I
nte
rna
t
io
na
l J
o
urna
l o
f
E
lect
rica
l a
nd
Co
m
p
ute
r
E
ng
in
ee
ring
(
I
J
E
CE
)
Vo
l.
10
,
No
.
4
,
A
u
g
u
s
t
2020
,
p
p
.
3
7
4
3
~
3
7
5
0
I
SS
N:
2088
-
8708
,
DOI
: 1
0
.
1
1
5
9
1
/
i
j
ec
e
.
v
10
i
4
.
p
p
3
7
4
3
-
3
7
5
0
3743
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ec
e.
ia
esco
r
e.
co
m/in
d
ex
.
p
h
p
/I
JE
C
E
An ada
ptatio
n of
Tex
t2Ont
o
for su
ppo
rting
the
French
l
a
ng
ua
g
e
M
o
ra
d H
a
j
j
i,
M
o
ha
m
m
e
d Q
ba
do
u,
K
ha
lifa
M
a
ns
o
uri
S
ig
n
a
ls,
Distrib
u
ted
S
y
ste
m
s a
n
d
A
rti
f
icia
l
In
telli
g
e
n
c
e
lab
o
ra
to
ry
(S
S
DIA
),
Un
iv
e
rsit
y
Ha
ss
a
n
II
Ca
sa
b
lan
c
a
,
M
o
r
o
c
c
o
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
u
l 8
,
2
0
1
9
R
ev
i
s
ed
J
an
1
5
,
2
0
2
0
A
cc
ep
ted
Feb
1
,
2
0
2
0
T
h
e
o
n
to
lo
g
ies
a
re
p
ro
g
re
ss
iv
e
ly
i
m
p
o
sin
g
th
e
m
se
lv
e
s
in
th
e
f
i
e
ld
o
f
k
n
o
w
led
g
e
m
a
n
a
g
e
m
e
n
t.
W
h
il
e
th
e
m
a
n
u
a
l
c
o
n
stru
c
ti
o
n
o
f
a
n
o
n
t
o
lo
g
y
is
b
y
f
a
r
th
e
m
o
st
re
li
a
b
le,
th
is
tas
k
h
a
s
p
ro
v
e
d
t
o
b
e
t
o
o
te
d
io
u
s
a
n
d
e
x
p
e
n
siv
e
.
T
o
a
ss
ist
h
u
m
a
n
s
in
th
e
p
ro
c
e
ss
o
f
b
u
il
d
in
g
a
n
o
n
to
l
o
g
y
,
se
v
e
ra
l
to
o
ls
h
a
v
e
e
m
e
rg
e
d
p
ro
p
o
sin
g
th
e
a
u
t
o
m
a
ti
c
o
r
se
m
i
-
a
u
to
m
a
ti
c
c
o
n
stru
c
ti
o
n
o
f
o
n
t
o
lo
g
ies
.
In
th
is
c
o
n
tex
t,
Tex
t2
On
to
h
a
s
b
e
c
o
m
e
o
n
e
o
f
th
e
m
o
st
re
c
o
g
n
ize
d
o
n
t
o
l
o
g
y
le
a
rn
in
g
to
o
ls.
T
h
e
p
e
rf
o
rm
a
n
c
e
o
f
th
is
to
o
l
is
c
o
n
f
irme
d
b
y
s
e
v
e
r
a
l
re
s
e
a
rc
h
wo
rk
s.
Ho
w
e
v
e
r,
th
e
d
e
v
e
lo
p
m
e
n
t
o
f
th
is
to
o
l
is
b
a
se
d
o
n
P
rin
c
e
to
n
W
o
rd
Ne
t
(
P
W
N)
f
o
r
En
g
li
sh
.
A
s
a
re
su
lt
,
it
is
li
m
it
e
d
to
t
h
e
p
r
o
c
e
ss
in
g
o
f
tex
tu
a
l
re
so
u
rc
e
s
w
ri
tt
e
n
in
En
g
li
sh
.
In
t
h
is
p
a
p
e
r,
w
e
p
re
s
e
n
t
o
u
r
a
p
p
r
o
a
c
h
b
a
se
d
o
n
JW
OL
F
,
a
Ja
v
a
A
P
I
to
a
c
c
e
ss
th
e
f
re
e
W
o
rd
Ne
t
f
o
r
F
re
n
c
h
th
a
t
w
e
h
a
v
e
d
e
v
e
lo
p
e
d
to
a
d
a
p
t
th
i
s
to
o
l
f
o
r
th
e
c
o
n
str
u
c
ti
o
n
o
f
o
n
to
l
o
g
ies
f
ro
m
c
o
rp
u
s
in
F
re
n
c
h
.
T
o
e
v
a
lu
a
te
th
e
u
se
f
u
ln
e
ss
o
f
o
u
r
a
p
p
ro
a
c
h
,
w
e
a
ss
e
ss
e
d
th
e
p
e
rf
o
rm
a
n
c
e
o
f
th
e
im
p
ro
v
e
d
v
e
rsio
n
o
f
T
e
x
t2
On
to
o
n
a
sim
p
li
stic
c
o
rp
u
s
o
f
F
re
n
c
h
lan
g
u
a
g
e
d
o
c
u
m
e
n
ts.
T
h
e
re
su
lt
s
o
f
th
is
e
x
p
e
ri
m
e
n
t
h
a
v
e
sh
o
w
n
th
a
t
th
e
i
m
p
ro
v
e
d
v
e
rsio
n
o
f
T
e
x
t2
On
to
a
c
c
o
rd
i
n
g
t
o
o
u
r
a
p
p
r
o
a
c
h
is
e
f
fe
c
ti
v
e
f
o
r
th
e
c
o
n
str
u
c
ti
o
n
o
f
a
n
ont
o
lo
g
y
f
ro
m
te
x
tu
a
l
d
o
c
u
m
e
n
ts i
n
t
h
e
F
re
n
c
h
lan
g
u
a
g
e
.
K
ey
w
o
r
d
s
:
J
W
OL
F
Natu
r
al
la
n
g
u
a
g
e
p
r
o
ce
s
s
in
g
W
o
r
d
Net
On
to
lo
g
y
lear
n
i
n
g
On
to
lo
g
y
Se
m
a
n
tic
w
eb
T
ex
t2
On
to
Co
p
y
rig
h
t
©
2
0
2
0
In
stit
u
te o
f
A
d
v
a
n
c
e
d
E
n
g
i
n
e
e
rin
g
a
n
d
S
c
ien
c
e
.
Al
l
rig
h
ts re
se
rv
e
d
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
Hajj
i M
o
r
ad
,
Sig
n
als,
Di
s
tr
ib
u
ted
S
y
s
te
m
s
a
n
d
A
r
ti
f
icia
l I
n
telli
g
e
n
ce
lab
o
r
ato
r
y
(
S
SDI
A
)
,
Un
i
v
er
s
it
y
Has
s
an
I
I
C
a
s
ab
lan
ca
,
Mo
r
o
cc
o
.
E
m
ail:
m
o
r
ad
.
h
aj
j
i@
g
m
ail.
co
m
1.
I
NT
RO
D
UCT
I
O
N
His
to
r
icall
y
,
t
h
e
o
r
ig
i
n
s
o
f
t
h
e
ter
m
“
o
n
to
lo
g
y
”
d
ate
b
ac
k
to
th
e
ti
m
e
o
f
p
h
ilo
s
o
p
h
er
s
P
lato
an
d
A
r
i
s
to
tle
(
4
0
0
-
3
6
0
B
C
)
.
T
h
is
ter
m
i
s
co
m
p
o
s
ed
o
f
t
h
e
Gr
ee
k
li
n
g
u
i
s
tic
r
o
o
ts
"
o
n
to
s
"
w
h
i
ch
m
ea
n
s
to
b
e
a
n
d
"
lo
g
o
s
"
w
h
ic
h
m
ea
n
s
s
c
ien
ce
.
T
h
u
s
,
"
On
to
lo
g
y
"
w
ith
a
ca
p
ital
O
m
ea
n
s
th
e
d
is
cip
li
n
e
o
f
m
etap
h
y
s
ics
w
h
ic
h
co
n
s
is
ts
o
f
“
s
t
u
d
y
o
f
b
ei
n
g
”
m
o
r
e
g
en
er
all
y
“
s
t
u
d
y
o
f
e
x
is
ten
t.”
T
h
e
ap
p
ea
r
an
ce
o
f
th
is
ter
m
in
t
h
e
f
ield
o
f
co
m
p
u
ti
n
g
d
ate
s
b
a
ck
to
th
e
1
9
7
0
s
w
ith
t
h
e
w
o
r
k
o
f
J
o
h
n
Mc
C
ar
th
y
i
n
th
e
f
ield
o
f
ar
ti
f
i
cial
in
tell
ig
e
n
ce
[
1
]
.
Du
r
in
g
t
h
e
1
9
9
0
s
,
it
w
a
s
tak
e
n
o
v
er
in
t
h
e
f
ie
ld
o
f
k
n
o
w
led
g
e
r
ep
r
esen
tatio
n
.
T
o
d
ay
,
th
e
n
o
tio
n
o
f
o
n
to
lo
g
y
h
as
a
g
r
o
w
in
g
i
n
ter
est
an
d
h
a
s
g
iv
e
n
b
ir
th
to
a
w
h
o
le
d
i
s
cip
l
in
e
“
o
n
to
lo
g
ical
e
n
g
i
n
ee
r
i
n
g
.”
I
n
f
ac
t,
o
n
to
lo
g
ies
ar
e
n
o
w
at
t
h
e
co
r
e
o
f
i
n
f
o
r
m
atio
n
r
etr
iev
a
l
o
r
d
ec
is
io
n
s
u
p
p
o
r
t
s
y
s
te
m
s
in
m
an
y
f
ield
s
s
u
c
h
a
s
h
ea
lt
h
[
2
]
,
leg
al
[
3
]
,
an
d
lear
n
in
g
[
4
].
Sin
ce
t
h
en
,
t
h
e
d
ef
i
n
itio
n
s
o
f
an
o
n
to
lo
g
y
in
co
m
p
u
ter
s
cie
n
ce
h
a
v
e
m
u
ltip
lied
.
T
h
e
m
o
s
t
f
a
m
o
u
s
i
s
Gr
u
b
er
'
s
d
e
f
i
n
itio
n
th
at
d
e
f
i
n
es
a
n
o
n
to
lo
g
y
as
th
e
"
ex
p
licit
s
p
ec
i
f
icatio
n
o
f
co
n
c
ep
tu
aliza
tio
n
"
[
5
].
T
h
en
,
Stu
d
er
et
al.
h
a
v
e
i
m
p
r
o
v
ed
th
is
d
e
f
in
itio
n
b
y
s
ta
tin
g
t
h
at
a
n
o
n
to
lo
g
y
i
s
a
"
f
o
r
m
al
an
d
e
x
p
licit
s
p
ec
if
icatio
n
o
f
a
s
h
ar
ed
co
n
ce
p
tu
aliza
tio
n
"
[
6
]
.
T
h
is
d
ef
i
n
itio
n
p
u
ts
f
o
r
w
ar
d
f
o
u
r
f
u
n
d
a
m
en
tal
n
o
tio
n
s
o
f
o
n
to
lo
g
y
,
n
a
m
e
l
y
:
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t
J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
10
,
No
.
4
,
A
u
g
u
s
t
2020
:
3
7
4
3
-
375
0
3744
Fo
r
m
al
s
p
ec
i
f
icatio
n
:
e
x
p
r
ess
ed
in
lo
g
ical
f
o
r
m
,
r
ea
d
ab
le
a
n
d
u
n
d
er
s
ta
n
d
ab
le
b
y
m
ac
h
in
es,
th
u
s
f
av
o
r
in
g
u
n
a
m
b
i
g
u
o
u
s
i
n
ter
p
r
etatio
n
s
,
w
h
ic
h
ex
cl
u
d
es t
h
e
u
s
e
o
f
n
a
t
u
r
al
lan
g
u
ag
e.
E
x
p
licit sp
ec
i
f
icatio
n
: e
x
p
licit
l
y
d
ef
i
n
es t
h
e
co
n
ce
p
ts
a
n
d
ax
io
m
s
t
h
at
b
in
d
t
h
e
m
.
