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.
8
,
No
.
3
,
J
u
n
e
201
8
,
p
p
.
1766
~
1
7
7
3
I
SS
N:
2088
-
8708
,
DOI
: 1
0
.
1
1
5
9
1
/
i
j
ec
e
.
v
8
i
3
.
p
p
1
7
6
6
-
1773
1766
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ia
e
s
co
r
e
.
co
m/
jo
u
r
n
a
ls
/in
d
ex
.
p
h
p
/
I
JE
C
E
Ana
pho
ra
Reso
lu
tion in Bus
in
ess
P
ro
cess
Requir
e
m
e
nt
Eng
ineering
Ria
d So
nb
o
l
1
,
G
ha
ida
Rebda
w
i
2
,
Na
da
G
hn
ei
m
3
1,
2
De
p
a
rtm
e
n
t
o
f
In
f
o
r
m
a
ti
c
s,
T
h
e
Hig
h
e
r
In
stit
u
te f
o
r
A
p
p
li
e
d
S
c
ie
n
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
,
S
y
ria
3
F
a
c
u
lt
y
o
f
In
f
o
r
m
a
ti
c
s,
Da
m
a
s
c
u
s
U
n
iv
e
rsit
y
,
S
y
ria
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Oct
15
,
2
0
1
7
R
ev
i
s
ed
J
an
12
,
2
0
1
8
A
cc
ep
ted
J
an
20
,
2
0
1
8
A
n
a
p
h
o
ra
re
so
lu
t
io
n
(A
R)
is
o
n
e
o
f
th
e
m
o
st
im
p
o
rtan
t
tas
k
s
in
n
a
tu
ra
l
lan
g
u
a
g
e
p
ro
c
e
ss
in
g
w
h
ich
f
o
c
u
se
s
o
n
th
e
p
ro
b
lem
o
f
re
so
lv
i
n
g
w
h
a
t
a
p
ro
n
o
u
n
,
o
r
a
n
o
u
n
p
h
ra
se
re
f
e
r
s
to
.
M
o
re
o
v
e
r,
A
R
p
la
y
s
a
n
e
ss
e
n
ti
a
l
ro
le
w
h
e
n
d
e
a
li
n
g
w
it
h
b
u
sin
e
ss
p
r
o
c
e
ss
tex
tu
a
l
d
e
sc
rip
ti
o
n
,
e
it
h
e
r
w
h
e
n
try
in
g
to
d
isc
o
v
e
r
th
e
p
r
o
c
e
ss
m
o
d
e
l
f
ro
m
th
e
tex
t,
o
r
w
h
e
n
v
a
li
d
a
ti
n
g
a
n
e
x
isti
n
g
m
o
d
e
l.
It
h
e
lp
s
t
h
e
se
sy
ste
m
s
i
n
d
isc
o
v
e
rin
g
t
h
e
c
o
re
c
o
m
p
o
n
e
n
ts
in
a
n
y
p
ro
c
e
ss
m
o
d
e
l
(a
c
to
rs
a
n
d
o
b
jec
ts).
In
th
is
p
a
p
e
r,
w
e
p
ro
p
o
se
a
d
o
m
a
in
sp
e
c
i
f
ic
AR
s
y
ste
m
.
T
h
e
a
p
p
ro
a
c
h
sta
rts
b
y
a
u
to
m
a
ti
c
a
ll
y
g
e
n
e
ra
ti
n
g
th
e
c
o
n
c
e
p
t
m
a
p
o
f
th
e
t
e
x
t,
th
e
n
th
e
s
y
ste
m
u
se
s
th
is
m
a
p
to
r
e
so
lv
e
re
fe
re
n
c
e
s
u
sin
g
th
e
sy
n
tac
ti
c
a
n
d
se
m
a
n
ti
c
re
latio
n
s
in
t
h
e
c
o
n
c
e
p
t
m
a
p
.
T
h
e
a
p
p
ro
a
c
h
o
u
t
p
e
rf
o
rm
s
th
e
st
a
te
-
of
-
th
e
a
rt
p
e
r
f
o
r
m
a
n
c
e
in
th
e
d
o
m
a
in
o
f
b
u
sin
e
ss
p
ro
c
e
ss
tex
ts
w
it
h
m
o
re
th
a
n
7
3
%
a
c
c
u
ra
c
y
.
In
a
d
d
it
i
o
n
,
th
is
a
p
p
ro
a
c
h
c
o
u
ld
b
e
e
a
sily
a
d
o
p
ted
to
re
s
o
lv
e
re
f
e
r
e
n
c
e
s in
o
t
h
e
r
d
o
m
a
in
s.
K
ey
w
o
r
d
:
An
ap
h
o
r
a
r
eso
lu
tio
n
B
u
s
i
n
ess
p
r
o
ce
s
s
m
o
d
eli
n
g
Natu
r
al
la
n
g
u
a
g
e
p
r
o
ce
s
s
in
g
P
r
o
ce
s
s
m
o
d
el
d
is
co
v
er
y
R
eq
u
ir
e
m
en
t e
n
g
in
ee
r
i
n
g
Co
p
y
rig
h
t
©
2
0
1
8
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
:
R
iad
So
n
b
o
l,
I
n
f
o
r
m
a
tics
Dep
ar
t
m
en
t,
T
h
e
Hig
h
er
I
n
s
tit
u
te
f
o
r
A
p
p
lied
Scien
ce
an
d
T
ec
h
n
o
lo
g
y
,
Da
m
asc
u
s
,
S
y
r
ia
.
E
m
ail:
r
iad
.
s
o
n
b
o
l@
h
ia
s
t.e
d
u
.
s
y
1.
I
NT
RO
D
UCT
I
O
N
An
ap
h
o
r
a
ar
e
b
ac
k
w
ar
d
r
ef
er
en
ce
s
to
ex
p
r
ess
io
n
s
(
u
s
u
all
y
n
o
u
n
s
)
w
h
ich
h
av
e
p
r
ev
io
u
s
l
y
b
ee
n
me
n
tio
n
ed
in
th
e
te
x
t
s
u
c
h
as
"
th
e
y
"
an
d
"
it
"
in
th
e
s
en
ten
ce
"
T
hey
b
u
y
th
e
is
s
u
e,
th
en
r
esell
it
to
th
e
p
u
b
lic
"
.
A
cc
o
r
d
in
g
to
it
s
lo
ca
tio
n
s
[
1
]
,
an
ap
h
o
r
a
co
u
ld
b
e
i
n
tr
a
-
s
en
t
en
tial
w
h
e
n
t
h
e
r
e
f
er
en
ce
is
l
o
ca
ted
in
t
h
e
s
a
m
e
s
en
te
n
ce
li
k
e
"
it"
in
th
e
last
e
x
a
m
p
le
,
o
r
co
u
ld
b
e
in
ter
-
s
en
te
n
tial
w
h
e
n
it
i
s
lo
ca
ted
i
n
p
r
ev
io
u
s
s
e
n
te
n
ce
s
lik
e
"
th
e
y
"
in
th
e
last
ex
a
m
p
le.
An
o
th
er
w
a
y
to
ca
teg
o
r
ize
an
a
p
h
o
r
a
is
b
ased
o
n
its
f
o
r
m
[
2
]
,
th
e
m
o
s
t
co
m
m
o
n
t
y
p
e
ac
co
r
d
in
g
to
th
is
w
a
y
o
f
ca
teg
o
r
izatio
n
is
p
r
o
n
o
m
i
n
al
an
ap
h
o
r
a
w
h
ic
h
co
u
ld
b
e
p
e
r
s
o
n
al
(
e.
g
.
h
e,
s
h
e,
it,
h
is
)
,
d
e
m
o
n
s
tr
ati
v
e
(
eg
.
t
h
is
,
th
at,
t
h
o
s
e)
,
o
r
r
ef
lex
i
v
e
(
e
.
g
.
h
i
m
s
el
f
,
its
e
lf
)
.
Ot
h
er
t
y
p
es
ar
e
q
u
an
ti
f
ier
s
(
e
.
g
.
o
n
e,
ea
ch
,
s
o
m
e)
,
o
r
d
in
al
(
f
ir
s
t,
f
o
r
m
er
,
latter
)
,
w
h
-
an
ap
h
o
r
a
(
e
.
g
.
w
h
o
,
w
h
ic
h
)
,
in
ad
d
itio
n
to
t
h
e
P
leo
n
asti
c
it,
an
d
id
io
m
atic
f
o
r
m
s
.
T
h
e
p
r
o
ce
s
s
o
f
id
en
tify
in
g
a
n
ap
h
o
r
ic
r
elatio
n
s
is
ca
lled
a
n
a
p
h
o
r
a
r
eso
lu
tio
n
(
A
R
)
.
AR
is
o
n
e
o
f
th
e
m
ai
n
task
s
in
Nat
u
r
al
L
an
g
u
a
g
e
P
r
o
ce
s
s
in
g
(
N
L
P
)
[
3
]
.
I
t
p
l
a
y
s
an
i
m
p
o
r
ta
n
t
r
o
le
in
m
a
n
y
ap
p
licatio
n
s
[
4
]
-
[
7
]
in
cl
u
d
in
g
I
n
f
o
r
m
at
io
n
E
x
tr
ac
t
io
n
,
T
ex
t
Su
m
m
ar
izatio
n
,
Q
u
esti
o
n
A
n
s
w
er
i
n
g
,
Ma
c
h
i
n
e
T
r
an
s
latio
n
,
Op
in
io
n
Min
i
n
g
,
R
eq
u
ir
e
m
e
n
t
an
a
l
y
s
is
,
an
d
d
is
co
v
er
in
g
m
o
d
els
f
r
o
m
te
x
t
u
al
d
escr
ip
tio
n
w
h
ic
h
is
th
e
d
o
m
ai
n
w
e
ar
e
f
o
cu
s
in
g
o
n
in
t
h
is
p
ap
er
.
Ho
w
e
v
er
,
A
R
i
s
co
n
s
id
er
ed
as
o
n
e
o
f
th
e
m
a
in
ch
a
llen
g
i
n
g
p
r
o
b
lem
in
N
L
P
b
ec
au
s
e
o
f
its
h
i
g
h
-
de
p
en
d
en
c
y
o
n
b
o
th
s
y
n
tac
tic
an
d
s
e
m
a
n
tic
p
r
o
ce
s
s
in
g
;
t
h
e
ac
cu
r
ac
y
o
f
th
e
s
e
t
w
o
t
y
p
e
s
o
f
p
r
e
-
p
r
o
ce
s
s
in
g
is
s
till
f
ar
f
r
o
m
id
ea
l,
w
h
ich
ad
d
m
o
r
e
d
if
f
ic
u
lties
o
n
b
u
i
ld
in
g
an
ac
cu
r
ate
AR
s
y
s
te
m
[
8
]
.
Ma
n
y
r
esear
ch
er
s
h
a
v
e
w
o
r
k
e
d
o
n
b
u
ild
i
n
g
a
n
AR
s
y
s
te
m
f
r
o
m
d
if
f
er
en
t p
er
s
p
ec
tiv
e
s
; p
ar
t
o
f
t
h
e
m
u
s
ed
r
u
le
-
b
ased
ap
p
r
o
ac
h
es,
an
d
o
th
er
s
f
o
llo
w
ed
a
s
tati
s
tical
p
r
o
ce
d
u
r
e
b
ased
o
n
tag
g
ed
co
r
p
o
r
a.
I
n
r
u
le
-
b
ased
ap
p
r
o
ac
h
es
,
[
9
]
,
[
10
]
,
a
s
et
o
f
m
a
n
u
al
-
en
co
d
ed
r
u
les
ar
e
u
s
ed
.
