h
i
n
g
,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
T
r
a
d
e
,
Ec
o
n
o
m
i
c
s
a
n
d
F
i
n
a
n
c
e
,
p
p
.
7
8
–
8
6
,
2
0
1
1
,
d
o
i
:
1
0
.
7
7
6
3
/
I
JTEF.
2
0
1
1
.
V
2
.
8
2
.
[
2
0
]
S
.
B
o
r
o
w
i
c
c
a
n
d
S
.
A
.
-
S
o
u
z
a
,
“
H
e
t
e
r
o
g
e
n
e
o
u
s
d
a
t
a
i
n
t
e
g
r
a
t
i
o
n
:
a
l
i
t
e
r
a
t
u
r
e
sc
o
p
e
r
e
v
i
e
w
,
”
i
n
2
6
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
En
t
e
r
p
ri
s
e
I
n
f
o
rm
a
t
i
o
n
S
y
st
e
m
s
,
2
0
2
4
,
p
p
.
1
8
9
–
2
0
0
,
d
o
i
:
1
0
.
5
2
2
0
/
0
0
1
2
5
5
1
0
0
0
0
0
3
6
9
0
.
[
2
1
]
C
.
M
a
,
B
.
M
o
l
n
a
r
,
A
.
Ta
r
c
s
i
,
a
n
d
A
.
B
e
n
c
z
u
r
,
“
K
n
o
w
l
e
d
g
e
e
n
r
i
c
h
e
d
sch
e
ma
ma
t
c
h
i
n
g
f
r
a
mew
o
r
k
f
o
r
h
e
t
e
r
o
g
e
n
e
o
u
s
d
a
t
a
i
n
t
e
g
r
a
t
i
o
n
,
”
i
n
2
0
2
2
I
E
EE
2
n
d
C
o
n
f
e
re
n
c
e
o
n
I
n
f
o
rm
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
a
n
d
D
a
t
a
S
c
i
e
n
c
e
,
M
a
y
2
0
2
2
,
p
p
.
1
8
3
–
188
,
d
o
i
:
1
0
.
1
1
0
9
/
C
I
TD
S
5
4
9
7
6
.
2
0
2
2
.
9
9
1
4
3
5
0
.
Evaluation Warning : The document was created with Spire.PDF for Python.