C
o
n
ce
p
tu
a
lizatio
n
:
ab
s
tr
ac
t
an
d
s
i
m
p
li
f
ied
r
ep
r
esen
tatio
n
o
f
th
e
s
t
u
d
ied
d
o
m
ai
n
.
A
cc
o
r
d
in
g
to
L
ee
et
al.
,
a
co
n
ce
p
tu
al
izatio
n
is
"
an
e
x
t
r
ac
tio
n
o
f
a
d
o
m
ai
n
v
o
ca
b
u
la
r
y
a
n
d
is
an
ab
s
tr
ac
t
a
n
d
s
i
m
p
lif
ied
v
ie
w
o
f
th
e
d
o
m
a
i
n
th
at
w
e
w
i
s
h
to
r
ep
r
esen
t"
[
7
].
Sh
ar
ed
:
it
d
escr
ib
es
co
n
s
e
n
s
u
al
k
n
o
w
led
g
e.
I
n
f
ac
t,
o
n
to
l
o
g
y
d
o
es
n
o
t
r
ep
r
esen
t
t
h
e
v
ie
w
p
o
in
t
o
f
a
n
in
d
iv
id
u
a
l,
b
u
t
i
t
s
er
v
es
as
a
g
en
er
al
co
n
s
e
n
s
u
s
,
ac
ce
p
ted
an
d
s
h
ar
ed
b
et
w
ee
n
t
h
e
in
d
i
v
id
u
al
s
o
f
a
w
h
o
le
co
m
m
u
n
it
y
.
I
n
ad
d
itio
n
,
w
e
ar
e
cu
r
r
en
tl
y
w
it
n
ess
in
g
th
e
t
h
ir
d
in
d
u
s
tr
ial
r
ev
o
lu
tio
n
:
th
e
d
ig
i
tal
r
ev
o
lu
tio
n
.
T
h
e
ch
an
g
es
b
r
o
u
g
h
t
b
y
th
i
s
r
ev
o
lu
tio
n
ar
e
r
ap
id
l
y
a
n
d
r
ad
icall
y
tr
a
n
s
f
o
r
m
i
n
g
th
e
m
o
d
er
n
er
a.
T
h
e
f
ield
o
f
d
ata
an
al
y
s
is
d
o
es
n
o
t
esca
p
e
th
e
ex
p
lo
s
iv
e
r
is
e
o
f
th
is
r
ev
o
lu
t
io
n
.
T
h
is
is
d
u
e,
o
n
th
e
o
n
e
h
a
n
d
,
to
th
e
tech
n
o
lo
g
ica
l
ev
o
l
u
tio
n
ac
co
m
p
li
s
h
ed
i
n
t
h
e
f
ield
o
f
co
m
p
u
ter
s
,
o
n
t
h
e
o
th
er
h
an
d
,
to
th
e
p
r
o
g
r
ess
m
ad
e
at
t
h
e
le
v
el
o
f
in
f
o
r
m
atio
n
p
r
o
ce
s
s
in
g
m
o
d
els
s
u
ch
a
s
b
u
s
i
n
ess
in
telli
g
en
ce
[8
]
,
th
e
ar
tif
icia
l
in
telli
g
e
n
ce
[9
]
,
an
d
b
ig
d
ata
[
1
0
]
.
Ho
w
e
v
er
,
m
u
ch
o
f
o
p
er
atio
n
a
l
in
f
o
r
m
atio
n
s
y
s
te
m
d
ata
in
o
r
g
an
izatio
n
s
r
e
m
ai
n
s
u
n
s
tr
u
c
tu
r
ed
an
d
n
o
n
-
tr
an
s
ac
tio
n
a
l.
I
n
d
ee
d
,
ac
co
r
d
in
g
to
T
s
en
g
&
C
h
o
u
[
11
]
,
2
0
%
o
f
an
o
r
g
a
n
izatio
n
'
s
d
a
ta
is
tr
an
s
ac
tio
n
al,
w
h
ile
t
h
e
r
est
o
f
th
e
d
ata
is
n
o
n
-
tr
an
s
ac
tio
n
a
l
an
d
o
f
te
n
s
av
ed
in
tex
tu
al
d
o
cu
m
e
n
ts
u
n
d
er
an
u
n
s
tr
u
ct
u
r
ed
f
o
r
m
.
As
a
r
es
u
lt,
th
e
y
r
e
m
ain
u
n
u
s
ab
le
in
an
ap
p
r
o
p
r
ia
te
an
d
e
f
f
ec
tiv
e
w
a
y
i
n
t
h
e
er
a
o
f
i
n
f
o
r
m
atio
n
ca
p
italizatio
n
.
T
h
u
s
,
a
p
h
as
e
o
f
v
alo
r
izatio
n
o
f
th
i
s
d
ata
co
n
s
is
t
s
o
f
ex
tr
ac
ti
n
g
a
k
n
o
w
led
g
e
b
ase
in
th
e
o
n
to
lo
g
ical
f
o
r
m
.
T
h
e
m
a
n
u
al
p
r
o
ce
s
s
o
f
b
u
ild
in
g
s
u
ch
a
b
ase
i
s
lab
o
r
io
u
s
,
ted
io
u
s
a
n
d
ti
m
e
-
co
n
s
u
m
i
n
g
.
I
n
o
r
d
er
to
s
u
p
p
o
r
t
th
is
co
n
s
t
r
u
ctio
n
,
s
e
v
er
al
r
esear
ch
p
r
o
j
ec
ts
h
a
v
e
b
ee
n
ca
r
r
ied
o
u
t
to
au
to
m
ate
th
e
ta
s
k
s
in
v
o
l
v
ed
.
T
h
is
au
to
m
atio
n
i
s
d
esig
n
a
ted
as
'On
to
lo
g
y
L
e
ar
n
in
g
,
'
w
h
ich
r
e
f
er
s
to
all
t
h
e
tech
n
iq
u
es
an
d
m
et
h
o
d
s
w
h
o
s
e
o
b
j
ec
tiv
e
is
t
h
e
a
u
to
m
atic
o
r
s
e
m
i
-
a
u
to
m
a
tic
co
n
s
tr
u
ctio
n
o
f
o
n
to
lo
g
ie
s
v
ia
t
h
e
e
x
tr
ac
tio
n
,
th
e
ac
q
u
i
s
itio
n
,
a
n
d
th
e
g
en
er
a
tio
n
f
r
o
m
s
tr
u
ct
u
r
ed
,
s
e
m
i
-
s
tr
u
ctu
r
ed
,
o
r
u
n
s
tr
u
ctu
r
ed
r
eso
u
r
c
es.
T
o
o
ls
to
p
er
f
o
r
m
t
h
i
s
e
x
tr
ac
ti
o
n
ar
e
n
u
m
er
o
u
s
.
T
ex
t2
o
n
to
s
tan
d
s
o
u
t
as
t
h
e
o
n
e
o
f
t
h
e
b
est
to
o
ls
kno
w
n
i
n
t
h
i
s
f
ield
.
I
t
h
a
s
s
e
r
v
ed
as
a
s
u
b
j
ec
t
o
f
n
u
m
er
o
u
s
s
t
u
d
ies
o
f
co
m
p
ar
ati
v
e
e
v
al
u
atio
n
o
f
o
n
to
lo
g
y
lear
n
in
g
to
o
ls
in
w
h
ich
it
h
as
ex
ce
lled
s
u
c
h
as
[
1
2
,
1
3
]
.
T
h
e
o
r
ig
in
al
v
er
s
i
o
n
o
f
T
ex
t2
On
to
is
in
te
n
d
ed
f
o
r
th
e
p
r
o
ce
s
s
i
n
g
o
f
t
h
e
co
r
p
u
s
w
r
itte
n
i
n
E
n
g
li
s
h
a
n
d
is
b
ase
d
o
n
th
e
P
r
in
ce
to
n
W
o
r
d
Net
(
P
W
N)
f
o
r
E
n
g
lis
h
i
n
o
r
d
er
t
o
p
er
f
o
r
m
s
o
m
e
li
n
g
u
i
s
tic
s
u
b
-
p
r
o
ce
s
s
es
s
u
c
h
as
t
h
e
i
m
p
le
m
e
n
tatio
n
o
f
a
v
ar
ia
n
t
o
f
th
e
alg
o
r
it
h
m
s
in
te
n
d
ed
f
o
r
t
h
e
d
is
co
v
er
y
o
f
Su
b
clas
s
o
f
r
elatio
n
s
h
ip
s
.
He
n
ce
,
th
i
s
to
o
l
i
s
li
m
ited
to
t
h
e
p
r
o
ce
s
s
in
g
o
f
te
x
t
u
al
r
eso
u
r
ce
s
w
r
itte
n
i
n
E
n
g
lis
h
.
T
o
o
v
er
co
m
e
t
h
is
p
r
o
b
lem
,
w
e
p
r
ese
n
t
i
n
th
i
s
p
a
p
er
o
u
r
ap
p
r
o
ac
h
f
o
r
th
e
c
u
s
to
m
izatio
n
a
n
d
ad
ap
tatio
n
o
f
t
h
e
E
n
g
lis
h
la
n
g
u
a
g
e
v
er
s
io
n
o
f
t
h
e
o
p
en
-
s
o
u
r
ce
T
ex
t2
On
to
to
o
l
to
s
u
p
p
o
r
t th
e
ex
tr
ac
tio
n
o
f
o
n
to
l
o
g
ies
f
r
o
m
Fre
n
c
h
d
o
cu
m
en
t
s
.
2.
O
NT
O
L
O
G
Y
L
E
ARN
I
N
G
On
to
lo
g
y
n
o
tio
n
i
s
at
t
h
e
h
ea
r
t
o
f
th
e
s
e
m
an
t
ic
w
eb
d
o
m
a
in
.
W
e
n
o
te
a
p
r
o
lif
er
atio
n
o
f
r
esear
c
h
ad
d
r
ess
in
g
th
e
n
o
tio
n
o
f
o
n
to
lo
g
y
a
s
ill
u
s
tr
ated
i
n
Fi
g
u
r
e
1
th
at
g
i
v
e
s
an
o
v
er
v
ie
w
o
f
s
tatis
t
ics
r
elate
d
to
ar
ticles
in
d
e
x
ed
in
“Sco
p
u
s
.
c
o
m
”
co
n
tai
n
i
n
g
t
h
e
ter
m
'
o
n
t
o
lo
g
y
.
'
T
h
ese
w
o
r
k
s
co
v
er
o
n
e
o
r
m
o
r
e
p
h
ase
s
o
f
th
e
m
a
n
a
g
e
m
en
t
o
f
an
o
n
to
lo
g
y
,
s
u
c
h
as
t
h
e
co
n
s
tr
u
ctio
n
o
f
an
o
n
to
lo
g
y
,
it
s
s
to
r
ag
e,
a
n
d
its
ex
p
lo
itat
io
n
.
T
h
e
co
n
s
tr
u
ctio
n
o
f
an
o
n
to
lo
g
y
ca
n
b
e
clas
s
if
ied
in
to
t
w
o
f
a
m
ilie
s
:
m
an
u
al
co
n
s
tr
u
ctio
n
an
d
s
e
m
i
-
a
u
to
m
a
tic/a
u
to
m
at
ic
co
n
s
tr
u
ctio
n
.
T
h
e
m
a
n
u
a
l
co
n
s
tr
u
ctio
n
o
f
a
n
o
n
to
lo
g
y
is
c
h
ar
ac
ter
ized
b
y
it
s
r
eliab
ilit
y
.
Ne
v
er
th
ele
s
s
,
it is
v
er
y
ted
io
u
s
,
v
er
y
ex
p
e
n
s
i
v
e
an
d
r
eq
u
ir
es
m
o
r
e
ti
m
e.