T
h
ese
r
u
les
ar
e
b
ased
o
n
v
ar
io
u
s
li
n
g
u
i
s
tic
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
p
h
o
r
a
R
eso
lu
tio
n
i
n
B
u
s
in
ess
P
r
o
ce
s
s
R
eq
u
ir
eme
n
t E
n
g
i
n
ee
r
in
g
(
R
ia
d
S
o
n
b
o
l
)
1767
f
ea
t
u
r
e
s
(
m
ai
n
l
y
m
o
r
p
h
o
-
s
y
n
t
ac
tic
f
ea
t
u
r
es s
u
c
h
as p
ar
t
-
of
-
s
p
ee
ch
an
d
g
e
n
d
er
/n
u
m
b
er
i
n
f
o
r
m
atio
n
)
.
T
h
e
b
est
-
ac
h
iev
ed
p
er
f
o
r
m
a
n
ce
i
n
MU
C
-
7
w
a
s
ar
o
u
n
d
7
0
%
p
r
ec
is
io
n
w
it
h
6
0
%
r
ec
all,
w
h
ic
h
is
s
t
ill
lo
w
er
t
h
a
n
w
h
a
t
w
e
n
ee
d
in
p
r
ac
tical
ap
p
licati
o
n
s
.
T
h
ese
r
u
le
s
ar
e
l
i
m
ited
in
g
e
n
er
al
an
d
d
o
es
n
o
t
w
o
r
k
eq
u
all
y
i
n
d
i
f
f
er
e
n
t
d
o
m
ai
n
s
.
Statis
t
ical
ap
p
r
o
ac
h
es
ap
p
ly
Ma
ch
i
n
e
L
ea
r
n
i
n
g
al
g
o
r
ith
m
s
,
s
u
c
h
as
Dec
i
s
io
n
T
r
ee
s
an
d
Su
p
p
o
r
t
Vec
to
r
Ma
ch
i
n
es [
1
1
]
-
[
1
3
]
.
Usu
all
y
,
t
h
ese
lear
n
i
n
g
al
g
o
r
ith
m
s
ar
e
ap
p
lied
o
n
lex
ical,
s
y
n
t
ac
tic,
s
e
m
an
t
ic,
an
d
k
n
o
w
led
g
e
-
b
a
s
ed
f
ea
t
u
r
es.
I
n
g
e
n
er
al,
th
e
ac
h
ie
v
ed
p
er
f
o
r
m
an
ce
is
c
lo
s
e
to
t
h
e
b
est
-
p
e
r
f
o
r
m
i
n
g
r
u
le
-
b
ased
s
y
s
te
m
i
n
MU
C
-
6
an
d
MU
C
-
7
.
Oth
er
w
o
r
k
s
p
r
esen
t
h
y
b
r
id
ap
p
r
o
ac
h
es
co
m
b
i
n
i
n
g
r
u
le
-
b
ased
an
d
m
ac
h
i
n
e
-
lear
n
in
g
co
m
p
o
n
e
n
t
s
[
1
4
]
,
w
h
i
ch
ai
m
t
o
co
m
b
i
n
e
t
h
e
ad
v
an
ta
g
e
o
f
ea
ch
o
f
th
e
s
e
ap
p
r
o
ac
h
es.
Sin
ce
t
h
e
p
r
o
b
le
m
o
f
A
R
is
s
ti
ll
f
ar
f
r
o
m
b
ei
n
g
s
o
lv
ed
[
1
5
]
,
m
an
y
p
ap
er
s
f
o
cu
s
ed
o
n
d
o
m
a
in
r
elate
d
AR
s
y
s
te
m
to
s
u
p
p
o
r
t a
s
p
ec
if
ic
d
o
m
a
in
o
r
a
s
p
ec
if
ic
ap
p
lica
tio
n
.
Ma
n
y
p
ap
er
s
h
av
e
b
ee
n
p
r
o
p
o
s
ed
to
r
eso
lv
e
an
ap
h
o
r
ic
NP
s
i
n
b
io
m
ed
ical
tex
ts
[
1
6
]
-
[
1
8
]
,
m
ac
h
in
e
tr
an
s
latio
n
[
1
9
]
,
o
r
b
u
s
ies
p
r
o
ce
s
s
d
o
m
ai
n
s
[
2
0
]
,
[
2
1
]
,
[
7
]
.
I
n
th
e
n
ex
t
s
ec
tio
n
s
,
w
e
will
f
o
c
u
s
o
n
t
h
e
d
o
m
ai
n
o
f
p
r
o
ce
s
s
m
o
d
eli
n
g
an
d
t
h
e
i
m
p
o
r
ta
n
ce
o
f
AR
s
y
s
te
m
s
in
th
is
d
o
m
ai
n
,
th
e
n
w
e
w
ill
r
ev
ie
w
s
o
m
e
r
elate
d
w
o
r
k
s
in
s
ec
tio
n
s
3
.
Sectio
n
4
p
r
esen
ts
o
u
r
p
r
o
p
o
s
ed
ap
p
r
o
ac
h
,
an
d
th
en
w
e
ev
al
u
ate
th
is
ap
p
r
o
ac
h
w
it
h
a
co
m
p
ar
i
s
o
n
to
o
th
er
r
esear
ch
e
s
in
S
ec
ti
o
n
5
.
W
e
co
n
clu
d
e
o
u
r
p
ap
er
in
S
ec
tio
n
6
.
2.
B
USI
NE
SS
P
RO
C
E
SS
M
O
DE
L
I
N
G
AND
T
H
E
N
E
E
D
F
O
R
AR
SYST
E
M
S
Mo
d
eli
n
g
is
o
n
e
o
f
t
h
e
co
r
e
task
s
in
b
u
s
in
e
s
s
p
r
o
ce
s
s
m
a
n
ag
e
m
e
n
t
(
B
P
M)
[
2
2
]
.
I
t
aim
s
to
cr
ea
te
r
ep
r
esen
tatio
n
s
(
u
s
u
all
y
ca
lled
m
o
d
els)
o
f
t
h
e
p
r
o
ce
s
s
es
o
f
a
n
o
r
g
an
izatio
n
to
u
n
d
er
s
ta
n
d
t
h
e
m
,
d
o
cu
m
e
n
ti
n
g
th
eir
d
etails,
an
al
y
zi
n
g
th
eir
p
er
f
o
r
m
a
n
ce
to
d
eter
m
i
n
e
o
p
p
o
r
tu
n
ities
f
o
r
i
m
p
r
o
v
e
m
en
ts
,
o
r
r
e
p
r
esen
tin
g
th
e
tar
g
et
p
r
o
ce
s
s
s
tate.
Du
e
to
its
ch
a
llen
g
es,
m
o
d
eli
n
g
r
ep
r
esen
t
s
t
h
e
m
o
s
t
cr
itica
l
s
tep
i
n
B
P
M
lif
e
c
y
cle.
I
t
i
s
t
h
e
m
o
s
t
ti
m
e
co
n
s
u
m
in
g
a
n
d
co
s
tl
y
tas
k
;
it
r
eq
u
ir
e
s
co
n
d
u
ct
in
g
a
n
u
m
b
er
o
f
m
ee
ti
n
g
s
,
w
o
r
k
s
h
o
p
s
,
in
ter
v
ie
w
s
b
et
w
ee
n
m
o
d
eli
n
g
ex
p
er
ts
an
d
p
r
o
ce
s
s
p
er
f
o
r
m
er
s
to
ac
q
u
ir
e
th
e
r
eq
u
ir
ed
k
n
o
w
led
g
e
in
a
h
i
g
h
l
y
i
n
ter
ac
ti
v
e
an
d
r
ep
etitiv
e
ap
p
r
o
ac
h
.
A
cc
o
r
d
in
g
to
[
2
3
]
,
b
u
ild
i
n
g
as
-
i
s
m
o
d
el
co
n
s
u
m
es
ab
o
u
t
6
0
%
o
f
th
e
o
v
er
all
ti
m
e
s
p
e
n
t
i
n
a
w
o
r
k
f
lo
w
p
r
o
j
ec
t.
On
t
h
e
o
th
er
h
an
d
,
i
n
m
o
s
t
o
r
g
an
izat
io
n
s
,
t
h
e
r
eq
u
ir
ed
i
n
f
o
r
m
at
io
n
ar
e
av
ai
lab
le
in
tex
t
u
al
f
o
r
m
s
;
8
5
%
o
f
th
e
in
f
o
r
m
atio
n
in
c
o
m
p
a
n
ies
ar
e
s
t
o
r
ed
in
u
n
s
tr
u
ctu
r
ed
d
o
cu
m
e
n
t
s
m
o
s
tl
y
te
x
tu
a
l.
T
h
is
in
cl
u
d
es
p
o
lices,
r
ep
o
r
ts
,
f
o
r
m
s
,
m
a
n
u
als,
k
n
o
w
led
g
e
m
a
n
a
g
e
m
e
n
t
s
y
s
te
m
s
,
a
n
d
e
m
a
ils
m
e
s
s
a
g
e
s
[
2
4
]
.
I
n
ad
d
itio
n
,
m
o
s
t
p
r
o
ce
s
s
p
er
f
o
r
m
er
s
ar
e
a
cc
u
s
to
m
ed
to
ex
p
r
ess
i
n
g
t
h
eir
n
ee
d
s
i
n
n
a
tu
r
al
la
n
g
u
a
g
e
[
2
5
]
.
A
ll
t
h
ese
tex
t
u
al
in
f
o
r
m
atio
n
r
ep
r
ese
n
t a
p
o
ten
t
ial
s
o
u
r
ce
s
o
f
k
n
o
w
led
g
e
n
ee
d
ed
in
b
u
ild
in
g
t
h
e
m
o
d
el.
T
h
ese
f
ac
ts
r
aised
t
h
e
q
u
e
s
tio
n
o
f
h
o
w
r
e
s
ea
r
ch
er
s
ca
n
s
a
v
e
th
is
co
s
t
b
y
b
u
ild
i
n
g
to
o
ls
th
at
co
u
ld
s
u
p
p
o
r
t
m
o
d
elin
g
ex
p
er
ts
in
t
h
eir
m
a
n
u
a
l
w
o
r
k
lo
ad
.
T
h
ese
s
y
s
te
m
s
w
ill
n
o
t
r
ep
lace
m
o
d
elin
g
ex
p
er
t
b
u
t
w
ill
h
elp
th
e
m
i
n
cr
ea
tin
g
m
o
d
els
m
o
r
e
e
f
f
icie
n
tl
y
in
ter
m
s
o
f
t
h
e
r
eq
u
ir
ed
ti
m
e,
co
s
t,
an
d
q
u
al
it
y
[
2
6
]
.
A
cc
o
r
d
in
g
to
[
7
]
,
s
u
b
s
tan
tial sa
v
i
n
g
s
ar
e
p
o
s
s
ib
le
b
y
p
r
o
v
id
i
n
g
s
u
c
h
au
t
o
m
a
tio
n
to
o
ls
.
Natu
r
al
L
an
g
u
ag
e
P
r
o
ce
s
s
i
n
g
(
NL
P
)
p
lay
s
a
n
ess
e
n
tia
l
r
o
le
in
ex
tr
ac
tin
g
t
h
e
m
o
d
el
f
r
o
m
d
o
cu
m
e
n
ts
,
s
in
ce
o
n
e
n
ee
d
to
h
a
n
d
le
m
an
y
co
m
p
le
x
c
h
alle
n
g
e
s
i
n
cl
u
d
in
g
e
x
tr
ac
tin
g
ac
t
iv
i
ties
,
o
r
d
er
in
g
t
h
e
m
,
an
d
d
ea
li
n
g
w
it
h
co
n
c
u
r
r
en
c
y
,
an
d
lo
o
p
s
[
2
7
]
.
A
n
ap
h
o
r
a
r
eso
lu
tio
n
is
o
n
e
o
f
th
e
p
r
o
b
lem
s
th
at
m
u
s
t
b
e
tack
led
w
h
e
n
an
al
y
z
in
g
te
x
t
u
al
p
r
o
ce
s
s
d
escr
ip
tio
n
s
,
as
m
an
y
co
n
ce
p
ts
,
task
s
,
ac
to
r
s
an
d
r
elatio
n
s
h
i
p
b
et
w
ee
n
p
h
r
a
s
e
s
w
o
u
ld
b
e
m
is
s
ed
if
th
e
r
ef
er
e
n
ce
s
i
n
te
x
t
ar
e
n
o
t
r
eso
l
v
ed
.
F
o
r
in
s
ta
n
ce
,
t
h
e
w
o
r
d
“
it”
i
n
th
e
s
en
ten
ce
(
“
I
f
i
t
is
n
o
t
av
ailab
le,
it
i
s
b
ac
k
-
o
r
d
er
ed
”
)
,
co
u
ld
n
o
t
b
e
m
ea
n
i
n
g
f
u
l
u
n
less
w
e
co
n
s
id
er
th
e
p
r
ev
io
u
s
co
n
te
x
t.
Mo
r
eo
v
er
,
s
o
m
e
a
cti
v
itie
s
ca
n
b
e
s
p
lit
u
p
in
to
m
o
r
e
t
h
an
o
n
e
s
en
te
n
ce
an
d
a
n
ap
h
o
r
a
an
al
y
s
is
h
elp
s
to
co
n
n
ec
t
an
d
r
ec
o
g
n
ize
t
h
ese
s
en
ten
ce
s
as
o
n
e
ac
ti
v
it
y
.
T
h
e
n
ex
t
e
x
a
m
p
le
s
h
o
w
s
t
h
e
i
m
p
o
r
ta
n
ce
o
f
g
o
o
d
AR
s
y
s
te
m
w
h
e
n
d
is
co
v
er
i
n
g
t
h
e
m
o
d
el
f
r
o
m
te
x
t
s
:
a)
Fin
all
y
,
s
he
as
s
i
g
n
s
th
e
o
r
d
er
to
th
e
w
ai
te
r
.
(
w
e
n
ee
d
A
R
to
d
i
s
co
ve
r
th
e
A
cto
r
)
b)
On
ce
t
h
e
f
o
o
d
,
j
u
ice,
an
d
ca
r
t
ar
e
r
ea
d
y
,
th
e
w
aiter
d
eliv
er
s
it
to
th
e
g
u
e
s
t
'
s
r
o
o
m
.
(
w
e
n
ee
d
A
R
to
d
etec
t
th
e
O
b
ject
)
c)
Usu
al
l
y
t
hey
p
la
y
a
tr
ip
le
r
o
le:
First,
t
hey
p
r
o
v
id
e
th
e
co
m
p
a
n
y
w
it
h
p
r
o
ce
d
u
r
al
an
d
f
i
n
an
cia
l
ad
v
ice,
th
en
t
hey
b
u
y
th
e
i
s
s
u
e,
an
d
f
i
n
all
y
t
hey
r
esell
it
to
th
e
p
u
b
lic.
(
W
e
n
ee
d
A
R
t
o
d
etec
t
b
o
th
th
e
o
b
ject
a
n
d
a
ct
o
r
s
)
d)
I
f
Ser
v
ice
Ma
n
a
g
e
m
e
n
t
is
s
u
r
e
th
e
y
ca
n
a
n
al
y
ze
it,
th
e
y
p
er
f
o
r
m
th
e
a
n
al
y
s
i
s
.
(
W
e
n
ee
d
A
R
to
d
etec
t
t
h
e
co
n
d
itio
n
)
I
n
th
e
ca
s
e
o
f
b
u
s
in
e
s
s
p
r
o
ce
s
s
m
o
d
elin
g
,
t
h
e
m
o
s
t c
o
m
m
o
n
u
s
a
g
e
o
f
an
ap
h
o
r
a
is
to
r
ef
er
t
o
an
ac
to
r
,
o
b
j
ec
t
o
r
r
eso
u
r
ce
.
T
h
ese
th
r
ee
k
in
d
s
o
f
n
o
u
n
p
h
r
ases
r
ep
r
esen
t
th
e
m
o
s
t
f
r
eq
u
en
t
e
n
ti
ties
in
an
y
te
x
tu
a
l
d
escr
ip
tio
n
.
T
h
is
f
ac
t
ad
d
s
m
o
r
e
d
if
f
icu
lt
ies
to
AR
s
y
s
te
m
s
in
t
h
i
s
d
o
m
ain
.
A
ct
u
all
y
,
u
s
in
g
s
i
m
p
le
d
is
ta
n
ce
h
eu
r
i
s
tics
w
o
u
ld
n
o
t
b
e
s
u
f
f
ici
en
t
to
g
et
a
n
ac
ce
p
ted
ac
c
u
r
ac
y
,
m
o
s
t
AR
s
y
s
te
m
s
in
t
h
is
d
o
m
ai
n
u
s
e
s
y
n
tact
ic
f
ea
t
u
r
es to
i
m
p
r
o
v
e
t
h
e
ac
cu
r
a
c
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.
8
,
No
.
3
,
J
u
n
e
201
8
:
1
7
6
6
–
1773
1768
3.
RE
L
AT
E
D
WO
R
K
S
I
n
[
2
0
]
,
an
A
R
s
y
s
te
m
h
a
s
b
ee
n
p
r
o
p
o
s
ed
to
s
u
p
p
o
r
t
th
e
s
i
m
ilar
it
y
c
h
ec
k
b
et
w
ee
n
an
ac
t
iv
it
y
i
n
t
h
e
p
r
o
ce
s
s
m
o
d
el
a
n
d
a
s
en
ten
ce
in
th
e
n
atu
r
al
la
n
g
u
a
g
e
te
x
t.
T
h
is
ap
p
r
o
ac
h
u
s
es
Sta
n
f
o
r
d
P
ar
s
er
to
r
etr
iev
e
a
d
ep
en
d
en
c
y
tr
ee
.
T
h
i
s
tr
ee
w
o
u
ld
b
e
u
s
ed
to
id
e
n
ti
f
y
o
b
j
ec
ts
in
th
e
s
e
n
te
n
ce
s
b
ased
o
n
t
h
e
r
elatio
n
s
o
f
d
ir
ec
t
o
b
j
ec
ts
an
d
n
o
m
i
n
al
s
u
b
j
ec
ts
.
I
f
t
h
e
s
en
te
n
ce
w
h
er
e
t
h
e
An
ap
h
o
r
a
o
cc
u
r
r
ed
h
as
n
o
o
b
j
ec
ts
,
t
h
e
an
ap
h
o
r
ic
is
r
ep
lace
d
b
y
an
o
b
j
ec
t p
r
esen
t in
th
e
p
r
ev
io
u
s
s
e
n
te
n
ce
.
[
2
1
]
I
n
tr
o
d
u
ce
s
t
h
r
ee
d
if
f
er
en
t
an
ap
h
o
r
a
r
eso
lu
tio
n
ap
p
r
o
ac
h
es
:
a
s
i
m
p
le
le
x
ical
ap
p
r
o
ac
h
an
d
t
w
o
f
u
r
t
h
er
ap
p
r
o
ac
h
es
b
ased
o
n
a
s
s
o
ciatio
n
r
u
le
s
w
h
ic
h
w
er
e
c
r
ea
ted
d
u
r
in
g
a
s
tati
s
tical
a
n
al
y
s
i
s
o
f
a
w
o
r
k
f
lo
w
co
r
p
u
s
u
s
i
n
g
a
s
eq
u
e
n
tial
p
att
er
n
m
i
n
i
n
g
th
at
w
a
s
p
r
esen
ted
b
y
Ag
r
a
w
al
[
3
1
]
.
T
h
e
p
ap
er
e
v
alu
a
tes
t
h
ese
t
h
r
ee
ap
p
r
o
ac
h
es
us
i
n
g
3
7
w
o
r
k
f
lo
w
s
cr
ea
ted
b
y
a
h
u
m
a
n
e
x
p
er
t
,
all
o
f
th
e
m
ar
e
f
r
o
m
co
o
k
i
n
g
d
o
m
a
in
,
t
h
e
b
est
ac
h
iev
ed
p
r
ec
is
io
n
w
a
s
ar
o
u
n
d
5
1
% w
i
th
3
0
% r
ec
all.
[
7
]
I
n
tr
o
d
u
ce
s
a
h
e
u
r
is
tic
s
-
b
a
s
ed
ap
p
r
o
ac
h
to
r
eso
lv
e
d
eter
m
i
n
er
an
d
p
r
o
n
o
u
n
s
.
T
h
e
ap
p
r
o
ac
h
u
s
e
s
th
e
d
is
ta
n
ce
b
et
w
ee
n
a
n
ap
h
o
r
a
an
d
n
o
u
n
s
,
in
ad
d
itio
n
to
a
s
et
o
f
s
y
n
tactic
m
atc
h
i
n
g
f
ea
tu
r
e
s
.
Usi
n
g
47
p
r
o
ce
s
s
d
escr
ip
tio
n
s
co
v
er
i
n
g
v
ar
io
u
s
d
o
m
ai
n
s
,
th
e
au
t
h
o
r
s
ev
al
u
ate
t
h
eir
w
o
r
k
a
n
d
co
m
p
ar
e
th
eir
ap
p
r
o
ac
h
w
it
h
t
w
o
g
e
n
er
ic
an
ap
h
o
r
a
r
eso
lu
tio
n
s
y
s
te
m
(
B
A
R
T
[
2
8
]
an
d
R
ec
o
n
cile
[
2
9
]
)
.
T
h
e
r
esu
lts
s
h
o
w
th
at
t
h
eir
ap
p
licatio
n
-
o
r
ien
ted
ap
p
r
o
ac
h
ac
h
ie
v
ed
a
n
ac
c
u
r
ac
y
o
f
6
3
.
0
6
%
w
h
ile
b
o
th
g
en
er
ic
ap
p
r
o
ac
h
es
w
er
e
n
o
t
ab
le
to
id
en
tify
m
o
r
e
t
h
an
4
2
% o
f
t
h
e
ca
s
es c
o
r
r
ec
tl
y
.
4.
O
UR
AP
P
RO
ACH
T
o
r
eso
lv
e
an
an
ap
h
o
r
a,
o
u
r
ap
p
r
o
ac
h
is
b
ased
o
n
tw
o
m
ain
s
tag
es
:
First,
w
e
p
r
o
ce
s
s
th
e
w
h
o
le
tex
t
to
ex
tr
ac
t it
s
co
n
ce
p
ts
m
ap
,
i.e
.
its
co
n
ce
p
ts
an
d
t
h
e
s
e
m
a
n
tic
r
elatio
n
s
h
ip
s
b
et
w
ee
n
t
h
ese
c
o
n
ce
p
ts
,
th
e
n
i
n
t
h
e
s
ec
o
n
d
s
tag
e
w
e
u
s
e
t
h
e
ex
tr
ac
ted
m
ap
to
r
eso
lv
e
an
ap
h
o
r
a
to
th
e
m
o
s
t
s
i
m
ilar
co
n
ce
p
t
b
ased
o
n
a
s
i
m
i
lar
it
y
m
ea
s
u
r
e.