On
t
h
e
o
t
h
er
h
a
n
d
,
th
e
s
ec
o
n
d
f
a
m
il
y
,
r
e
f
er
r
ed
as
'On
to
l
o
g
y
L
ea
r
n
in
g
,
'
r
ef
er
s
to
all
a
p
p
r
o
ac
h
es
w
h
o
s
e
o
b
j
ec
tiv
e
i
s
t
h
e
s
e
m
i
-
au
to
m
at
ic
co
n
s
tr
u
ct
io
n
o
f
o
n
to
lo
g
ies
v
ia
th
e
ex
tr
ac
tio
n
,
t
h
e
g
en
er
atio
n
a
n
d
th
e
ac
q
u
is
itio
n
.
A
s
p
ar
t
o
f
On
to
lo
g
y
L
ea
r
n
i
n
g
,
s
e
v
er
al
ap
p
r
o
ac
h
es
h
av
e
e
m
er
g
ed
to
p
r
o
m
o
te
th
e
ac
co
m
p
an
i
m
e
n
t
a
n
d
f
ac
ilit
atio
n
o
f
th
i
s
p
ain
f
u
l
co
n
s
tr
u
cti
o
n
.
Am
o
n
g
th
e
s
e
ap
p
r
o
ac
h
es
w
e
d
is
ti
n
g
u
is
h
th
a
t
o
f
o
n
to
lo
g
y
b
u
ild
i
n
g
f
r
o
m
t
ex
tu
a
l
d
o
cu
m
e
n
t
s
,
d
ictio
n
ar
i
es,
k
n
o
w
led
g
e
b
ases
,
s
e
m
i
-
s
tr
u
ctu
r
ed
d
ata
an
d
r
elatio
n
al
d
atab
ases
.
So
,
th
e
s
e
ap
p
r
o
ac
h
es a
r
e
v
ar
ian
t p
r
i
m
ar
i
l
y
ac
co
r
d
in
g
to
t
h
e
d
ata
s
o
u
r
ce
s
co
n
s
id
er
ed
.
Sev
er
al
m
e
th
o
d
o
lo
g
ies
h
av
e
em
er
g
ed
f
r
o
m
t
h
e
p
er
s
p
ec
tiv
e
o
f
d
ef
i
n
i
n
g
a
r
o
ad
m
ap
f
o
r
s
u
ch
a
co
n
s
tr
u
ct
io
n
,
a
m
o
n
g
th
e
b
es
t
-
k
n
o
w
n
ar
e
Me
th
o
n
to
lo
g
y
[
1
4
]
,
On
-
To
-
Kn
o
w
led
g
e
[
1
5
]
,
DI
L
I
GE
NT
[
1
6
]
an
d
NeO
n
[
1
7
]
.
T
h
e
co
n
s
tr
u
ctio
n
o
f
an
o
n
to
lo
g
y
b
r
in
g
s
to
g
et
h
e
r
a
co
n
s
id
er
ab
le
s
e
t
o
f
tas
k
s
.
T
h
e
au
to
m
at
io
n
o
f
th
is
co
n
s
tr
u
ctio
n
a
m
o
u
n
ts
to
au
to
m
ati
n
g
tas
k
s
o
r
s
o
m
e
o
f
th
ese
ta
s
k
s
.
T
h
e
ap
p
r
o
ac
h
es
f
o
r
o
n
to
lo
g
y
co
n
s
tr
u
ct
io
n
f
r
o
m
tex
tu
al
d
o
cu
m
e
n
t
s
ar
e
g
r
o
u
p
ed
in
to
s
ev
er
al
ca
te
g
o
r
ies.
Am
o
n
g
o
t
h
er
s
,
w
e
m
e
n
tio
n
ap
p
r
o
ac
h
es b
ased
o
n
lin
g
u
is
t
ic
tech
n
iq
u
es,
o
n
s
tatis
tical
tech
n
iq
u
e
s
an
d
th
o
s
e
b
ased
o
n
lear
n
in
g
co
n
ce
p
t.
I
n
t
h
is
co
n
te
x
t,
o
n
e
o
f
th
e
m
o
s
t
p
o
p
u
lar
to
o
ls
o
f
o
n
to
lo
g
y
l
ea
r
n
in
g
i
s
T
ex
t2
O
n
to
[
1
8
]
.
T
h
is
to
o
l
h
a
s
s
er
v
ed
as
s
ev
er
al
r
esear
ch
w
o
r
k
s
.
I
n
f
ac
t,
o
n
Go
o
g
le
Sc
h
o
lar
,
th
e
s
ea
r
c
h
o
f
th
e
ter
m
'
T
ex
t2
o
n
to
'
g
iv
e
s
r
es
u
l
t
in
cl
u
d
in
g
9
8
8
p
ag
es
d
is
p
la
y
i
n
g
1
0
ele
m
en
t
s
,
tak
in
g
i
n
to
co
n
s
id
er
atio
n
t
h
at
w
e
h
av
e
e
x
clu
d
ed
p
aten
ts
a
n
d
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8708
A
n
a
d
a
p
ta
tio
n
o
f Tex
t2
On
to
fo
r
s
u
p
p
o
r
tin
g
th
e
F
r
en
ch
la
n
g
u
a
g
e
(
Mo
r
a
d
Ha
jji
)
3745
citatio
n
s
.
T
h
i
s
g
iv
e
s
a
r
es
u
lt
o
f
9
8
8
*
1
0
=
9
8
8
0
(
s
ea
r
ch
d
ate
0
5
/1
2
/2
0
1
8
)
w
h
er
e
t
h
e
ter
m
'T
ex
t2
o
n
to
'
ap
p
ea
r
s
.
I
n
ad
d
itio
n
,
th
e
Sco
p
u
s
i
n
d
ex
i
n
g
d
atab
ase
li
s
ts
3
9
7
d
o
cu
m
en
ts
co
n
tai
n
i
n
g
t
h
e
ter
m
T
ex
t2
O
n
to
.
Mo
r
eo
v
er
,
o
u
r
ch
o
ice
o
f
th
e
T
ex
t2
On
to
to
o
l
is
j
u
s
ti
f
ied
b
y
its
p
er
f
o
r
m
a
n
ce
co
n
f
ir
m
ed
b
y
s
ev
er
a
l
r
esear
ch
w
o
r
k
s
,
s
u
ch
as
T
o
ad
er
Gh
er
asi
m
[
1
2
]
w
o
r
k
w
h
o
m
ad
e
a
co
m
p
ar
ati
v
e
s
tu
d
y
o
f
th
is
to
o
l
w
it
h
t
h
r
ee
o
th
er
to
o
ls
(
On
to
L
ea
r
n
,
a
s
iu
m
an
d
s
p
r
at)
an
d
J
in
s
o
o
P
ar
k
a
n
d
al.
[
1
3
]
w
o
r
k
w
h
o
p
er
f
o
r
m
ed
a
co
m
p
ar
is
o
n
o
f
th
e
s
a
m
e
to
o
l
w
ith
t
h
r
ee
o
th
er
to
o
ls
(
DOD
DL
E
-
OW
L
,
On
to
B
u
ild
er
an
d
On
to
L
T
)
.
T
ex
t2
On
to
to
o
l
p
r
o
v
id
es
to
th
e
d
esi
g
n
er
,
s
ev
er
al
a
lg
o
r
it
h
m
s
d
ed
icate
d
to
t
h
e
d
if
f
er
en
t
task
s
o
f
o
n
to
lo
g
y
g
en
er
a
tio
n
[
1
8
]
.
T
h
e
o
n
to
lo
g
y
d
esig
n
er
ch
o
o
s
es
a
m
o
n
g
th
e
s
e
alg
o
r
ith
m
s
t
h
o
s
e
to
u
s
e
f
o
r
ea
ch
tas
k
o
f
t
h
is
g
en
er
atio
n
.
T
h
e
in
ter
v
en
tio
n
o
f
th
e
d
esi
g
n
er
allo
w
s
th
e
p
ar
a
m
eter
izatio
n
o
f
th
e
to
o
l
in
ad
d
itio
n
to
t
h
e
r
ef
i
n
e
m
e
n
t
an
d
v
alid
atio
n
o
f
th
e
in
ter
m
ed
iate
r
es
u
lt
f
o
r
th
e
g
en
er
atio
n
o
f
t
h
e
f
i
n
al
o
n
to
lo
g
y
.
T
h
e
o
p
er
atio
n
o
f
ex
tr
ac
ti
n
g
a
n
o
n
to
lo
g
y
f
r
o
m
th
e
t
ex
t
i
s
b
ased
o
n
a
n
al
y
s
i
s
p
r
im
iti
v
es.
T
h
ese
p
r
i
m
iti
v
es
b
elo
n
g
to
t
h
e
n
at
u
r
al
la
n
g
u
a
g
e
p
r
o
ce
s
s
in
g
an
d
ca
n
b
e
o
r
g
a
n
ized
in
a
p
y
r
a
m
id
al
m
o
d
el
in
th
e
f
o
r
m
o
f
a
'
C
a
k
e
'
as
ill
u
s
tr
at
ed
in
Fi
g
u
r
e
2
.
T
h
e
ad
ap
tatio
n
o
f
T
ex
t2
On
to
to
o
l f
o
r
t
h
e
Fre
n
ch
lan
g
u
ag
e
g
o
es,
f
ir
s
t o
f
all,
b
y
th
e
ad
ap
tatio
n
o
f
th
e
s
e
p
r
i
m
it
iv
e
s
.
Fig
u
r
e
1
.
On
to
lo
g
y
ter
m
p
r
o
life
r
atio
n
Fig
u
r
e
2
.
On
to
lo
g
y
lear
n
i
n
g
la
y
er
ca
k
e
[
1
9
]
3.
T
E
X
T
2
O
NT
O
T
ex
t2
On
to
[
1
8
]
is
a
f
r
am
e
w
o
r
k
f
o
r
lear
n
in
g
o
n
to
lo
g
ie
s
f
r
o
m
tex
tu
al
d
ata
ac
co
r
d
in
g
to
a
tr
an
s
p
ar
en
t
p
r
o
ce
s
s
.
T
h
is
to
o
l
h
as
s
e
v
er
al
alg
o
r
ith
m
s
g
r
o
u
p
ed
in
to
s
e
v
en
s
ets
s
u
c
h
a
s
"
C
o
n
ce
p
t,"
"
I
n
s
tan
ce
,
"
"
Sim
i
lar
it
y
,
"
"
Su
b
class
O
f
,
"
"
I
n
s
tan
ce
O
f
,
"
"Relatio
n
,
"
an
d
"
Su
b
to
p
icOf
.
"
Am
o
n
g
t
h
e
al
g
o
r
ith
m
s
o
f
th
e
g
r
o
u
p
"
Su
b
class
O
f
"
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t
J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
10
,
No
.
4
,
A
u
g
u
s
t
2020
:
3
7
4
3
-
375
0
3746
is
th
e
alg
o
r
it
h
m
W
o
r
d
NetCo
n
ce
p
tC
lass
if
ica
tio
n
th
a
t
is
b
ased
o
n
th
e
r
elatio
n
s
h
ip
o
f
th
e
s
tr
u
ctu
r
e
o
f
h
y
p
er
n
y
m
t
y
p
e
in
W
o
r
d
Net.
T
h
e
d
esig
n
er
s
o
f
t
h
i
s
to
o
l
im
p
le
m
e
n
ted
t
h
is
al
g
o
r
ith
m
i
n
o
r
d
er
to
lear
n
s
u
b
class
-
o
f
r
elatio
n
s
b
y
ex
p
lo
itin
g
t
h
e
h
y
p
er
n
y
m
r
elat
io
n
s
h
ip
in
W
o
r
d
Net.
Ho
w
e
v
e
r
,
W
o
r
d
Net
is
an
elec
tr
o
n
ic
l
ex
ical
d
ata
b
ase
f
o
r
E
n
g
l
is
h
.
T
h
is
co
n
s
ti
tu
te
s
a
li
m
itatio
n
f
o
r
d
ea
lin
g
w
it
h
o
th
e
r
lan
g
u
ag
e
s
w
it
h
t
h
is
to
o
l,
es
p
ec
iall
y
f
o
r
lear
n
i
n
g
s
u
b
clas
s
-
o
f
r
elatio
n
s
r
elate
d
to
Fre
n
ch
.
I
n
f
ac
t,
P
.
C
i
m
ian
o
a
n
d
V.
J
o
h
an
n
a
h
av
e
d
ev
e
lo
p
ed
T
ex
t2
On
to
to
o
v
er
co
m
e
t
h
e
o
th
er
to
o
ls
li
m
ita
tio
n
s
s
u
ch
a
s
T
ex
tT
o
On
to
[
2
0
]
,
A
SIU
M
[
2
1
]
,
Mo
'
k
W
o
r
k
b
en
ch
[
2
2
]
,
On
to
L
ea
r
n
[
2
3
]
o
r
On
n
ea
r
L
T
[
2
4
]
.
Am
o
n
g
t
h
ese
li
m
itatio
n
s
is
th
e
d
ep
en
d
en
c
y
o
f
a
s
p
ec
i
f
ic
o
r
p
r
o
p
r
ietar
y
o
n
to
lo
g
ical
m
o
d
el
,
th
e
n
e
g
lect
o
f
t
h
e
in
ter
ac
tio
n
w
it
h
th
e
e
n
d
u
s
er
a
n
d
t
h
e
lac
k
o
f
co
n
s
id
er
atio
n
o
f
c
h
a
n
g
e
s
in
t
h
e
d
ata
s
o
u
r
ce
.
T
o
o
v
er
co
m
e
th
e
f
ir
s
t
li
m
i
tati
o
n
,
P
.
C
i
m
ian
o
a
n
d
V.
J
o
h
an
n
a
r
elied
o
n
a
l
ev
e
l
o
f
ab
s
tr
ac
tio
n
g
o
v
er
n
ed
b
y
th
e
r
ep
r
esen
tat
io
n
o
f
an
o
n
to
lo
g
ical
s
tr
u
ct
u
r
e
b
y
a
m
eta
-
m
o
d
el
b
ased
o
n
m
o
d
eli
n
g
p
r
i
m
iti
v
es.
T
h
is
g
i
v
e
s
th
e
ir
m
o
d
el
t
h
e
ab
ilit
y
to
tr
an
s
la
te
t
h
e
lear
n
ed
o
n
to
lo
g
y
i
n
to
R
DF
S,
OW
L
o
r
F
-
L
o
g
ic.
T
o
o
v
er
co
m
e
th
e
s
ec
o
n
d
li
m
i
tatio
n
,
th
e
a
u
th
o
r
s
ad
o
p
ted
a
p
r
o
b
a
b
ilis
tic
o
n
to
lo
g
y
m
o
d
el
(
P
OM
)
b
y
p
r
esen
tin
g
t
h
e
r
esu
lts
to
th
e
en
d
u
s
er
w
it
h
p
r
o
b
ab
ilit
ies
o
f
co
n
f
id
en
ce
.
Fro
m
t
h
e
m
o
m
en
t
th
e
r
es
u
lt
s
ar
e
o
r
d
er
e
d
b
y
ce
r
tain
t
y
w
it
h
th
e
p
o
s
s
ib
ilit
y
o
f
li
m
iti
n
g
t
h
e
m
to
t
h
o
s
e
ex
ce
ed
in
g
a
co
n
f
id
en
ce
t
h
r
esh
o
ld
,
th
e
in
ter
ac
tio
n
w
ith
t
h
e
en
d
u
s
er
is
m
ad
e
ef
f
ec
tiv
e.
T
o
o
v
e
r
co
m
e
t
h
e
th
ir
d
li
m
i
tatio
n
,
th
e
d
ev
elo
p
er
s
o
f
th
is
to
o
l
h
av
e
d
ev
elo
p
ed
i
t
b
y
e
x
p
lo
itin
g
t
h
e
Data
-
Dr
i
v
en
d
esi
g
n
p
atter
n
.
T
h
at
g
r
an
ts
t
h
e
to
o
l
th
e
ab
ilit
y
to
h
an
d
l
e
ch
an
g
es
i
n
a
co
r
p
u
s
ad
eq
u
atel
y
.
As
a
r
esu
lt,
co
r
p
u
s
ch
a
n
g
es
ar
e
d
etec
ted
an
d
P
OM
ch
a
n
g
e
s
ar
e
ca
lcu
lated
b
ased
o
n
th
ese
ch
a
n
g
es
w
i
th
o
u
t
m
a
k
i
n
g
a
r
ec
alcu
latio
n
o
f
t
h
e
P
OM
f
o
r
th
e
w
h
o
le
co
r
p
u
s
.
3
.
1
.
L
ing
uis
t
ic
prepro
ce
s
s
i
n
g
T
o
ex
tr
ac
t
o
n
to
lo
g
ies
f
r
o
m
a
co
r
p
u
s
,
T
ex
t2
On
to
'
s
au
t
h
o
r
s
h
av
e
r
elied
o
n
th
e
co
m
b
in
atio
n
o
f
th
e
m
ac
h
i
n
e
lear
n
in
g
an
d
n
atu
r
al
lan
g
u
a
g
e
p
r
o
ce
s
s
in
g
tec
h
n
i
q
u
es.
I
n
d
ee
d
,
T
ex
t2
On
to
is
b
ased
o
n
th
e
g
en
er
a
l
ar
ch
itect
u
r
e
f
o
r
tex
t
en
g
i
n
ee
r
i
n
g
f
r
a
m
e
w
o
r
k
(
G
A
T
E
)
,
w
h
ich
g
i
v
es
t
h
is
to
o
l
a
ce
r
tain
f
le
x
ib
ilit
y
f
o
r
ad
ap
tatio
n
an
d
cu
s
to
m
izatio
n
.
P
r
ep
r
o
ce
s
s
in
g
b
e
g
in
s
w
i
th
t
h
e
p
r
eli
m
i
n
ar
y
s
ta
g
es
o
f
t
h
e
L
i
n
g
u
is
tic
P
r
ep
r
o
ce
s
s
in
g
i
n
T
ex
t2
On
to
,
n
a
m
el
y
to
k
e
n
izati
o
n
an
d
s
en
te
n
ce
s
p
litt
i
n
g
.
T
h
e
n
,
t
h
e
r
es
u
lt
o
f
t
h
is
s
tep
is
u
s
e
d
b
y
a
tag
g
er
P
OS
b
y
a
s
s
i
g
n
in
g
ea
c
h
to
k
e
n
its
s
y
n
tactic
ca
te
g
o
r
y
.
A
f
ter
,
th
e
p
h
ase
o
f
th
i
s
p
r
etr
ea
t
m
e
n
t
is
co
m
p
le
te
d
b
y
a
m
o
r
p
h
o
lo
g
ical
an
al
y
ze
r
a
n
d
a
s
te
m
m
er
t
h
at
p
er
f
o
r
m
le
m
m
atiza
tio
n
o
r
s
te
m
m
i
n
g
.
So
,
b
a
s
ic
p
r
ep
r
o
ce
s
s
in
g
in
v
o
l
v
es t
h
e
f
o
llo
w
in
g
t
h
r
ee
s
t
ep
s
:
T
o
k
en
izatio
n
an
d
s
e
n
te
n
ce
s
s
p
litt
in
g
.
A
ttrib
u
tio
n
o
f
s
y
n
tac
tic
ca
teg
o
r
ies.
L
e
m
m
atiza
tio
n
o
r
s
te
m
m
i
n
g
.
T
h
e
af
o
r
e
m
en
tio
n
ed
s
tep
s
co
n
s
ti
tu
te
th
e
b
asic
p
r
etr
ea
t
m
e
n
t
af
ter
w
h
ic
h
t
h
e
a
n
n
o
tated
r
esu
lt
th
u
s
o
b
tain
ed
u
n
d
er
g
o
e
s
p
r
o
ce
s
s
i
n
g
b
y
a
J
a
v
a
An
n
o
tatio
n
P
atter
n
s
E
n
g
i
n
e
(
J
A
P
E
)
.
T
h
is
G
A
T
E
m
o
d
u
l
e
is
u
s
ed
f
o
r
s
u
r
f
ac
e
an
al
y
s
is
a
n
d
id
en
ti
f
icatio
n
o
f
m
o
d
eli
n
g
p
r
i
m
it
iv
e
s
.
3
.
2
.
Co
ncept
s
a
nd
ins
t
a
nces
I
n
th
e
co
n
te
x
t
o
f
o
n
to
lo
g
y
lear
n
in
g
,
th
e
e
x
tr
ac
tio
n
o
f
t
er
m
s
t
h
a
t
ca
n
r
ep
r
esen
t
co
n
ce
p
ts
an
d
r
elatio
n
s
h
ip
s
is
b
ased
o
n
t
w
o
t
y
p
e
s
o
f
ap
p
r
o
ac
h
es:
s
tatis
t
ical
ap
p
r
o
ac
h
es
an
d
lin
g
u
is
tic
ap
p
r
o
ac
h
es.
L
in
g
u
is
ti
c
ap
p
r
o
ac
h
es
ar
e
b
ased
o
n
th
e
a
n
al
y
s
i
s
o
f
th
e
g
r
a
m
m
a
tical
s
tr
u
ctu
r
e
o
f
t
h
e
s
en
te
n
ce
s
t
h
at
m
ak
e
u
p
th
e
tex
t
an
d
o
n
t
h
e
id
en
ti
f
icat
io
n
o
f
t
h
e
s
y
n
tactic
(
s
u
b
j
ec
t,
d
ir
ec
t o
b
j
ec
t,
etc.
)
an
d
m
o
r
p
h
o
-
s
y
n
tac
tic
(
n
o
u
n
,
v
er
b
,
ad
j
ec
tiv
e)
r
o
les
o
f
ea
ch
w
o
r
d
o
r
g
r
o
u
p
o
f
w
o
r
d
s
.
W
h
ile
s
ta
tis
t
ical
ap
p
r
o
ac
h
es
ar
e
b
ased
o
n
ca
lcu
la
ti
n
g
t
h
e
r
ele
v
an
ce
o
f
a
ter
m
in
a
co
r
p
u
s
.
I
n
t
h
is
co
n
t
ex
t,
T
ex
t2
On
to
d
ev
elo
p
er
s
h
a
v
e
i
m
p
le
m
e
n
ted
alg
o
r
it
h
m
s
to
ca
lcu
late:
R
elati
v
e
ter
m
f
r
eq
u
e
n
c
y
(
R
T
F
)
.
T
er
m
f
r
eq
u
e
n
c
y
i
n
v
er
ted
d
o
cu
m
en
t f
r
eq
u
e
n
c
y
(
T
FID
F).
E
n
tr
o
p
y
.
C
-
v
al
u
e/N
C
-
v
al
u
e.
T
h
ese
v
alu
e
s
ar
e
n
o
r
m
alize
d
f
o
r
ea
ch
ter
m
a
n
d
u
s
ed
as p
r
o
b
ab
ilit
y
at
t
h
e
lev
el
o
f
th
e
P
OM
.
3
.
3
.
Su
bcla
s
s
O
f
re
la
t
io
ns
hip
s
I
n
th
e
o
r
ig
in
al
v
er
s
io
n
o
f
T
ex
t2
o
n
to
,
th
e
d
e
v
elo
p
er
s
o
f
t
h
is
to
o
l
i
m
p
le
m
e
n
ted
th
r
ee
al
g
o
r
ith
m
s
to
ex
tr
ac
t
S
u
b
class
O
f
r
elatio
n
s
h
ip
s
.
I
n
d
ee
d
,
th
e
y
i
m
p
le
m
e
n
ted
th
e
p
atter
n
co
n
ce
p
t
cla
s
s
i
f
icatio
n
,
v
er
tical
r
elatio
n
s
c
o
n
ce
p
t
class
i
f
icat
io
n
an
d
w
o
r
d
n
et
co
n
ce
p
t
clas
s
if
ica
tio
n
al
g
o
r
ith
m
s
ac
co
r
d
in
g
to
th
e
ap
p
r
o
ac
h
p
r
o
p
o
s
ed
b
y
P
.
C
i
m
ian
o
e
t
al.
[
2
5
]
.
T
h
ese
al
g
o
r
ith
m
s
ar
e
u
s
ed
f
o
r
e
x
tr
ac
tin
g
S
u
b
class
O
f
r
elatio
n
s
h
ip
s
f
r
o
m
tex
t
w
r
itte
n
in
E
n
g
l
is
h
.