T
h
is
s
i
m
ilar
i
t
y
m
e
asu
r
e
w
o
u
ld
h
a
v
e
t
w
o
i
m
p
o
r
tan
t
p
r
o
p
er
ties
:
(
1
)
it
w
o
u
l
d
b
e
b
ased
o
n
th
e
r
elatio
n
s
h
ip
s
i
n
t
h
e
m
ap
w
h
ic
h
r
ep
r
esen
t
s
t
h
e
w
h
o
le
tex
t
i.e
.
n
o
t
o
n
l
y
b
ased
o
n
a
f
e
w
s
en
te
n
ce
s
b
e
f
o
r
e
o
r
af
ter
th
e
an
ap
h
o
r
a.
(
2
)
it
is
b
ased
o
n
a
d
o
m
ai
n
-
s
p
ec
if
ic
s
e
m
an
tic
n
et
w
o
r
k
,
n
o
t
o
n
a
g
en
er
i
c
n
et
w
o
r
k
s
u
ch
a
s
w
o
r
d
Net,
t
h
is
f
ac
t
m
a
k
e
t
h
e
m
ea
s
u
r
e
m
e
n
t
s
clo
s
er
to
t
h
e
co
n
tex
t
o
f
th
e
co
n
ce
p
ts
i
n
t
h
e
tex
t.
I
n
th
e
n
e
x
t
p
ar
ag
r
ap
h
s
,
w
e
w
i
ll g
iv
e
m
o
r
e
d
etails ab
o
u
t e
ac
h
o
f
t
h
ese
t
wo
s
tag
es:
3
.
1
.
I
nitia
l c
o
ncept
m
a
p g
ener
a
t
io
n
1)
Mo
r
p
h
o
lo
g
ical
an
d
L
e
x
ical
An
al
y
s
i
s
I
n
th
i
s
s
tep
,
w
e
s
p
lit
t
h
e
tex
t
in
to
s
en
ten
ce
s
an
d
s
e
n
ten
ce
s
in
to
w
o
r
d
s
.
T
h
en
,
w
e
ap
p
ly
Sta
n
f
o
r
d
L
e
m
m
atize
r
o
n
ea
ch
w
o
r
d
to
r
e
m
o
v
e
i
n
f
lectio
n
al
e
n
d
in
g
s
an
d
to
f
in
d
th
e
b
ase
f
o
r
m
o
f
t
h
e
w
o
r
d
(
i.e
.
lem
m
a)
.
2)
S
y
n
tactic
An
al
y
s
i
s
First
,
w
e
u
s
e
Stan
f
o
r
d
p
o
s
-
ta
g
g
er
[
3
0
]
to
tag
ea
ch
w
o
r
d
w
i
th
its
s
u
itab
le
P
OS
tag
w
h
ich
i
n
d
icate
s
t
h
e
s
y
n
tactic
r
o
le
o
f
t
h
e
w
o
r
d
(
s
u
ch
a
s
p
lu
r
al
No
u
n
,
s
i
n
g
u
lar
No
u
n
,
A
d
v
er
b
,
A
d
j
ec
tiv
e,
etc
.
)
.
T
h
is
s
y
n
tactic
in
f
o
r
m
atio
n
w
o
u
ld
h
e
lp
u
s
to
d
eter
m
in
e
th
e
e
n
titi
e
s
a
n
d
t
h
e
co
n
ce
p
ts
i
n
n
e
x
t
s
e
m
an
tic
p
r
o
ce
s
s
i
n
g
s
tep
s
.
T
h
en
,
w
e
g
e
n
er
ate
t
h
e
d
ep
en
d
en
c
y
t
r
ee
f
o
r
ea
c
h
s
e
n
te
n
ce
u
s
in
g
t
h
e
w
o
r
k
o
f
C
h
e
n
a
n
d
Ma
n
n
in
g
[
3
1
]
.
T
h
is
p
ar
s
er
co
n
clu
d
es
th
e
d
ep
en
d
en
c
y
tr
ee
d
ep
en
d
in
g
o
n
n
e
u
r
al
n
et
w
o
r
k
b
y
r
ep
r
ese
n
ti
n
g
all
w
o
r
d
s
,
P
OS
tag
s
a
n
d
d
ep
en
d
en
c
y
r
elatio
n
s
h
ip
s
’
lab
els
as
d
en
s
e
v
ec
to
r
s
.
A
cc
o
r
d
in
g
to
th
e
a
u
th
o
r
s
,
t
h
e
p
ar
s
er
is
ab
le
to
p
a
r
s
e
m
o
r
e
th
an
1
0
0
0
s
en
te
n
ce
s
p
er
s
ec
o
n
d
at
9
2
.
2
%
u
n
lab
eled
attac
h
m
en
t
s
co
r
e
o
n
t
h
e
E
n
g
li
s
h
P
e
n
n
T
r
ee
b
an
k
,
w
h
ich
ma
k
e
i
t s
u
itab
le
f
o
r
o
u
r
n
ee
d
s
in
th
is
w
o
r
k
.
3)
No
u
n
P
h
r
ase
B
o
u
n
d
ar
y
(
NP
B
T
)
T
ag
g
i
n
g
I
n
th
is
s
tep
,
w
e
u
s
ed
a
r
u
le
-
b
ased
tag
g
i
n
g
ap
p
r
o
ac
h
to
ta
g
w
o
r
d
s
w
it
h
th
r
ee
p
o
s
s
ib
le
No
u
n
P
h
r
ase
B
o
u
n
d
ar
y
(
NP
B
)
T
ag
s
,
th
ese
t
h
r
ee
tag
s
w
o
u
ld
b
e
u
s
ed
later
t
o
d
eter
m
i
n
e
th
e
b
o
u
n
d
ar
ies o
f
th
e
n
o
u
n
p
h
r
ases
:
a.
"
SE
"
(
Star
t o
f
E
n
tit
y
)
: t
h
e
tag
g
ed
w
o
r
d
is
t
h
e
f
ir
s
t
w
o
r
d
in
a
n
o
u
n
p
h
r
ase.
b.
"
I
E
"
(
I
n
E
n
tit
y
)
:
t
h
e
tag
g
ed
wo
r
d
is
p
ar
t
o
f
a
n
o
u
n
p
h
r
ase
(
b
u
t s
h
o
u
ld
n
o
t b
e
th
e
f
ir
s
t
w
o
r
d
in
it).
c.
"
O
"
(
Ou
t)
:
th
e
tag
g
ed
w
o
r
d
co
u
ld
n
o
t b
e
p
ar
t o
f
a
n
o
u
n
p
h
r
a
s
e.
Ou
r
s
y
s
te
m
u
s
e
s
1
8
r
u
les
to
tag
th
e
w
o
r
d
s
w
it
h
th
e
s
e
th
r
e
e
NP
B
tag
s
.
T
h
e
lef
t
s
id
e
o
f
ea
ch
r
u
le
r
ep
r
esen
ts
it
s
co
n
te
x
t
u
al
co
n
d
itio
n
s
.
W
e
d
escr
ib
e
th
e
co
n
te
x
t
b
y
t
h
e
m
o
r
p
h
o
lo
g
ical,
s
y
n
t
ac
tical
tag
s
f
o
r
t
h
e
r
elate
d
w
o
r
d
s
an
d
th
e
la
s
t
t
h
r
e
e
m
en
ti
o
n
ed
n
o
u
n
p
h
r
ase
b
o
u
n
d
ar
ies
’
ta
g
s
.
W
h
en
a
n
y
s
eq
u
en
ce
o
f
w
o
r
d
s
in
t
h
e
tex
t
s
at
is
f
y
t
h
e
co
n
te
x
t
u
al
co
n
d
itio
n
o
f
a
r
u
le,
w
e
ap
p
l
y
th
e
s
et
o
f
ch
a
n
g
es
i
n
n
o
u
n
p
h
r
a
s
e
b
o
u
n
d
ar
ies
’
tag
s
d
ef
in
ed
i
n
th
e
r
i
g
h
t
s
id
e
o
f
th
e
r
u
le.
E
x
a
m
p
le
:
I
n
th
e
f
o
llo
w
in
g
r
u
le
:
"
L
e
m
m
a=
o
f
@
0
#
NP
B
T
=O
!
@
-
1#
NP
B
T
=O
!
@
1
=>
NPB
T
=I
E
@
0
"
th
e
co
n
tex
t
u
al
co
n
d
itio
n
o
f
t
h
is
r
u
le
i
s
(
L
e
m
m
a=
o
f
@
0
#
NP
B
T
=O
!
@
-
1
#
NP
B
T
=O
!
@
1
)
w
h
ic
h
m
ea
n
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
p
h
o
r
a
R
eso
lu
tio
n
i
n
B
u
s
in
ess
P
r
o
ce
s
s
R
eq
u
ir
eme
n
t E
n
g
i
n
ee
r
in
g
(
R
ia
d
S
o
n
b
o
l
)
1769
a.
L
e
m
m
a=
o
f
@
0
: th
e
le
m
m
a
o
f
t
h
e
w
o
r
d
in
t
h
e
p
o
s
itio
n
ze
r
o
is
"
o
f
"
.
b.
NP
B
T
=O
!
@
-
1
:
th
e
NP
B
tag
is
n
o
t
O
(
!
m
ea
n
s
a
n
eg
at
iv
e
c
o
n
d
itio
n
)
in
th
e
p
r
ev
io
u
s
w
o
r
d
(
s
in
ce
@
-
1
m
ea
n
s
"
at
th
e
in
d
e
x
-
1
"
)
c.
NP
B
T
=O
!
@
1
: th
e
NP
B
tag
is
n
o
t O
in
t
h
e
n
e
x
t
w
o
r
d
(
s
in
ce
@
+
1
m
ea
n
"
at
th
e
in
d
ex
+
1
"
)
T
h
e
r
esu
lt
w
o
u
ld
b
e
tag
g
in
g
t
h
e
w
o
r
d
at
p
o
s
itio
n
0
in
th
e
tar
g
et
co
n
tex
t
w
i
th
t
h
e
ta
g
(
I
E
)
.
4)
C
o
n
ce
p
ts
Dete
ct
io
n
I
n
th
i
s
s
tep
,
w
e
s
ca
n
th
e
tex
t
to
ex
tr
ac
t
t
h
e
n
o
u
n
p
h
r
ases
u
s
i
n
g
t
h
e
r
esu
lt
o
f
NP
B
-
tag
g
er
.
A
n
y
s
eq
u
en
ce
w
o
r
d
s
w
it
h
ta
g
s
SE
an
d
I
E
r
ep
r
esen
ts
a
p
o
s
s
ib
le
co
n
ce
p
t
.
A
n
ap
h
o
r
a
ca
s
es
s
u
ch
as
"
He
"
,
o
r
"
Sh
e"
ar
e
co
n
s
id
er
ed
as
p
o
s
s
ib
le
co
n
ce
p
ts
i
n
t
h
e
la
s
t
ta
g
g
in
g
s
te
p
.
T
o
d
is
tin
g
u
i
s
h
b
et
w
ee
n
t
h
e
o
cc
u
r
r
en
ce
o
f
th
e
s
a
m
e
p
r
o
n
o
u
n
i
n
d
i
f
f
er
e
n
t
s
e
n
ten
ce
s
w
e
ad
d
a
lo
ca
tio
n
s
u
f
f
i
x
to
ea
c
h
an
ap
h
o
r
a
w
h
e
n
ex
tr
ac
ti
n
g
i
t
as
a
p
o
s
s
ib
le
co
n
ce
p
t
in
th
is
s
ta
g
e.
Fo
r
ex
a
m
p
le,
if
w
e
h
a
v
e
t
h
e
p
r
o
n
o
u
n
"
h
e"
as
a
th
ir
d
w
o
r
d
in
t
h
e
s
ec
o
n
d
s
en
te
n
ce
w
e
ad
d
th
e
co
n
ce
p
t
h
e_
2
_
3
w
h
er
e
2
_
3
is
th
e
lo
ca
tio
n
p
r
ef
i
x
.
I
n
t
h
is
w
a
y
,
ea
c
h
p
r
o
n
o
u
n
w
o
u
ld
b
e
s
to
r
ed
as
a
d
is
tin
ct
co
n
ce
p
t
e
v
en
i
f
m
o
r
e
t
h
a
n
o
n
e
p
r
o
n
o
u
n
r
ef
er
to
th
e
s
a
m
e
n
a
m
ed
en
tit
y
.
L
ater
,
w
e
w
ill
r
eso
lv
e
th
e
s
e
an
ap
h
o
r
a
ca
s
es a
n
d
m
er
g
e
s
u
c
h
ca
s
e
s
.
5)
A
lia
s
Dete
ctio
n
So
m
e
co
n
ce
p
t
s
co
u
ld
ap
p
ea
r
in
d
if
f
er
e
n
t
f
o
r
m
s
in
t
h
e
te
x
t
.
I
n
t
h
is
s
tep
,
w
e
m
er
g
e
al
l
o
f
t
h
ese
p
o
s
s
ib
le
co
n
ce
p
ts
i
n
o
n
e
co
n
ce
p
t.
T
o
d
o
so
,
w
e
d
etec
t
t
h
e
p
o
s
s
ib
le
m
er
g
es
b
y
ch
ec
k
i
n
g
i
f
a
n
y
o
f
th
e
p
o
s
s
ib
le
co
n
ce
p
ts
is
an
e
n
d
in
g
f
o
r
an
o
th
er
p
o
s
s
i
b
le
co
n
ce
p
t
(
r
eg
ar
d
less
o
f
th
e
m
o
r
p
h
o
lo
g
ical
c
h
an
g
es)
.
F
o
r
ex
a
m
p
le
,
"
r
esp
o
n
s
e
co
m
m
e
n
t"
an
d
"
th
e
co
m
m
en
t"
r
ep
r
esen
t
a
p
o
s
s
ib
le
m
er
g
e
s
i
n
ce
t
h
e
s
ec
o
n
d
c
o
n
ce
p
t
i
s
a
n
en
d
in
g
f
o
r
th
e
f
ir
s
t
o
n
e.
P
r
ac
tically
,
w
e
f
o
u
n
d
th
a
t
t
h
is
h
e
u
r
is
tic
is
s
u
f
f
icie
n
t
to
d
etec
t
th
e
p
o
s
s
ib
le
m
er
g
e
s
,
b
u
t
r
ar
e
l
y
t
h
er
e
ar
e
ca
s
e
s
w
h
er
e
u
s
er
s
u
s
e
co
m
p
let
el
y
d
if
f
er
e
n
t
w
o
r
d
s
(
s
y
n
o
n
y
m
s
)
to
ex
p
r
ess
t
h
e
s
a
m
e
co
n
ce
p
t
w
h
e
n
d
escr
ib
in
g
a
b
u
s
i
n
ess
p
r
o
ce
s
s
.
W
h
en
w
e
f
i
n
d
t
w
o
p
o
s
s
ib
le
m
er
g
e
s
s
u
ch
as
th
e
ca
s
e
o
f
"
d
o
cu
m
e
n
t"
in
[
"d
o
cu
m
en
t"
,
"
co
n
f
ir
m
atio
n
d
o
cu
m
e
n
t"
]
,
[
"d
o
cu
m
en
t"
,
"
r
e
j
ec
tio
n
d
o
cu
m
en
t"
]
,
w
e
ch
o
o
s
e
t
h
e
n
ea
r
es
t
co
n
ce
p
t
to
m
er
g
e
w
it
h
,
i
n
ter
m
s
o
f
n
u
m
b
er
o
f
wo
r
d
s
b
etw
ee
n
ea
ch
o
f
th
e
s
e
t
w
o
co
n
ce
p
ts
.
Af
ter
m
er
g
i
n
g
co
n
ce
p
ts
,
w
e
co
n
s
id
er
th
e
lo
n
g
e
s
t
s
tr
i
n
g
(
in
ter
m
s
o
f
n
u
m
b
er
o
f
w
o
r
d
s
)
as
a
m
ai
n
co
n
ce
p
t,
an
d
w
e
co
n
s
id
er
all
o
th
er
s
tr
i
n
g
s
a
s
alia
s
es.
T
h
e
m
ai
n
co
n
ce
p
t
w
o
u
ld
b
e
u
s
e
d
w
h
en
b
u
ild
i
n
g
t
h
e
m
o
d
el
w
h
e
n
ev
er
an
y
o
f
t
h
e
aliases
w
er
e
u
s
ed
.
A
s
n
o
tes,
th
i
s
s
tep
d
o
es
n
o
t
co
v
er
d
etec
tin
g
an
ap
h
o
r
a
aliase
s
s
in
ce
t
h
ese
a
n
ap
h
o
r
as h
a
v
e
n
o
t
b
ee
n
r
eso
l
v
ed
y
et.
6)
R
elatio
n
s
h
ip
Gen
er
atio
n
:
Af
ter
ex
tr
ac
t
in
g
th
e
co
n
ce
p
ts
f
r
o
m
t
h
e
tex
t,
w
e
n
ee
d
to
co
n
n
ec
t
th
e
m
b
y
s
e
m
a
n
tica
ll
y
r
el
atio
n
s
h
ip
.
T
o
d
o
th
at
w
e
ad
d
f
o
u
r
k
in
d
s
o
f
r
elatio
n
s
h
ip
s
b
et
w
ee
n
co
n
ce
p
ts
:
a.
I
f
a
co
n
ce
p
t
X
s
tar
ts
w
it
h
a
co
n
ce
p
t
Y,
w
e
ad
d
a
r
elatio
n
s
h
ip
f
r
o
m
X
to
Y,
f
o
r
ex
a
m
p
le:
"
A
C
o
n
f
ir
m
atio
n
"
an
d
"
C
o
n
f
ir
m
atio
n
Do
c
u
m
e
n
t
"
,
th
e
lab
el
o
f
th
is
r
elatio
n
s
h
ip
is
"
r
elate
d
to
".
b.
B
y
c
h
ec
k
in
g
t
h
e
d
ep
en
d
en
c
y
tr
ee
(
th
e
o
u
tp
u
t
o
f
s
y
n
tact
ic
an
al
y
s
is
)
,
I
f
t
h
er
e
is
a
v
er
b
co
n
n
ec
ti
n
g
t
w
o
co
n
ce
p
ts
u
s
i
n
g
s
u
b
j
ec
t
an
d
o
b
j
ec
t
d
ep
en
d
en
cy
r
elatio
n
s
h
ip
s
,
w
e
cr
ea
te
a
r
elatio
n
b
et
w
ee
n
t
h
e
m
lab
eled
b
y
th
e
v
er
b
.
W
e
co
n
s
id
er
a
v
er
b
is
co
n
n
ec
ti
n
g
t
w
o
co
n
ce
p
ts
i
f
it
co
n
n
ec
t
s
an
y
w
o
r
d
f
r
o
m
t
h
e
f
ir
s
t
co
n
ce
p
t
w
it
h
a
n
y
w
o
r
d
f
r
o
m
th
e
s
ec
o
n
d
o
n
e.
Her
e
w
e
d
i
f
f
er
b
et
w
e
en
t
w
o
t
y
p
es
o
f
co
n
n
ec
tio
n
s
:
th
e
v
er
b
h
a
s
a
r
elatio
n
to
t
w
o
d
if
f
er
en
t
co
n
ce
p
ts
,
th
er
e
is
a
r
elatio
n
f
r
o
m
t
h
e
f
ir
s
t
co
n
ce
p
t
to
th
e
v
er
b
,
an
d
a
r
elat
io
n
f
r
o
m
th
is
v
er
b
to
an
o
th
er
co
n
ce
p
t.
I
n
b
o
th
ca
s
es,
o
u
r
p
r
o
ce
s
s
i
n
g
d
ea
l
w
it
h
co
n
j
u
n
c
tio
n
ca
s
e
s
u
ch
a
s
:
X
ca
n
ac
ce
p
t
o
r
r
ej
e
ct
Y"
,
"
X
p
r
o
ce
s
s
Y
an
d
Z
.
"
,
"
X
an
d
Y
P
r
o
ce
s
s
X".
c.
I
f
th
er
e
i
s
a
d
ep
en
d
en
c
y
r
ela
tio
n
s
h
ip
b
et
w
ee
n
a
n
y
t
w
o
co
n
ce
p
ts
,
w
e
r
e
f
lect
it
a
s
a
r
el
atio
n
s
h
ip
in
th
e
co
n
ce
p
t
m
ap
,
w
e
lab
el
t
h
is
r
el
atio
n
s
h
ip
b
y
th
e
n
a
m
e
o
f
t
h
e
d
ep
en
d
en
c
y
+
t
h
e
s
p
ec
i
f
ied
s
tr
i
n
g
i
f
e
x
is
t.
3.
2
.
Ana
ph
o
ra
re
s
o
lv
er
W
e
r
eso
lv
e
an
ap
h
o
r
a
u
s
in
g
t
h
e
co
n
ce
p
ts
an
d
t
h
e
r
elatio
n
s
h
ip
s
w
h
ic
h
h
av
e
b
ee
n
e
x
tr
ac
t
ed
till
n
o
w
.
Fig
u
r
e
1
r
ep
r
esen
t
s
t
h
e
r
e
s
u
l
t
o
f
ap
p
l
y
i
n
g
t
h
e
la
s
t
s
tep
s
o
n
t
h
e
f
o
llo
w
in
g
p
r
o
ce
s
s
:
"
F
ir
s
t,
t
h
e
Ma
n
a
g
er
ch
ec
ks
th
e
o
p
en
lea
d
s
.
A
fter
w
a
r
d
s
,
h
e
s
elec
ts
th
e
to
p
five
o
n
es.
H
e
th
en
tells
h
is
S
a
les
A
s
s
is
ta
n
t
to
ca
ll
th
e
co
n
ta
ct
p
ers
o
n
o
f
th
e
lea
d
s
.
Th
e
S
a
les
A
s
s
is
ta
n
t
ca
lls
ea
ch
cu
s
to
mer
.
I
f
s
o
meo
n
e
is
in
teres
ted
,
h
e
s
en
d
s
a
n
o
te
to
th
e
Ma
n
a
g
er.
Th
e
Ma
n
a
g
er th
en
p
r
o
ce
s
s
es th
e
lea
d
.
Oth
erw
is
e,
h
e
p
h
o
n
e
s
th
e
n
ex
t c
u
s
to
mer."
T
h
e
last
co
n
ce
p
t
m
ap
co
n
tain
s
6
an
ap
h
o
r
as:
h
e_
2
,
h
e_
3
,
h
e_
5
,
h
e_
7
,
o
n
es_
2
,
an
d
s
o
m
e
o
n
e_
5
.