Fo
r
th
e
s
u
p
p
o
r
t
o
f
Fre
n
c
h
,
w
e
h
ad
to
im
p
le
m
e
n
t
v
ar
ia
n
ts
o
f
t
h
e
s
e
th
r
ee
alg
o
r
it
h
m
s
ad
ap
ted
to
th
e
s
p
ec
if
icatio
n
s
o
f
th
e
f
r
ee
w
o
r
d
n
et
f
o
r
Fre
n
c
h
(
W
OL
F)
an
d
th
e
p
ar
tic
u
lar
itie
s
o
f
Fre
n
c
h
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8708
A
n
a
d
a
p
ta
tio
n
o
f Tex
t2
On
to
fo
r
s
u
p
p
o
r
tin
g
th
e
F
r
en
ch
la
n
g
u
a
g
e
(
Mo
r
a
d
Ha
jji
)
3747
T
h
e
i
m
p
le
m
en
tat
io
n
o
f
t
h
e
p
at
ter
n
co
n
ce
p
t
c
lass
if
ica
tio
n
a
lg
o
r
ith
m
is
b
a
s
ed
o
n
t
h
e
tech
n
iq
u
es
o
r
m
et
h
o
d
s
o
f
th
e
n
a
tu
r
al
la
n
g
u
a
g
e
m
o
d
el
s
,
in
p
ar
ticu
lar
o
n
th
e
Hea
r
s
t
-
P
atter
n
s
,
ill
u
s
tr
ated
i
n
Fig
u
r
e
3
,
w
h
ich
i
s
b
ased
o
n
lex
ico
-
s
y
n
tac
tic
m
o
d
els b
a
s
ed
o
n
h
y
p
o
n
y
m
an
d
h
y
p
er
n
y
m
r
e
latio
n
s
h
ip
s
.
Fig
u
r
e
3
.
Hea
r
s
t p
atter
n
s
T
h
e
i
m
p
le
m
en
tat
io
n
o
f
t
h
e
V
er
ticalR
elatio
n
s
C
o
n
ce
p
tC
la
s
s
i
f
icatio
n
al
g
o
r
ith
m
i
s
b
ased
o
n
th
e
h
e
u
r
is
tic
o
f
"
v
er
tical
r
elatio
n
s
"
[
2
6
]
.
T
h
is
alg
o
r
ith
m
is
u
s
ed
f
o
r
co
m
p
o
s
it
e
n
o
u
n
p
h
r
ases
.
T
h
e
i
m
p
le
m
e
n
tatio
n
o
f
th
e
W
o
r
d
NetCo
n
ce
p
tC
las
s
if
icati
o
n
alg
o
r
it
h
m
is
b
ased
o
n
th
e
h
y
p
er
n
y
m
r
elatio
n
s
h
ip
s
f
r
o
m
P
r
in
ce
to
n
W
o
r
d
Net.
T
h
e
s
tan
d
ar
d
ized
f
r
eq
u
en
c
y
o
f
o
cc
u
r
r
en
ce
s
o
f
a
m
o
d
el
r
ep
r
esen
ts
t
h
e
ce
r
tain
t
y
o
f
a
r
e
latio
n
s
h
ip
,
in
o
t
h
er
w
o
r
d
s
,
th
e
p
r
o
b
ab
ilit
y
o
f
a
S
u
b
class
O
f
r
elatio
n
s
h
ip
.
3
.
4
.
I
ns
t
a
nce
o
f
re
la
t
io
ns
T
h
e
cr
ea
to
r
s
o
f
th
e
T
ex
t2
On
to
to
o
l
h
av
e
ad
o
p
ted
an
ap
p
r
o
ac
h
b
ased
o
n
th
e
n
o
tio
n
o
f
s
i
m
ilar
it
y
.
I
n
th
e
f
ir
s
t
p
lace
,
th
e
y
es
tab
lis
h
t
h
e
co
m
p
u
tatio
n
o
f
t
h
e
co
n
tex
t
u
al
v
ec
to
r
s
f
o
r
th
e
in
s
tan
ce
s
as
f
o
r
th
e
co
n
ce
p
ts
.
I
n
t
h
e
s
ec
o
n
d
p
lace
,
th
e
y
estab
li
s
h
th
e
co
m
p
u
ta
ti
o
n
o
f
t
h
e
s
i
m
ilar
it
y
b
et
w
ee
n
th
e
v
ec
to
r
s
o
f
th
e
in
s
ta
n
ce
s
an
d
t
h
o
s
e
o
f
t
h
e
co
n
ce
p
ts
b
y
u
s
i
n
g
t
h
e
d
iv
er
g
en
ce
o
f
S
k
e
w
ed
[
2
7
]
.
Fin
all
y
,
th
e
y
ass
i
g
n
in
s
ta
n
ce
s
t
o
th
e
co
n
ce
p
ts
w
i
th
t
h
e
g
r
ea
te
s
t
s
i
m
i
lar
it
y
a
s
in
[
2
3
].
4.
ADAP
T
I
NG
T
E
XT
2
O
N
T
O
F
O
R
T
H
E
SUPP
O
R
T
O
F
T
H
E
F
RE
NCH
L
AN
G
UA
G
E
I
n
o
r
d
er
to
ad
ap
t
th
e
s
o
u
r
ce
co
d
e
o
f
th
e
T
ex
t2
o
n
to
to
o
l,
th
eo
r
etica
l
c
h
alle
n
g
e
s
a
n
d
tech
n
ical
co
n
s
tr
ain
ts
m
u
s
t
b
e
tak
en
i
n
t
o
ac
co
u
n
t.
I
n
d
ee
d
,
ea
ch
lan
g
u
ag
e
i
s
ch
ar
ac
ter
ized
b
y
it
s
s
p
ec
if
ic
lex
ica
l
a
n
d
s
y
n
tactic
m
o
r
p
h
o
lo
g
ies.
W
e
b
eg
in
t
h
e
n
at
u
r
al
lan
g
u
a
g
e
p
r
o
ce
s
s
in
g
o
f
a
co
r
p
u
s
o
f
d
o
cu
m
e
n
t
s
in
Fre
n
c
h
lan
g
u
a
g
e
b
y
p
r
etr
ea
t
m
en
t
f
o
r
ele
m
e
n
tar
y
d
ec
o
m
p
o
s
itio
n
wh
o
s
e
p
u
r
p
o
s
e
is
th
e
ex
tr
ac
tio
n
o
f
th
e
ter
m
s
th
a
t
m
ak
e
u
p
th
e
s
en
te
n
ce
s
.
T
h
is
p
h
ase
co
n
s
id
er
s
th
at
a
s
en
ten
ce
co
n
s
i
s
ts
o
f
s
y
m
b
o
ls
w
h
o
s
e
u
n
io
n
r
ep
r
esen
ts
t
h
e
te
x
t
as
a
s
et
.
T
h
e
o
p
e
r
atio
n
o
f
th
is
s
p
litt
in
g
o
f
th
e
s
e
n
te
n
ce
s
o
f
t
h
e
te
x
t
in
to
s
y
m
b
o
l
s
is
r
ef
er
r
ed
b
y
t
h
e
to
k
e
n
izatio
n
.
Fo
r
th
is
,
w
e
h
a
v
e
ex
p
lo
ited
,
cu
s
to
m
ized
an
d
ad
ap
ted
th
e
p
r
o
ce
s
s
in
g
r
eso
u
r
ce
s
o
f
f
er
ed
b
y
GA
T
E
in
th
i
s
ar
ea
.
I
n
f
ac
t,
G
A
T
E
h
as
s
e
v
er
al
t
y
p
es
o
f
r
eso
u
r
ce
s
,
i
n
cl
u
d
in
g
p
r
o
ce
s
s
i
n
g
r
eso
u
r
ce
s
,
lan
g
u
ag
e
r
e
s
o
u
r
ce
s
,
an
d
v
is
u
al
r
eso
u
r
ce
s
.
I
n
o
r
d
er
to
r
ea
ch
th
is
p
h
ase,
w
e
h
av
e
u
s
ed
an
d
p
ar
am
eter
ized
t
h
e
d
ef
a
u
lt
to
k
en
i
s
er
,
th
e
d
e
f
au
lt
g
az
ettee
r
an
d
t
h
e
Se
n
te
n
ce
Sp
l
itter
r
eso
u
r
ce
s
f
r
o
m
t
h
e
co
llectio
n
o
f
r
eu
s
ab
le
o
b
j
ec
ts
f
o
r
lan
g
u
a
g
e
en
g
i
n
ee
r
in
g
p
lu
g
i
n
(
C
R
E
O
L
E
)
.
T
h
e
ad
a
p
tatio
n
o
f
th
e
C
R
E
O
L
E
to
o
ls
o
f
tr
ea
t
m
e
n
t
r
eq
u
ir
es
th
e
cu
s
to
m
izat
io
n
o
f
th
eir
p
ar
a
m
eter
s
.
I
n
d
ee
d
,
th
e
to
k
en
izatio
n
o
p
er
a
tio
n
r
ef
e
r
s
to
th
e
f
r
ag
m
e
n
tatio
n
o
f
th
e
tex
t
in
to
to
k
e
n
s
u
s
i
n
g
g
r
a
m
m
atica
l
r
u
le
s
.
T
h
ese
to
k
e
n
s
r
ep
r
ese
n
t
t
h
e
w
o
r
d
s
,
n
u
m
b
er
s
a
n
d
p
u
n
ct
u
atio
n
co
n
s
tit
u
ti
n
g
t
h
e
ele
m
e
n
tar
y
b
u
ild
in
g
b
lo
ck
s
w
it
h
w
h
ic
h
th
e
te
x
t
is
co
n
s
tr
u
cte
d
.
I
n
th
e
co
n
tex
t
o
f
th
i
s
p
ap
er
,
w
e
h
av
e
i
m
p
le
m
e
n
ted
an
d
u
s
ed
a
Fre
n
c
h
T
o
k
en
is
er
.
r
u
les
f
ile
lis
tin
g
t
h
e
g
r
a
m
m
atica
l
r
u
les
f
o
r
th
e
t
o
k
en
izatio
n
o
p
er
atio
n
o
f
tex
t
w
r
itte
n
in
Fre
n
c
h
.
T
h
ese
r
u
les
ar
e
co
m
p
o
s
ed
o
f
t
w
o
p
ar
ts
:
t
h
e
le
f
t
p
ar
t
co
n
s
is
ts
o
f
r
eg
u
lar
ex
p
r
es
s
io
n
s
o
f
c
o
r
r
e
s
p
o
n
d
en
ce
an
d
th
e
r
ig
h
t
p
ar
t
g
i
v
e
s
an
n
o
tatio
n
s
to
ass
i
g
n
.
T
h
e
g
az
ettee
r
is
u
s
ed
to
an
n
o
tate
t
h
e
p
r
o
p
er
n
a
m
e
s
o
f
co
u
n
tr
ies,
p
r
o
v
in
ce
s
,
citie
s
,
o
r
g
a
n
izatio
n
s
,
d
a
y
s
o
f
t
h
e
w
ee
k
,
etc.
b
ase
d
o
n
f
ile
s
co
n
tain
i
n
g
li
s
ts
o
f
t
h
ese
n
a
m
es.
I
n
t
h
i
s
ca
s
e,
th
e
f
ile
'
co
u
n
tr
y
.
ls
t
'
li
s
ts
th
e
n
a
m
es
o
f
t
h
e
co
u
n
tr
ies,
i
n
o
u
r
co
n
te
x
t,
w
r
itte
n
in
Fre
n
c
h
.
T
h
e
g
az
ettee
r
u
s
es
an
in
d
e
x
in
g
f
ile
'
li
s
ts
.
d
ef
'
to
ac
ce
s
s
all
t
h
e
f
i
les i
n
th
e
li
s
ts
.
I
n
o
r
d
er
t
o
s
eg
m
e
n
t
a
tex
t
i
n
to
s
en
te
n
ce
s
,
t
h
e
ex
p
lo
itati
o
n
o
f
th
e
s
p
litt
i
n
g
o
p
er
atio
n
b
ased
o
n
th
e
'Sen
ten
ce
Sp
litt
er
'
r
e
s
o
u
r
ce
o
f
f
er
ed
b
y
G
A
T
E
is
u
s
ed
.