T
h
e
a
ttach
ed
s
u
f
f
i
x
(
s
u
c
h
as
_
2
an
d
_
7
)
d
ef
in
e
an
ap
h
o
r
a
'
s
lo
ca
ti
o
n
in
th
e
te
x
t
(
h
e_
2
r
ef
er
s
to
t
h
e
"
h
e"
o
cc
u
r
r
in
g
i
n
th
e
s
ec
o
n
d
s
e
n
ten
ce
,
w
h
ile
h
e
_
7
r
ef
er
s
to
its
o
cc
u
r
r
en
ce
in
s
en
te
n
ce
7
)
.
Fo
r
ea
ch
an
ap
h
o
r
a,
w
e
co
n
s
id
er
all
p
r
ev
io
u
s
co
n
ce
p
ts
,
i
n
ter
m
s
o
f
th
e
ir
o
cc
u
r
r
en
ce
in
t
h
e
te
x
t,
as
a
p
o
s
s
ib
le
r
eso
lv
er
.
Ou
r
o
b
j
ec
tiv
e
in
th
i
s
s
tep
w
o
u
ld
b
e
r
an
k
in
g
t
h
ese
p
o
s
s
i
b
le
co
n
ce
p
ts
an
d
c
h
o
o
s
i
n
g
th
e
m
o
s
t
s
u
itab
le
o
n
e.
W
e
d
o
th
a
t
b
y
co
m
p
ar
i
n
g
th
e
co
n
tex
t
o
f
t
h
e
a
n
ap
h
o
r
a
an
d
th
e
co
n
tex
t
o
f
ea
c
h
p
o
s
s
ib
l
e
co
n
ce
p
t.
T
h
e
co
n
te
x
t
co
u
l
d
b
e
ac
h
iev
ed
b
y
co
n
s
id
er
in
g
co
n
ce
p
ts
'
p
o
s
itio
n
in
t
h
e
co
n
ce
p
t
m
ap
i.e
.
its
in
-
r
elatio
n
s
h
ip
s
(
r
elatio
n
s
f
r
o
m
o
th
er
n
o
d
es)
,
an
d
o
u
t
-
r
elatio
n
s
h
ip
s
(
r
elatio
n
s
to
o
th
er
n
o
d
es)
.
Fo
r
ex
a
m
p
le,
th
e
co
n
tex
t
o
f
"
h
e_
7
"
co
u
ld
b
e
d
ef
in
ed
b
y
it
s
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.
8
,
No
.
3
,
J
u
n
e
201
8
:
1
7
6
6
–
1773
1770
r
elatio
n
w
it
h
"
cu
s
to
m
er
"
n
o
d
e:
it
is
th
e
o
n
e
w
h
o
"
p
h
o
n
es
"
th
e
"
cu
s
to
m
er
"
.
I
n
th
e
s
a
m
e
w
a
y
,
"
h
e
-
5
"
is
a
co
n
ce
p
t
w
h
ic
h
"
s
en
d
"
a
"
n
o
te
"
,
an
d
th
e
o
n
e
w
h
o
"
s
en
d
s
t
h
to
"
th
e
"
m
an
a
g
er
"
.
Fig
u
r
e
1
.
s
a
m
p
le
o
u
tp
u
t o
f
ap
p
l
y
i
n
g
i
n
itia
l c
o
n
ce
p
t
m
ap
g
e
n
e
r
atio
n
s
tag
e
W
e
g
iv
e
ea
ch
p
o
s
s
ib
le
co
n
ce
p
t a
s
co
r
e
f
o
r
b
ein
g
a
r
eso
lv
er
f
o
r
th
e
an
ap
h
o
r
a
in
t
h
e
f
o
llo
w
i
n
g
w
a
y
:
(
)
(
)
i.e
.
w
e
ca
lc
u
late
t
h
e
s
i
m
i
lar
it
y
b
et
w
ee
n
ea
c
h
r
elatio
n
s
h
ip
co
n
n
ec
ted
w
it
h
t
h
e
an
ap
h
o
r
a
in
co
n
ce
p
t
m
ap
,
an
d
ea
ch
r
elatio
n
co
n
n
ec
ted
w
it
h
th
e
co
n
ce
p
t
w
e
w
an
t
to
r
an
k
.
T
h
en
th
e
s
co
r
e
o
f
th
is
co
n
ce
p
t
w
o
u
ld
b
e
th
e
m
a
x
s
co
r
e
w
e
f
in
d
b
et
w
ee
n
a
n
y
t
wo
r
elatio
n
s
.
T
h
e
s
i
m
ilar
it
y
b
et
w
ee
n
t
w
o
r
el
atio
n
s
h
ip
s
i
n
th
e
co
n
ce
p
t
m
ap
w
o
u
ld
b
e
ca
lcu
lated
as
f
o
llo
w
i
n
g
:
a.
I
f
r
el1
is
a
n
in
-
r
elatio
n
f
o
r
th
e
co
n
ce
p
t a
n
d
r
el2
is
an
o
u
t
-
r
ela
tio
n
f
o
r
th
e
a
n
ap
h
o
r
a
b.
(
)
Sin
ce
t
h
ese
t
w
o
r
elatio
n
s
ar
e
n
o
co
m
p
atib
le
in
ter
m
o
f
d
ir
ec
ti
o
n
.
c.
I
f
r
el1
is
a
n
o
u
t
-
r
elatio
n
f
o
r
th
e
co
n
ce
p
t a
n
d
r
el2
is
an
i
n
-
r
elatio
n
f
o
r
th
e
a
n
ap
h
o
r
a
(
)
Sin
ce
t
h
ese
t
w
o
r
elatio
n
s
ar
e
n
o
co
m
p
atib
le
in
ter
m
o
f
d
ir
ec
ti
o
n
.
d.
I
f
r
el1
is
a
n
in
-
r
elatio
n
f
o
r
th
e
co
n
ce
p
t a
n
d
r
el2
is
an
i
n
-
re
lati
o
n
f
o
r
th
e
an
ap
h
o
r
a
(
)
(
)
(
)
s
in
ce
b
o
th
r
elatio
n
s
ar
e
in
-
r
ela
tio
n
s
,
w
e
s
h
o
u
ld
co
n
s
id
er
th
e
s
o
u
r
ce
an
d
th
e
lab
el
o
f
ea
ch
o
f
th
e
m
.
W
u
_
P
s
i
m
alr
it
y
(
o
r
Wu
-
P
al
m
er
s
i
m
i
lar
it
y
)
i
s
o
n
e
o
f
t
h
e
c
o
m
m
o
n
w
o
r
d
Net
-
b
ased
s
e
m
a
n
tic
s
i
m
ilar
it
y
[
3
2
]
w
h
ic
h
ch
ec
k
t
h
e
s
i
m
ilar
it
y
b
et
w
ee
n
t
w
o
s
tr
i
n
g
s
,
it
g
i
v
e
s
s
i
m
ilar
it
y
o
n
a
[
0
,
1
]
s
ca
le
r
ef
lectin
g
th
e
m
i
n
i
m
u
m
d
is
ta
n
ce
b
et
w
ee
n
a
n
y
t
w
o
s
y
n
s
ets
o
f
t
w
o
g
i
v
en
co
n
ce
p
ts
i
n
W
o
r
d
Net.
e.
I
f
r
el1
is
a
n
o
u
t
-
r
elatio
n
f
o
r
th
e
co
n
ce
p
t a
n
d
r
el2
is
an
o
u
t
-
r
e
latio
n
f
o
r
th
e
a
n
ap
h
o
r
a
(
)
(
)
(
)
s
in
ce
b
o
th
r
elatio
n
s
ar
e
o
u
t
-
r
el
atio
n
s
,
w
e
s
h
o
u
ld
co
n
s
id
er
th
e
tar
g
et
an
d
th
e
lab
el
o
f
ea
c
h
o
f
th
e
m
Af
ter
ap
p
l
y
i
n
g
t
h
e
la
s
t
ca
lc
u
l
atio
n
s
,
w
e
ch
o
o
s
e
th
e
co
n
ce
p
t
w
it
h
m
ax
ac
o
r
e.
W
h
en
t
w
o
co
n
ce
p
ts
h
a
v
e
t
h
e
s
a
m
e
s
co
r
e,
w
e
ch
o
o
s
e
t
h
e
clo
s
est o
n
e
to
th
e
a
n
ap
h
o
r
a.
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
p
h
o
r
a
R
eso
lu
tio
n
i
n
B
u
s
in
ess
P
r
o
ce
s
s
R
eq
u
ir
eme
n
t E
n
g
i
n
ee
r
in
g
(
R
ia
d
S
o
n
b
o
l
)
1771
E
x
ce
p
tio
n
al
C
a
s
es:
I
n
ad
d
itio
n
to
th
e
p
r
ev
io
u
s
ca
l
cu
latio
n
s
,
w
e
ad
d
ed
th
ese
t
w
o
h
eu
r
i
s
tics
:
a.
I
f
th
er
e
is
a
s
e
m
a
n
tic
r
elatio
n
b
et
w
ee
n
th
e
an
ap
h
o
r
a
an
d
a
p
o
s
s
ib
le
co
n
ce
p
t,
w
e
ex
cl
u
d
e
th
is
co
n
ce
p
t
f
r
o
m
th
e
p
o
s
s
ib
le
r
eso
lv
er
b
y
g
i
v
in
g
it a
n
eg
ati
v
e
p
r
o
b
ab
ilit
y
.
b.
I
f
th
er
e
is
a
p
r
ev
io
u
s
an
ap
h
o
r
a
w
h
ic
h
eq
u
al
th
e
c
u
r
r
en
t a
n
ap
h
o
r
a
lex
icall
y
,
w
e
m
u
ltip
l
y
it
s
s
co
r
e
b
y
t
w
o
.
5.
RE
SU
L
T
AND
DI
SCUS
SI
O
N
T
o
ev
alu
ate
o
u
r
w
o
r
k
,
w
e
u
s
e
d
th
e
d
atase
t
co
llected
b
y
[
7
]
.
W
e
d
ec
id
ed
to
u
s
e
t
h
i
s
d
ataset
s
i
n
ce
:
(
1
)
it
is
t
h
e
b
est
d
atase
t
w
e
k
n
o
w
i
n
t
h
i
s
d
o
m
ai
n
in
ter
m
s
o
f
its
s
ize
a
n
d
v
ar
iet
y
,
a
s
it
co
n
s
i
s
ts
o
f
4
7
tex
t
u
al
p
r
o
ce
s
s
d
escr
ip
tio
n
s
(
in
to
tal,
4
3
2
s
en
ten
ce
s
)
co
llected
f
r
o
m
d
if
f
er
e
n
t
s
o
u
r
ce
s
(
ac
ad
e
m
i
c
an
d
in
d
u
s
tr
y
)
a
n
d
f
r
o
m
d
i
f
f
er
e
n
t
d
o
m
ai
n
s
(
co
m
p
u
ter
,
h
o
tels
,
m
a
n
u
f
ac
t
u
r
i
n
g
,
HR
.
.
.
)
.
(
2
)
w
e
ca
n
co
m
p
ar
e
o
u
r
r
esu
lt
s
w
it
h
t
h
e
r
esu
lt
s
o
f
Frie
d
r
ich
AR
w
h
ic
h
is
d
esig
n
ed
s
p
ec
i
f
icall
y
f
o
r
th
i
s
d
o
m
ain
,
a
s
a
p
ar
t o
f
o
n
e
o
f
t
h
e
b
est
-
k
n
o
w
n
tex
t
-
to
-
m
o
d
el
s
y
s
te
m
s
ac
co
r
d
in
g
t
o
[
2
6
]
.
Mo
r
e
o
v
er
,
w
e
ca
n
co
m
p
ar
e
o
u
r
r
es
u
lt
s
w
i
th
t
w
o
g
en
er
ic
AR
s
y
s
te
m
s
:
B
A
R
T
an
d
th
e
R
ec
o
n
cile
.