T
h
is
r
eso
u
r
ce
co
n
s
is
ts
o
f
a
s
u
ite
o
f
f
in
ite
s
tate
tr
an
s
d
u
ce
r
s
.
T
h
is
p
r
o
ce
s
s
in
g
r
eso
u
r
ce
u
s
es
g
az
ettee
r
lis
ts
a
n
d
J
A
P
E
p
atter
n
s
d
ef
in
i
n
g
t
h
e
g
r
a
m
m
atica
l
r
u
le
s
f
o
r
s
en
ten
ce
m
o
r
p
h
o
lo
g
ie
s
t
h
a
t
w
e
h
a
v
e
e
s
tab
lis
h
ed
f
o
r
s
o
u
r
ce
s
w
r
i
tte
n
i
n
Fre
n
ch
.
G
A
T
E
p
r
o
v
id
es
a
s
y
n
ta
x
-
b
ased
tag
g
er
(
P
OST
ag
g
er
:
P
ar
t
-
Of
-
Sp
ee
ch
T
ag
g
er
)
f
o
r
id
en
ti
f
y
in
g
,
i
n
d
ep
en
d
en
tl
y
o
f
t
h
e
la
n
g
u
a
g
e,
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t
J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
10
,
No
.
4
,
A
u
g
u
s
t
2020
:
3
7
4
3
-
375
0
3748
th
e
s
y
n
tactic
ca
te
g
o
r
y
as
w
ell
as
th
e
le
m
m
a
o
f
a
g
iv
e
n
to
k
en
.
A
s
p
ar
t
o
f
G
A
T
E
,
tr
ee
tag
g
i
n
g
is
d
o
n
e
u
s
in
g
s
p
ec
if
ic
s
h
ell
s
cr
ip
ts
n
a
m
ed
tr
ee
T
ag
g
er
B
in
ar
y
.
T
o
ex
ec
u
te
th
ese
s
cr
ip
t
s
,
w
e
u
s
e
a
J
av
a
w
r
ap
p
er
s
h
ell
s
cr
ip
t.
W
e
h
av
e
d
ev
elo
p
ed
alg
o
r
it
h
m
s
f
o
r
t
h
e
p
r
o
ce
s
s
i
n
g
o
f
t
ex
tu
a
l
r
eso
u
r
ce
s
i
n
Fre
n
c
h
,
in
cl
u
d
in
g
th
e
W
o
lf
Net
co
n
ce
p
t
clas
s
i
f
ic
atio
n
al
g
o
r
ith
m
w
h
o
s
e
p
u
r
p
o
s
e
is
to
ex
tr
ac
t
r
elatio
n
s
h
ip
s
o
f
Su
b
clas
s
O
f
t
y
p
e.
I
n
d
ee
d
,
in
o
r
d
er
to
lear
n
s
u
b
c
lass
-
o
f
r
elatio
n
s
f
o
r
tex
t
i
n
Fr
en
ch
,
w
e
i
m
p
le
m
e
n
ted
i
n
T
ex
t2
On
to
v
ar
ia
n
ts
o
f
alg
o
r
ith
m
s
e
x
p
lo
iti
n
g
t
h
e
h
y
p
er
n
y
m
s
tr
u
ct
u
r
e
in
W
O
L
F.
T
o
b
e
ab
le
to
ex
p
lo
it
th
is
h
y
p
er
n
y
m
s
tr
u
ct
u
r
e
in
W
OL
F,
w
e
h
av
e
d
ev
elo
p
ed
J
W
OL
F
[
2
8
]
an
A
P
I
i
n
J
av
a
b
ased
o
n
th
e
J
av
a
A
r
c
h
itect
u
r
e
f
o
r
XM
L
B
in
d
i
n
g
(
J
A
XB
)
A
P
I
f
o
r
th
e
m
a
n
ip
u
lat
io
n
o
f
XM
L
f
iles
.
5.
DIS
CU
SS
I
O
N
I
n
itiall
y
,
t
h
e
ad
ap
tatio
n
o
f
t
h
e
T
ex
t2
On
to
to
o
l
f
o
r
th
e
p
r
o
ce
s
s
i
n
g
o
f
co
r
p
o
r
a
o
f
d
o
cu
m
en
t
s
in
Fre
n
ch
s
ee
m
ed
a
n
ea
s
y
ta
s
k
.
Ho
w
e
v
er
,
as
w
e
p
r
o
g
r
ess
in
th
is
ad
v
en
tu
r
e,
en
d
les
s
tech
n
ica
l
ch
allen
g
es
ar
is
e
co
n
tin
u
o
u
s
l
y
.
W
e
f
ac
ed
e
n
d
less
ch
al
len
g
es
t
h
at
r
eq
u
ir
ed
p
ain
s
ta
k
i
n
g
e
f
f
o
r
ts
.
I
t
tu
r
n
s
o
u
t
t
h
at
b
ased
o
n
GA
T
E
,
T
ex
t2
On
to
is
clo
s
el
y
r
elate
d
to
th
is
ar
c
h
itect
u
r
e.
T
h
is
s
tr
o
n
g
d
ep
en
d
en
c
y
r
eq
u
ir
e
s
th
e
lear
n
i
n
g
an
d
ass
i
m
ilatio
n
o
f
co
n
ce
p
ts
a
n
d
n
o
tio
n
s
o
n
w
h
ich
G
A
T
E
is
b
u
ilt.
T
h
e
f
ir
s
t
les
s
o
n
w
e
lear
n
ed
is
th
at
s
o
m
et
i
m
e
s
it's
b
etter
to
b
u
ild
f
r
o
m
th
e
b
eg
in
n
i
n
g
t
h
an
to
tr
y
to
ad
ap
t
a
p
r
e
-
ex
is
tin
g
s
o
lu
t
io
n
.
I
n
p
ar
tic
u
lar
,
i
f
t
h
e
s
o
lu
tio
n
n
o
lo
n
g
er
h
as
s
u
p
p
o
r
t o
r
at
lea
s
t c
o
n
tac
ts
l
ik
el
y
to
s
h
ed
li
g
h
t
o
n
t
h
e
ad
ap
tatio
n
ap
p
r
o
ac
h
.
T
h
e
s
ec
o
n
d
les
s
o
n
is
th
at
b
ef
o
r
e
attac
k
i
n
g
t
h
e
p
er
s
o
n
aliza
tio
n
o
f
a
s
o
lu
t
io
n
,
w
e
s
h
o
u
ld
m
a
s
ter
th
e
th
eo
r
etica
l
n
o
tio
n
s
a
nd
th
e
tech
n
ical
to
o
ls
o
n
/
w
it
h
w
h
ich
it is
e
s
tab
lis
h
ed
.
A
r
m
ed
w
it
h
a
g
r
ea
t
te
n
ac
it
y
a
n
d
d
eter
m
i
n
atio
n
,
w
e
h
av
e
b
r
av
el
y
m
a
n
a
g
ed
th
e
ad
ap
tatio
n
ch
alle
n
g
e
o
f
T
ex
t2
On
to
to
o
l.
A
t
th
e
en
d
o
f
th
is
ad
v
e
n
tu
r
e,
w
e
m
a
n
a
g
ed
to
p
r
o
d
u
ce
a
v
er
s
io
n
o
f
T
ex
t2
On
to
ab
le
to
g
en
er
ate
a
n
o
n
to
lo
g
y
f
r
o
m
te
x
tu
al
r
eso
u
r
ce
s
w
r
itte
n
in
Fre
n
c
h
.
A
s
it
i
s
s
h
o
w
n
in
Fig
u
r
e
4
,
th
e
r
esu
lts
w
e
h
a
v
e
o
b
tain
ed
ar
e
in
cr
ed
ib
le
an
d
e
x
ce
ed
o
u
r
e
x
p
ec
ted
ex
p
ec
tati
o
n
s
.
I
n
d
ee
d
,
b
y
u
s
i
n
g
t
h
is
v
er
s
io
n
f
o
r
a
s
i
m
p
li
s
tic
d
o
cu
m
en
t,
w
e
f
o
u
n
d
th
a
t
it
allo
w
s
t
h
e
d
is
co
v
er
y
o
f
r
el
atio
n
s
h
ip
s
w
h
o
s
e
e
x
i
s
ten
ce
i
s
u
n
s
u
s
p
ec
ted
a
n
d
i
m
p
lau
s
ib
le.
Fig
u
r
e
4
.
T
ex
t2
On
to
u
s
er
in
ter
f
ac
e
–
ex
a
m
p
le
o
f
u
s
e
f
o
r
Fre
n
c
h
Fig
u
r
e
4
s
h
o
w
s
th
e
r
esu
lts
o
b
tain
ed
f
o
r
a
s
i
m
p
lis
tic
ex
a
m
p
le
o
f
a
d
o
cu
m
en
t
w
r
itte
n
in
Fre
n
c
h
.
P
r
im
ar
il
y
,
it
ill
u
s
tr
ates
t
h
e
S
u
b
class
O
f
r
elatio
n
s
h
ip
s
o
b
tain
e
d
th
r
o
u
g
h
t
h
e
ap
p
licatio
n
o
f
o
u
r
W
o
lf
Net
co
n
ce
p
t
class
i
f
icatio
n
alg
o
r
it
h
m
.
Fo
r
th
e
d
ev
elo
p
m
e
n
t
o
f
th
i
s
al
g
o
r
ith
m
,
w
e
h
a
v
e
b
ased
o
n
th
e
ex
p
lo
itatio
n
o
f
th
e
W
O
L
F
le
x
ical
d
atab
ase
u
s
i
n
g
t
h
e
J
W
O
L
F
A
P
I
.
L
i
k
e
its
co
u
n
ter
p
ar
t
in
t
h
e
o
r
ig
in
al
v
er
s
io
n
,
w
e
h
av
e
in
v
e
s
ted
t
h
e
W
O
L
F
e
x
p
lo
r
atio
n
f
ea
t
u
r
es
o
f
f
er
ed
b
y
J
W
O
L
F
p
ar
ticu
lar
l
y
i
n
ter
m
s
o
f
s
tr
u
ctu
r
e
in
v
e
s
ti
g
atio
n
s
o
f
th
e
h
y
p
er
n
y
m
r
elatio
n
s
h
ip
b
et
w
ee
n
th
e
d
i
f
f
er
e
n
t te
r
m
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J
E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8708
A
n
a
d
a
p
ta
tio
n
o
f Tex
t2
On
to
fo
r
s
u
p
p
o
r
tin
g
th
e
F
r
en
ch
la
n
g
u
a
g
e
(
Mo
r
a
d
Ha
jji
)
3749
I
n
Fi
g
u
r
e
5
,
w
e
g
iv
e
th
e
g
r
ap
h
ical
r
ep
r
esen
tat
io
n
o
f
t
h
e
in
s
tan
ce
s
o
f
t
h
e
S
u
b
class
O
f
r
elatio
n
ex
tr
ac
ted
an
d
illu
s
tr
ated
in
Fi
g
u
r
e
4
.
T
h
e
m
o
s
t
s
u
r
p
r
is
i
n
g
is
th
e
ab
ilit
y
o
f
th
i
s
v
er
s
io
n
to
d
is
co
v
er
in
s
tan
ce
s
o
f
th
is
r
elatio
n
s
h
ip
t
h
at
w
e
d
id
n
o
t e
v
e
n
i
m
a
g
i
n
e
s
o
th
a
t
w
e
r
el
ied
o
n
t
h
e
f
ea
t
u
r
es
o
f
f
er
ed
b
y
th
e
W
O
L
F
B
r
o
w
s
er
[2
8
]
to
en
s
u
r
e
t
h
e
v
er
ac
it
y
o
f
t
h
e
r
esu
l
ts
.
A
t t
h
is
le
v
el,
w
e
s
h
o
u
ld
ex
p
ec
t th
e
u
n
e
x
p
ec
ted
.
Fig
u
r
e
5
.
Gr
ap
h
ical
v
ie
w
o
f
S
u
b
class
Of
r
elatio
n
s
h
ip
in
s
tan
c
es
6.