Ou
r
ap
p
r
o
ac
h
w
as
ab
le
to
r
e
s
o
lv
e
m
o
r
e
th
a
n
7
3
%
o
f
an
a
p
h
o
r
as
co
r
r
ec
tly
,
w
h
ich
o
u
tp
er
f
o
r
m
t
h
e
r
esu
lt
s
o
f
Fri
ed
r
ich
[
7
]
w
h
ic
h
r
ea
ch
ed
ab
o
u
t
6
3
%
w
h
en
u
s
in
g
t
h
e
s
a
m
e
d
ataset.
I
n
ad
d
itio
n
,
it
clea
r
l
y
o
u
tp
er
f
o
r
m
s
B
A
R
T
an
d
R
ec
o
n
cile
s
y
s
te
m
s
i
n
th
e
d
o
m
a
i
n
o
f
b
u
s
in
e
s
s
p
r
o
ce
s
s
r
eq
u
ir
e
m
en
t
en
g
i
n
ee
r
in
g
:
ac
co
r
d
in
g
to
[
7
]
,
th
ese
t
w
o
g
en
er
ic
A
R
s
y
s
te
m
s
w
er
e
n
o
t
ab
le
to
co
r
r
ec
tly
id
e
n
ti
f
y
m
o
r
e
th
a
n
4
2
%
i
n
t
h
is
d
ataset: B
E
R
T
ca
n
r
eso
lv
e
o
n
l
y
4
1
.
4
4
% o
f
th
e
ca
s
e
s
o
n
t
h
e
s
a
m
e
d
ataset,
w
h
ile
R
ec
o
n
cile
ca
n
r
eso
lv
e
3
9
.
6
4
%
co
r
r
ec
tly
.
O
f
co
u
r
s
e,
t
h
ese
r
e
s
u
lts
co
u
ld
n
o
t
b
e
g
e
n
er
alize
d
to
o
th
er
d
o
m
ai
n
s
s
in
ce
B
AR
T
an
d
t
h
e
R
ec
o
n
cile
ar
e
g
en
er
ic
A
R
s
y
s
te
m
s
.
T
h
e
f
o
llo
w
i
n
g
tab
le
s
u
m
m
ar
izes t
h
e
r
esu
lts
:
T
ab
le
1
.
A
cc
u
r
ac
y
o
f
t
h
e
f
o
u
r
AR
s
y
s
te
m
s
O
u
r
A
p
p
r
o
a
c
h
F
r
i
e
d
r
i
c
h
B
A
R
T
R
e
c
o
n
c
i
l
e
#
o
f
r
e
f
1
1
1
1
1
1
1
1
1
1
1
1
R
e
so
l
v
e
d
C
o
r
r
e
c
t
l
y
82
70
46
44
A
c
c
u
r
a
c
y
7
3
.
8
7
%
6
3
.
0
6
%
4
1
.
4
4
%
3
9
.
6
4
%
T
h
e
u
s
ag
e
o
f
t
h
e
co
n
ce
p
t
m
ap
w
a
s
th
e
k
e
y
ad
v
a
n
ta
g
e
in
o
u
r
ap
p
r
o
ac
h
co
m
p
ar
in
g
to
o
th
er
w
o
r
k
s
.
I
n
m
an
y
ca
s
e
s
,
an
ap
h
o
r
a
co
u
ld
n
o
t
b
e
r
eso
lv
ed
in
its
n
ar
r
o
w
co
n
tex
t,
it
co
u
ld
b
e
r
eso
lv
ed
o
n
l
y
w
h
e
n
co
n
n
ec
ti
n
g
th
e
co
n
ce
p
ts
w
it
h
all
r
elate
d
p
r
o
p
er
ties
an
d
all
o
f
its
s
e
m
a
n
tic
r
elatio
n
s
in
t
h
e
w
h
o
le
te
x
t
,
th
e
e
f
f
ec
t
o
f
th
i
s
k
in
d
o
f
p
r
o
ce
s
s
in
g
b
ec
o
m
e
clea
r
er
w
h
en
d
ea
li
n
g
w
it
h
in
ter
-
s
en
te
n
tial
an
ap
h
o
r
a
w
h
e
n
th
e
an
ap
h
o
r
a
an
d
th
e
r
elate
d
r
eso
lv
er
ar
e
lo
ca
ted
in
t
w
o
d
if
f
er
en
t
s
e
n
te
n
ce
s
.
Ou
r
s
tatis
t
ics
s
h
o
w
t
h
at
o
u
r
ap
p
r
o
ac
h
g
i
v
es
co
r
r
ec
t
r
esu
lt
s
1
.
2
5
tim
e
s
b
etter
th
an
Frie
d
r
ich
ap
p
r
o
ac
h
in
in
t
e
r
-
s
en
ten
tial
an
ap
h
o
r
a
ca
s
es
,
w
h
i
le
it
g
iv
es
th
e
co
r
r
ec
t
an
s
w
er
1
.
0
8
ti
m
es b
etter
in
t
h
e
ca
s
e
o
f
in
tr
a
-
s
en
te
n
tial
.
Ta
b
le
2
.
C
o
m
p
ar
in
g
t
h
e
ac
cu
r
ac
y
b
et
w
ee
n
in
tr
a
-
s
e
n
ten
tial
a
n
d
in
t
er
-
s
en
te
n
tial
a
n
ap
h
o
r
a
O
u
r
A
p
p
r
o
a
c
h
F
r
i
e
d
r
i
c
h
I
mp
r
o
v
e
me
n
t
i
n
t
r
a
-
se
n
t
e
n
t
i
a
l
c
a
se
s
8
2
.
2
%
7
5
.
6
%
1
.
0
8
i
n
t
er
-
se
n
t
e
n
t
i
a
l
c
a
se
s
6
8
.
2
%
5
4
.
5
%
1
.
2
5
T
ab
le
2
s
h
o
w
h
o
w
ac
c
u
r
ac
y
o
f
b
o
th
s
y
s
te
m
s
(
Frie
d
r
ich
a
n
d
o
u
r
ap
p
r
o
ac
h
)
ch
an
g
e
d
ep
en
d
in
g
o
n
an
ap
h
o
r
a
t
y
p
e,
th
e
f
ir
s
t
t
w
o
co
lu
m
n
s
s
h
o
w
t
h
e
ac
cu
r
ac
y
o
f
b
o
th
s
y
s
te
m
s
i
n
ea
ch
t
y
p
e,
an
d
th
e
la
s
t
co
lu
m
n
ca
lc
u
late
i
m
p
r
o
v
e
m
en
t p
er
ce
n
ta
g
e
(
ex
a
m
p
le:
1
.
2
5
=6
8
.
2
/5
4
.
5
)
.
6.
CO
NCLU
SI
O
N
I
n
t
h
is
p
ap
er
,
w
e
p
r
esen
ted
a
d
o
m
a
in
s
p
ec
i
f
ic
a
n
ap
h
o
r
a
r
eso
l
u
tio
n
s
y
s
te
m
,
f
o
c
u
s
i
n
g
o
n
th
e
d
o
m
ai
n
o
f
b
u
s
i
n
ess
p
r
o
ce
s
s
r
eq
u
ir
e
m
e
n
t
en
g
i
n
ee
r
i
n
g
.
T
h
e
ap
p
r
o
ac
h
d
ea
ls
w
it
h
th
e
te
x
t
a
s
o
n
e
b
lo
ck
,
an
d
g
e
n
er
ates
a
co
n
ce
p
t
m
ap
r
ef
lecti
n
g
t
h
e
co
n
ce
p
ts
an
d
th
e
s
e
m
a
n
tic
r
elati
o
n
s
h
ip
s
in
t
h
e
tex
t.
B
ased
o
n
th
is
m
ap
,
a
s
e
m
an
tic
s
i
m
ilar
it
y
m
ea
s
u
r
e
m
e
n
t
h
as
b
ee
n
p
r
o
p
o
s
ed
to
r
eso
lv
e
r
ef
er
en
ce
s
.
T
h
e
ac
cu
r
ac
y
o
f
o
u
r
s
y
s
te
m
o
u
tp
er
f
o
r
m
s
w
ell
-
k
n
o
w
n
AR
s
y
s
te
m
s
i
n
t
h
is
d
o
m
ai
n
,
u
s
i
n
g
Frie
d
r
ich
d
ataset
[
7
]
,
w
e
r
ea
c
h
ed
m
o
r
e
th
an
7
3
%
ac
cu
r
ac
y
o
u
tp
er
f
o
r
m
i
n
g
s
i
m
ilar
a
p
p
r
o
ac
h
es.
T
h
ese
r
esu
lt
s
en
co
u
r
a
g
e
u
s
to
test
th
i
s
ap
p
r
o
ac
h
in
m
o
r
e
d
o
m
ai
n
s
a
n
d
to
ad
o
p
t
th
e
alg
o
r
ith
m
to
b
e
a
d
o
m
a
in
-
o
r
ien
ted
an
ap
h
o
r
a
r
eso
lu
tio
n
s
y
s
te
m
;
co
n
ce
p
t
m
ap
g
en
er
atio
n
s
h
o
u
ld
b
e
test
ed
in
o
th
er
d
o
m
ai
n
s
to
b
e
s
u
r
e
th
a
t
it
g
i
v
es
g
o
o
d
ac
cu
r
ac
y
in
al
l
d
o
m
ai
n
s
n
o
t
o
n
l
y
i
n
t
h
e
d
o
m
ai
n
w
e
f
o
cu
s
o
n
in
o
u
r
w
o
r
k
.
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.
8
,
No
.
3
,
J
u
n
e
201
8
:
1
7
6
6
–
1773
1772
RE
F
E
R
E
NC
E
S
[1
]
Iid
a
R,
In
u
i
K,
M
a
tsu
m
o
to
Y
,
“
Zero
-
a
n
a
p
h
o
ra
re
so
lu
t
io
n
b
y
lea
rn
in
g
rich
sy
n
tac
ti
c
p
a
tt
e
rn
f
e
a
tu
re
s
”
,
A
CM
T
ra
n
sa
c
ti
o
n
s o
n
A
sia
n
L
a
n
g
u
a
g
e
In
f
o
rm
a
ti
o
n
P
r
o
c
e
ss
in
g
(TAL
IP
)
,
2
0
0
7
De
c
1
,
v
o
l.
6
,
n
o
.
4
,
p
p
.
1
.
[2
]
De
n
b
e
r
M
,
A
u
to
m
a
ti
c
re
so
lu
ti
o
n
o
f
a
n
a
p
h
o
ra
i
n
E
n
g
li
sh
,
Ea
stma
n
Ko
d
a
k
C
o
,
1
9
9
8
Ju
n
3
0
.
[3
]
M
it
k
o
v
R
,
A
n
a
p
h
o
ra
re
so
lu
ti
o
n
,
Ro
u
tl
e
d
g
e
,
2
0
1
4
F
e
b
2
4
.
[4
]
Ak
k
in
e
n
i
H,
L
a
k
sh
m
i
P
V,
Ba
b
u
B
,
“
On
li
n
e
Cro
w
d
s
Op
in
i
o
n
-
M
i
n
in
g
it
to
A
n
a
ly
z
e
Cu
rre
n
t
T
re
n
d
:
A
Re
v
ie
w
”
,
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
E
lec
trica
l
a
n
d
C
o
mp
u
ter
En
g
in
e
e
rin
g
(
IJ
ECE
)
,
2
0
1
5
Oc
t
1
,
v
o
l.
5
,
n
o
.