CO
NCLU
SI
O
N
I
n
th
i
s
p
ap
er
,
w
e
p
r
esen
ted
o
u
r
ap
p
r
o
ac
h
f
o
r
ad
ap
tin
g
th
e
T
ex
t2
On
to
to
o
l
f
o
r
th
e
ex
t
r
ac
tio
n
o
f
o
n
to
lo
g
ies
f
r
o
m
co
r
p
o
r
a
o
f
tex
tu
a
l
d
o
cu
m
e
n
t
s
w
r
itte
n
in
F
r
en
ch
.
Desp
ite
th
e
o
b
s
tacle
s
en
co
u
n
ter
ed
d
u
e
to
lack
o
f
d
o
cu
m
e
n
tatio
n
an
d
s
u
p
p
o
r
t,
w
e
m
an
a
g
ed
to
p
r
o
d
u
ce
a
n
en
h
an
ce
d
v
er
s
io
n
o
f
T
ex
t2
On
to
ab
le
to
g
en
er
ate
a
n
o
n
to
lo
g
y
f
r
o
m
a
co
r
p
u
s
in
Fre
n
c
h
.
A
d
m
itt
ed
ly
,
w
it
h
t
h
is
v
er
s
io
n
w
e
ar
e
ab
le
to
ex
tr
ac
t
s
u
c
h
an
o
n
to
lo
g
y
.
Ho
w
e
v
er
,
th
e
ad
ap
tatio
n
o
f
th
is
to
o
l
is
ex
tr
e
m
el
y
o
v
er
w
h
el
m
in
g
.
I
n
d
ee
d
,
th
is
v
er
s
io
n
allo
w
s
u
s
to
e
x
tr
ac
t
a
n
o
n
to
lo
g
y
f
r
o
m
a
co
r
p
u
s
o
f
d
o
cu
m
e
n
t
s
in
Fre
n
c
h
,
n
e
v
er
th
ele
s
s
t
h
e
p
er
f
o
r
m
an
ce
s
d
o
n
o
t
s
atis
f
y
o
u
r
p
er
f
ec
t
io
n
is
t
ex
p
ec
tatio
n
s
.
Ho
w
e
v
er
,
t
h
is
ad
v
en
tu
r
e
h
a
s
o
p
en
ed
th
e
w
a
y
to
s
et
u
p
a
m
o
r
e
s
o
p
h
is
ticated
v
er
s
io
n
.
I
n
f
u
t
u
r
e
w
o
r
k
,
m
o
r
e
ef
f
o
r
ts
a
r
e
n
ee
d
ed
,
o
n
t
h
e
o
n
e
h
a
n
d
,
to
f
u
r
th
er
i
m
p
r
o
v
e
t
h
e
al
g
o
r
ith
m
s
t
h
at
w
e
h
av
e
ad
ap
ted
,
o
n
th
e
o
t
h
er
h
a
n
d
,
to
o
p
tim
iz
e
th
e
e
x
ec
u
tio
n
ti
m
e
a
n
d
u
til
izatio
n
o
f
r
eso
u
r
c
es
in
ter
m
s
o
f
C
P
U
co
n
s
u
m
p
tio
n
a
n
d
m
e
m
o
r
y
o
cc
u
p
atio
n
.
No
t
to
m
e
n
tio
n
,
ev
al
u
ati
n
g
t
h
is
v
er
s
io
n
o
n
a
lar
g
e
s
ca
le.
T
h
e
r
es
u
lt
o
f
th
is
co
n
tr
ib
u
tio
n
is
t
h
e
b
r
o
ad
en
in
g
o
f
o
u
r
h
o
r
izo
n
s
i
n
t
h
e
f
ield
o
f
o
n
to
lo
g
y
lear
n
i
n
g
.
O
n
e
o
f
th
e
au
x
il
iar
y
r
esu
lt
s
i
s
t
h
e
i
n
v
esti
g
atio
n
o
f
th
e
b
ases
o
n
w
h
ic
h
T
ex
t2
O
n
to
is
b
u
ilt
a
n
d
t
h
e
tech
n
ical
a
n
d
m
eth
o
d
o
lo
g
ical
asp
ec
ts
o
f
its
d
ev
elo
p
m
e
n
t.
T
h
is
is
an
en
li
g
h
ten
ed
an
d
in
f
o
r
m
ed
w
a
y
o
p
en
i
n
g
f
o
r
th
e
ad
ap
tatio
n
o
f
th
i
s
to
o
l
to
s
u
p
p
o
r
t th
e
o
th
er
lan
g
u
ag
e
s
.
RE
F
E
R
E
NC
E
S
[1
]
V
.
P
sy
c
h
e
,
J.
Bo
u
rd
e
a
u
,
a
n
d
O.
M
e
n
d
e
s,
“
A
p
p
o
rt
d
e
l’i
n
g
é
n
ierie
o
n
t
o
lo
g
iq
u
e
a
u
x
e
n
v
iro
n
n
e
m
e
n
ts
d
e
f
o
r
m
a
ti
o
n
à
d
istan
c
e
,
”
S
c
ien
c
e
s
e
t
T
e
c
h
n
o
lo
g
ies
d
e
l’In
f
o
rm
a
ti
o
n
e
t
d
e
l
a
Co
mm
u
n
ica
ti
o
n
p
o
u
r
l’É
d
u
c
a
ti
o
n
e
t
la
F
o
rm
a
ti
o
n
,
v
o
l.
1
0
,
n
o
.
1
,
p
p
.
8
9
–
1
2
6
,
2
0
0
3
.
[2
]
X
.
A
im
é
,
J.
Ch
a
rletJ,
F
.
F
u
rst,
P
.
Ku
n
tz,
F
.
T
rich
e
t,
a
n
d
F
.
Dh
o
m
b
re
s,
“
Ra
re
d
ise
a
se
s
k
n
o
w
led
g
e
m
a
n
a
g
e
m
e
n
t:
th
e
c
o
n
tri
b
u
ti
o
n
o
f
p
r
o
x
im
it
y
m
e
a
su
r
e
m
e
n
ts
in
On
t
o
Orp
h
a
a
n
d
OMIM
,
”
S
tu
d
ies
i
n
He
a
lt
h
T
e
c
h
n
o
lo
g
y
a
n
d
I
n
f
o
rm
a
ti
c
s
,
p
p
.
88
–
9
2
,
2
0
1
2
,
[3
]
N.
Ca
se
ll
a
s,
L
e
g
a
l
o
n
to
l
o
g
y
e
n
g
in
e
e
rin
g
:
M
e
th
o
d
o
lo
g
ies
,
mo
d
e
ll
in
g
tre
n
d
s,
a
n
d
th
e
o
n
t
o
lo
g
y
o
f
p
ro
fes
sio
n
a
l
ju
d
ici
a
l
k
n
o
wled
g
e
,
v
o
l.
3
.
S
p
ri
n
g
e
r
S
c
ien
c
e
&
Bu
sin
e
ss
M
e
d
ia,
2
0
1
1
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8708
I
n
t
J
E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
10
,
No
.
4
,
A
u
g
u
s
t
2020
:
3
7
4
3
-
375
0
3750
[4
]
M
.
HA
JJ
I,
M
.
QB
A
DO
U
a
n
d
K
.
M
A
NSOURI,
"
T
o
w
a
rd
s
a
n
A
u
to
m
a
ti
c
A
u
th
o
rin
g
a
n
d
O
p
ti
m
iza
ti
o
n
S
y
ste
m
o
f
A
d
a
p
ti
v
e
Co
u
rse
M
a
teria
ls,
"
2
0
1
9
5
th
I
n
ter
n
a
t
io
n
a
l
Co
n
fer
e
n
c
e
o
n
Op
ti
miza
t
io
n
a
n
d
Ap
p
li
c
a
ti
o
n
s (
ICOA)
,
Ke
n
it
ra
,
M
o
ro
c
c
o
,
2
0
1
9
.
[5
]
T
.
R.
G
ru
b
e
r,
“
A
tran
sla
ti
o
n
a
p
p
ro
a
c
h
to
p
o
rtab
le
o
n
t
o
lo
g
y
sp
e
c
i
fica
ti
o
n
s,”
Kn
o
wled
g
e
Acq
u
isit
io
n
,
v
o
l.
5
,
n
o
.
2
,
p
p
.
1
9
9
–
2
2
0
,
J
u
n
.
1
9
9
3
.
[6
]
R.
S
t
u
d
e
r,
V
.
R.
Be
n
jam
in
s,
a
n
d
D.
F
e
n
se
l,
“
Kn
o
w
led
g
e
e
n
g
in
e
e
ri
n
g
:
P
rin
c
i
p
les
a
n
d
m
e
th
o
d
s,”
Da
t
a
&
Kn
o
wled
g
e
En
g
i
n
e
e
rin
g
,
v
o
l.
2
5
,
n
o
.
1
,
p
p
.
1
6
1
–
1
9
7
,
M
a
r.
1
9
9
8
.
[7
]
J.
L
e
e
,
H.
Ch
a
e
,
C.
-
H.
Kim
,
a
n
d
K.
Kim
,
“
De
sig
n
o
f
p
ro
d
u
c
t
o
n
t
o
lo
g
y
a
rc
h
it
e
c
tu
re
f
o
r
c
o
ll
a
b
o
ra
ti
v
e
e
n
terp
rise
s,”
Exp
e
rt S
y
ste
ms
wit
h
A
p
p
l
ica
ti
o
n
s
,
v
o
l.
3
6
,
n
o
.
2
,
P
a
rt
1
,
p
p
.
2
3
0
0
–
2
3
0
9
,
M
a
r.
2
0
0
9
.
[8
]
S
.
Ne
g
a
sh
a
n
d
P
.
G
ra
y
,
“
Bu
sin
e
s
s
In
telli
g
e
n
c
e
,
”
in
Ha
n
d
b
o
o
k
o
n
De
c
isio
n
S
u
p
p
o
rt
S
y
ste
ms
2
:
Va
ria
ti
o
n
s
,
Be
rli
n
,
He
id
e
lb
e
rg
:
S
p
ri
n
g
e
r
Be
rli
n
He
id
e
lb
e
rg
,
2
0
0
8
,
p
p
.
1
7
5
–
1
9
3
.
[9
]
D.
M
c
De
rm
o
tt
,
“
A
rti
f
icia
l
In
telli
g
e
n
c
e
M
e
e
ts Na
tu
ra
l
S
tu
p
id
i
ty
,
”
S
IGAR
T
Bu
ll
.
,
n
o
.
5
7
,
p
p
.
4
–
9
,
A
p
r.
1
9
7
6
.
[1
0
]
De
M
a
u
ro
A
n
d
re
a
,
“
A
f
o
r
m
a
l
d
e
fin
it
i
o
n
o
f
Big
Da
ta
b
a
s
e
d
o
n
it
s
e
ss
e
n
ti
a
l
f
e
a
tu
re
s,”
L
ib
ra
ry
Rev
iew
,
v
o
l.
6
5
,
n
o
.
3
,
p
p
.
1
2
2
–
1
3
5
,
Ja
n
.
2
0
1
6
.
[1
1
]
F
.
S
.
C.
T
se
n
g
a
n
d
A
.
Y.
H.
Ch
o
u
,
“
T
h
e
c
o
n
c
e
p
t
o
f
d
o
c
u
m
e
n
t
w
a
r
e
h
o
u
sin
g
f
o
r
m
u
lt
i
-
d
im
e
n
sio
n
a
l
m
o
d
e
li
n
g
o
f
tex
tu
a
l
-
b
a
se
d
b
u
si
n
e
ss
in
telli
g
e
n
c
e
,
”
De
c
isio
n
S
u
p
p
o
rt
S
y
ste
ms
,
v
o
l.
4
2
,
n
o
.
2
,
p
p
.
7
2
7
–
7
4
4
,
No
v
.
2
0
0
6
.
[1
2
]
T
.
G
h
e
ra
si
m
,
“
Dé
t
e
c
ti
o
n
d
e
p
ro
b
lèm
e
s
d
e
q
u
a
li
té
d
a
n
s
les
o
n
to
lo
g
ies
c
o
n
stru
it
e
s
a
u
to
m
a
ti
q
u
e
m
e
n
t
à
p
a
rti
r
d
e
tex
tes
,
”
In
telli
g
e
n
c
e
a
rti
f
i
c
ielle [
c
s.A
I]
,
Un
iv
e
rsité d
e
Na
n
tes
,
2
0
1
3
.
[1
3
]
J.
P
a
rk
,
W
.
Ch
o
,
a
n
d
S
.
Rh
o
,
“
Ev
a
lu
a
ti
n
g
o
n
t
o
lo
g
y
e
x
trac
ti
o
n
to
o
ls
u
sin
g
a
c
o
m
p
re
h
e
n
siv
e
e
v
a
lu
a
ti
o
n
f
ra
m
e
w
o
rk
,
”
Da
ta
&
Kn
o
wled
g
e
E
n
g
i
n
e
e
rin
g
,
v
o
l.
6
9
,
n
o
.
1
0
,
p
p
.
1
0
4
3
–
1
0
6
1
,
2
0
1
0
.
[1
4
]
M
.
F
e
rn
á
n
d
e
z
-
L
ó
p
e
z
,
A
.
G
ó
m
e
z
-
P
é
re
z
,
a
n
d
N.
Ju
rist
o
,
“
M
ET
HO
NT
O
L
O
GY
:
F
ro
m
On
to
lo
g
i
c
a
l
A
rt
T
o
wa
rd
s
On
to
l
o
g
ica
l
En
g
in
e
e
rin
g
,
”
AAAI
-
9
7
S
p
ri
n
g
S
y
mp
o
si
u
m
S
e
rie
s
,
p
p
.
3
3
–
4
0
,
1
9
9
7
.
[1
5
]
S
.
S
taa
b
,
R.
S
tu
d
e
r,
H.
-
P
.
S
c
h
n
u
r
r,
a
n
d
Y.
S
u
re
,
“
Kn
o
w
led
g
e
p
ro
c
e
ss
e
s
a
n
d
o
n
to
l
o
g
ies
,
”
IEE
E
In
telli
g
e
n
t
S
y
ste
ms
,
v
o
l.
1
6
,
n
o
.
1
,
p
p
.
2
6
–
3
4
,
F
e
b
.
2
0
0
1
.
[1
6
]
H.
S
.
P
in
t
o
,
S
.
S
taa
b
,
a
n
d
C
.
T
e
m
p
ich
,
“
DIL
I
G
ENT
:
T
o
w
a
rd
s a
f
in
e
-
g
ra
in
e
d
m
e
th
o
d
o
l
o
g
y
f
o
r
DIs
tri
b
u
ted
,
L
o
o
se
ly
-
c
o
n
tro
ll
e
d
a
n
d
e
v
o
lv
In
G
En
g
in
e
e
rin
g
o
f
o
NT
o
lo
g
ies
,
”
i
n
Pro
c
e
e
d
in
g
s
o
f
th
e
1
6
th
Eu
ro
p
e
a
n
Co
n
fer
e
n
c
e
o
n
Arti
fi
c
ia
l
I
n
telli
g
e
n
c
e
,
p
p
.
3
9
3
–
3
9
7
,
2
0
0
4
.
[1
7
]
M
.
C.
S
u
á
re
z
-
F
ig
u
e
ro
a
,
“
Ne
On
M
e
th
o
d
o
lo
g
y
f
o
r
Bu
il
d
in
g
On
t
o
lo
g
y
Ne
t
w
o
rk
s:
S
p
e
c
if
i
c
a
ti
o
n
,
S
c
h
e
d
u
l
in
g
a
n
d
Re
u
se
,
”
Ju
n
-
2
0
1
0
.
[1
8
]
P
.
Cim
ian
o
a
n
d
J.
Vö
lk
e
r,
“
T
e
x
t2
On
to
:
A
F
ra
m
e
w
o
rk
f
o
r
On
to
l
o
g
y
L
e
a
rn
in
g
a
n
d
Da
ta
-
Driv
e
n
Ch
a
n
g
e
Disc
o
v
e
r
y
,
”
in
L
e
c
tu
re
N
o
tes
in
C
o
mp
u
ter
S
c
i
e
n
c
e
,
v
o
l.
3
5
1
3
,
p
p
.
2
2
7
–
2
3
8
,
2
0
0
5
.
[1
9
]
P
.
Cim
ian
o
,
“
On
to
lo
g
y
L
e
a
rn
in
g
a
n
d
P
o
p
u
lati
o
n
f
ro
m
T
e
x
t:
A
lg
o
rit
h
m
s,
Ev
a
lu
a
ti
o
n
a
n
d
A
p
p
li
c
a
ti
o
n
s,”
Ber
li
n
,
He
id
e
lb
e
rg
:
S
p
rin
g
e
r
-
Ver
la
g
,
2
0
0
6
.
[2
0
]
A
.
M
a
e
d
c
h
e
a
n
d
S
.
S
taa
b
,
“
Disc
o
v
e
rin
g
Co
n
c
e
p
tu
a
l
Re
latio
n
s
f
ro
m
Tex
t,
”
in
Pro
c
e
e
d
in
g
s
o
f
t
h
e
1
4
t
h
Eu
ro
p
e
a
n
Co
n
fer
e
n
c
e
o
n
Arti
fi
c
i
a
l
I
n
telli
g
e
n
c
e
,
Am
ste
rd
a
m
,
T
h
e
Ne
th
e
rlan
d
s,
T
h
e
Ne
th
e
rlan
d
s,
p
p
.
3
2
1
–
3
2
5
,
2
0
0
0
.
[2
1
]
D.
F
a
u
re
a
n
d
C.
Né
d
e
ll
e
c
,
“
A
Co
rp
u
s
-
b
a
se
d
C
o
n
c
e
p
t
u
a
l
Cl
u
ste
rin
g
M
e
th
o
d
f
o
r
V
e
rb
F
ra
m
e
s
a
n
d
O
n
to
lo
g
y
A
c
q
u
isit
io
n
,
”
i
n
L
RE
C
wo
rk
sh
o
p
o
n
,
p
p
.
5
–
1
2
,
1
9
9
8.
[2
2
]
G
.
Biss
o
n
,
C.
Né
d
e
ll
e
c
,
a
n
d
D.
Ca
ñ
a
m
e
ro
,
“
De
sig
n
in
g
Clu
ste
rin
g
M
e
th
o
d
s
f
o
r
On
to
l
o
g
y
Bu
il
d
in
g
-
T
h
e
M
o
’K
W
o
rk
b
e
n
c
h
.
,
”
in
ECA
I’2
0
0
0
W
o
rk
sh
o
p
o
n
On
t
o
l
o
g
y
L
e
a
rn
i
n
g
,
Pro
c
e
e
d
in
g
s
o
f
th
e
Fi
rs
t
W
o
rk
sh
o
p
o
n
On
t
o
lo
g
y
L
e
a
rn
in
g
OL’
2
0
0
0
,
Ber
li
n
,
Ge
rm
a
n
y
,
A
u
g
u
st
2
5
,
2
0
0
0
.
He
ld
i
n
c
o
n
ju
n
c
ti
o
n
wit
h
th
e
1
4
th
E
u
ro
p
e
a
n
Co
n
fer
e
n
c
e
o
n
Arti
fi
c
ia
l
I
n
telli
g
e
n
c
e
ECA
I’
2
0
0
0
,
Ber
li
n
,
Ge
rm
a
n
y
,
2
0
0
0
.
[2
3
]
E.
A
lf
o
n
se
c
a
a
n
d
S
.
M
a
n
a
n
d
h
a
r,
“
Ex
ten
d
in
g
a
L
e
x
ica
l
On
to
lo
g
y
b
y
a
Co
m
b
in
a
ti
o
n
o
f
Distrib
u
ti
o
n
a
l
S
e
m
a
n
ti
c
s
S
ig
n
a
tu
re
s,”
in
Pro
c
e
e
d
in
g
s
o
f
th
e
1
3
th
I
n
ter
n
a
t
io
n
a
l
Co
n
fer
e
n
c
e
o
n
Kn
o
wled
g
e
En
g
i
n
e
e
rin
g
a
n
d
Kn
o
wled
g
e
M
a
n
a
g
e
me
n
t.
On
t
o
l
o
g
ies
a
n
d
th
e
S
e
ma
n
ti
c
W
e
b
,
Be
rli
n
,
He
id
e
lb
e
rg
,
p
p
.
1
–
7
,
2
0
0
2
.
[2
4
]
J.
Ch
a
rlet,
B
.
Ba
c
h
im
o
n
t,
a
n
d
R.
T
ro
n
c
y
,
“
On
to
lo
g
ies
p
o
u
r
le
w
e
b
sé
m
a
n
ti
q
u
e
,
”
L
e
W
e
b
sé
ma
n
ti
q
u
e
-
Rev
u
e
I
3
:
In
fo
rm
a
t
io
n
-
I
n
ter
a
c
ti
o
n
-
I
n
telli
g
e
n
c
e
-
Nu
mé
ro
h
o
rs
sé
rie
,
p
p
.
6
9
–
1
0
0
,
2
0
0
4
.
[2
5
]
P
.
Cim
ian
o
,
A
.
P
iv
k
,
L
.
S
c
h
m
id
t
-
T
h
iem
e
,
a
n
d
S
.
S
taa
b
,
“
L
e
a
r
n
in
g
T
a
x
o
n
o
m
ic
Re
l
a
ti
o
n
s
f
ro
m
He
tero
g
e
n
e
o
u
s
S
o
u
rc
e
s o
f
Ev
id
e
n
c
e
,
”
IOS
Pre
ss
S
tyle
S
a
m
p
le
,
p
p
.
1
-
1
5
,
2
0
1
9
.
[2
6
]
P.
V
e
lard
i
,
P
.
F
a
b
ria
n
i,
a
n
d
M
.
M
issik
o
ff
,
“
Us
in
g
t
e
x
t
p
ro
c
e
ss
in
g
tec
h
n
iq
u
e
s
to
a
u
t
o
m
a
ti
c
a
ll
y
e
n
rich
a
d
o
m
a
in
o
n
t
o
lo
g
y
,
”
in
Pro
c
e
e
d
in
g
s
o
f
th
e
in
ter
n
a
ti
o
n
a
l
c
o
n
fer
e
n
c
e
o
n
Fo
r
ma
l
On
t
o
lo
g
y
i
n
In
f
o
rm
a
ti
o
n
S
y
s
tem
s
-
Vo
lu
me
2
0
0
1
,
Og
u
n
q
u
it
,
M
a
in
e
,
USA
,
p
p
.
2
7
0
–
2
8
4
,
2
0
0
1
.
[2
7
]
L
.
L
e
e
,
“
M
e
a
su
re
s
o
f
Distrib
u
ti
o
n
a
l
S
im
il
a
rit
y
,
”
in
Pro
c
e
e
d
in
g
s
o
f
th
e
3
7
t
h
An
n
u
a
l
M
e
e
ti
n
g
o
f
th
e
Asso
c
ia
ti
o
n
f
o
r
Co
mp
u
t
a
ti
o
n
a
l
L
in
g
u
isti
c
s
o
n
C
o
mp
u
ta
ti
o
n
a
l
L
i
n
g
u
isti
c
s
,
S
tr
o
u
d
sb
u
rg
,
P
A
,
USA
,
p
p
.
2
5
–
32
,
1
9
9
9
.
[2
8
]
M
.
Ha
jj
i,
M
.
Qb
a
d
o
u
,
a
n
d
K.
M
a
n
so
u
ri,
“
J
W
O
L
F
:
Ja
v
a
F
re
e
F
re
n
c
h
W
o
rd
n
e
t
L
ib
ra
ry
,
”
In
ter
n
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
Ad
v
a
n
c
e
d
Co
mp
u
ter
S
c
ien
c
e
a
n
d
Ap
p
li
c
a
ti
o
n
s
,
v
o
l
.
1
0
,
n
o
.
2
,
p
p
.
3
3
9
-
3
4
5
,
2
0
1
9
.
Evaluation Warning : The document was created with Spire.PDF for Python.