5
.
[5
]
Kh
a
m
a
y
s
e
h
,
F
a
isa
l
T
,
“
In
f
e
rrin
g
S
tu
d
e
n
t'
s
Ch
a
t
T
o
p
ic
in
Co
ll
o
q
u
i
a
l
A
ra
b
ic
T
e
x
t
u
sin
g
S
e
m
a
n
ti
c
Re
p
re
se
n
tatio
n
”
,
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
E
lec
trica
l
a
n
d
C
o
mp
u
ter
En
g
in
e
e
rin
g
(
IJ
ECE
)
,
v
o
l.
6
,
n
o
.
4
(
2
0
1
6
)
,
1
8
9
7
.
[6
]
Kili
c
o
g
lu
H,
F
isz
m
a
n
M
,
De
m
n
e
r
-
F
u
sh
m
a
n
D
,
“
In
terp
re
ti
n
g
c
o
n
su
m
e
r
h
e
a
lt
h
q
u
e
stio
n
s:
T
h
e
ro
le
o
f
a
n
a
p
h
o
ra
a
n
d
e
ll
ip
sis
”
,
In
P
r
o
c
e
e
d
in
g
s
o
f
th
e
2
0
1
3
W
o
rk
sh
o
p
o
n
Bi
o
me
d
ica
l
Na
tu
r
a
l
L
a
n
g
u
a
g
e
Pro
c
e
ss
in
g
2
0
1
3
.
A
u
g
8
,
p
p
.
5
4
-
62
[7
]
F
ried
rich
F
,
M
e
n
d
li
n
g
J,
P
u
h
l
m
a
n
n
F
,
“
P
r
o
c
e
ss
m
o
d
e
l
g
e
n
e
r
a
ti
o
n
f
ro
m
n
a
tu
ra
l
lan
g
u
a
g
e
tex
t
”
,
In
Ad
v
a
n
c
e
d
In
fo
rm
a
t
io
n
S
y
ste
ms
En
g
in
e
e
rin
g
2
0
1
1
,
p
p
.
4
8
2
-
4
9
6
,
S
p
ri
n
g
e
r
Be
rli
n
/He
id
e
lb
e
rg
.
[8
]
Po
e
sio
M
,
S
t
u
c
k
a
rd
t
R,
V
e
rsle
y
Y
,
A
n
a
p
h
o
ra
Re
so
l
u
ti
o
n
,
S
p
ri
n
g
e
r
,
2
0
1
6
.
[9
]
Ha
g
h
i
g
h
i
A
,
Kle
in
D
,
“
S
im
p
le
c
o
re
fe
re
n
c
e
re
so
lu
ti
o
n
w
it
h
rich
sy
n
tac
ti
c
a
n
d
se
m
a
n
ti
c
fe
a
tu
re
s
”
,
In
P
r
o
c
e
e
d
in
g
s
o
f
th
e
2
0
0
9
C
o
n
fer
e
n
c
e
o
n
Emp
iric
a
l
M
e
th
o
d
s
i
n
N
a
tu
r
a
l
L
a
n
g
u
a
g
e
Pro
c
e
ss
i
n
g
:
Vo
l
u
me
3
-
Vo
l
u
me
3
2
0
0
9
Au
g
6,
p
p
.
1
1
5
2
-
1
1
6
1
.
[1
0
]
M
it
k
o
v
R
“
F
a
c
to
rs
in
a
n
a
p
h
o
ra
re
so
lu
ti
o
n
:
t
h
e
y
a
re
n
o
t
th
e
o
n
ly
th
in
g
s
th
a
t
m
a
tt
e
r:
a
c
a
se
stu
d
y
b
a
se
d
o
n
tw
o
d
if
fe
re
n
t
a
p
p
ro
a
c
h
e
s
”
,
In
P
r
o
c
e
e
d
in
g
s
o
f
a
W
o
rk
sh
o
p
o
n
O
p
e
ra
ti
o
n
a
l
Fa
c
to
rs
i
n
Pra
c
ti
c
a
l,
R
o
b
u
st
An
a
p
h
o
r
a
Res
o
lu
ti
o
n
fo
r Un
re
stric
ted
T
e
x
ts
1
9
9
7
J
u
l
11
,
p
p
.
1
4
-
21
.
[1
1
]
S
o
o
n
W
M
,
Ng
HT
,
L
i
m
DC
,
“
A
m
a
c
h
in
e
lea
rn
in
g
a
p
p
ro
a
c
h
to
c
o
re
f
e
r
e
n
c
e
re
so
lu
ti
o
n
o
f
n
o
u
n
p
h
ra
se
s
”
,
Co
mp
u
t
a
ti
o
n
a
l
li
n
g
u
isti
c
s
,
2
0
0
1
De
c
,
v
o
l.
27
,
n
o
.
4
,
p
p
.
5
2
1
-
5
44
[1
2
]
Ng
V
,
Ca
rd
ie
C
,
“
Im
p
ro
v
in
g
m
a
c
h
in
e
lea
rn
i
n
g
a
p
p
r
o
a
c
h
e
s
to
c
o
r
e
fe
re
n
c
e
re
so
lu
ti
o
n
”
,
In
P
ro
c
e
e
d
i
n
g
s
o
f
th
e
4
0
th
a
n
n
u
a
l
me
e
ti
n
g
o
n
a
ss
o
c
ia
ti
o
n
fo
r co
mp
u
t
a
ti
o
n
a
l
li
n
g
u
isti
c
s 2
0
0
2
J
u
l
6
,
p
p
.
1
0
4
-
1
1
1
.
[1
3
]
W
ise
m
a
n
S
,
Ru
sh
A
M
,
S
h
ieb
e
r
S
M
,
“
L
e
a
rn
in
g
g
lo
b
a
l
fe
a
tu
re
s
f
o
r
c
o
re
f
e
re
n
c
e
re
so
lu
ti
o
n
”
,
a
rX
iv
p
re
p
rin
t
a
rX
iv
:1
6
0
4
.
0
3
0
3
5
.
2
0
1
6
A
p
r
1
1
.
[1
4
]
L
e
e
C,
Ju
n
g
S
,
P
a
rk
CE
,
A
n
a
p
h
o
r
a
R
e
so
lu
ti
o
n
w
it
h
P
o
i
n
ter Ne
tw
o
rk
s
,
P
a
tt
e
rn
Re
c
o
g
n
it
io
n
L
e
tt
e
rs
,
2
0
1
7
M
a
y
1
9
.
[1
5
]
Ha
rd
m
e
ier
C,
Na
k
o
v
P
,
S
ty
m
n
e
S
,
T
i
e
d
e
m
a
n
n
J,
V
e
rsle
y
Y,
Ce
tt
o
lo
M
,
“
P
r
o
n
o
u
n
-
f
o
c
u
se
d
M
T
a
n
d
c
ro
ss
-
li
n
g
u
a
l
p
ro
n
o
u
n
p
re
d
icti
o
n
:
F
i
n
d
i
n
g
s
o
f
th
e
2
0
1
5
Disc
o
M
T
sh
a
re
d
tas
k
o
n
p
r
o
n
o
u
n
tra
n
sla
ti
o
n
”
,
I
n
S
e
c
o
n
d
W
o
rk
sh
o
p
o
n
Disc
o
u
rs
e
in
M
a
c
h
i
n
e
T
ra
n
sla
ti
o
n
(
Disc
o
M
T
),
1
7
S
e
p
tem
b
e
r
2
0
1
5
,
L
isb
o
n
,
P
o
rt
u
g
a
l
2
0
1
5
,
p
p
.
1
-
16
.
[1
6
]
Kili
c
o
g
lu
H,
Ro
se
m
b
l
a
t
G
,
F
isz
m
a
n
M
,
Rin
d
f
les
c
h
T
C
,
“
S
o
rtal
a
n
a
p
h
o
ra
re
so
lu
t
io
n
to
e
n
h
a
n
c
e
re
l
a
ti
o
n
e
x
trac
ti
o
n
f
ro
m
b
io
m
e
d
ica
l
li
tera
tu
re
”
,
BM
C
b
io
in
f
o
rm
a
ti
c
s
,
2
0
1
6
A
p
r
14
,
v
o
l
.
17
,
n
o
.
1
,
p
p
.
1
6
3
.
[1
7
]
Be
ll
D,
Ha
h
n
-
P
o
w
e
ll
G
,
V
a
len
z
u
e
la
-
Esc
á
rc
e
g
a
M
A
,
S
u
rd
e
a
n
u
M
,
“
S
iev
e
-
b
a
se
d
Co
re
f
e
re
n
c
e
R
e
so
lu
ti
o
n
i
n
t
h
e
Bio
m
e
d
ica
l
Do
m
a
in
”
,
a
rX
iv
p
re
p
rin
t
a
r
X
iv
:1
6
0
3
.
0
3
7
5
8
,
2
0
1
6
M
a
r
1
1
.
[1
8
]
Ch
o
i
M
J
,
Co
re
f
e
re
n
c
e
re
so
lu
ti
o
n
f
o
r
b
io
m
e
d
ica
l
p
a
th
w
a
y
d
a
ta
(Do
c
to
ra
l
d
isse
rtatio
n
)
2
0
1
7
.
[1
9
]
L
o
á
icig
a
S
,
Weh
rli
E
,
“
Ru
le
-
b
a
se
d
p
ro
n
o
m
in
a
l
a
n
a
p
h
o
ra
trea
tm
e
n
t
f
o
r
m
a
c
h
in
e
tra
n
sla
ti
o
n
”
,
In
Pr
o
c
e
e
d
in
g
s
o
f
t
h
e
S
e
c
o
n
d
W
o
rk
sh
o
p
o
n
Disc
o
u
rs
e
in
M
a
c
h
i
n
e
T
r
a
n
sl
a
ti
o
n
2
0
1
5
S
e
p
1
7
,
p
p
.
8
6
-
93
,
A
ss
o
c
iatio
n
f
o
r
Co
m
p
u
tatio
n
a
l
L
in
g
u
isti
c
s L
isb
o
n
,
P
o
rt
u
g
a
l
.
[2
0
]
v
a
n
d
e
r
A
a
H,
L
e
o
p
o
ld
H,
Re
ij
e
rs
H
A
,
“
D
e
tec
ti
n
g
in
c
o
n
siste
n
c
ies
b
e
twe
e
n
p
ro
c
e
ss
m
o
d
e
ls
a
n
d
tex
tu
a
l
d
e
sc
rip
ti
o
n
s
”
,
In
In
ter
n
a
ti
o
n
a
l
C
o
n
fer
e
n
c
e
o
n
B
u
sin
e
ss
Pro
c
e
ss
M
a
n
a
g
e
me
n
t
2
0
1
5
A
u
g
3
1
,
p
p
.
9
0
-
1
0
5
,
S
p
r
in
g
e
r,
Ch
a
m
.
[2
1
]
S
c
h
u
m
a
c
h
e
r
P
,
M
i
n
o
r
M
,
S
c
h
u
lt
e
-
Zu
rh
a
u
se
n
E
,
“
Ex
trac
ti
n
g
a
n
d
e
n
rich
in
g
w
o
rk
f
lo
w
s
f
ro
m
tex
t
”
,
In
In
f
o
rm
a
ti
o
n
Reu
se
a
n
d
In
teg
ra
ti
o
n
(
IRI
),
2
0
1
3
IEE
E
1
4
t
h
In
ter
n
a
ti
o
n
a
l
C
o
n
fer
e
n
c
e
o
n
2
0
1
3
Au
g
14
,
p
p
.
2
8
5
-
2
9
2
,
IEE
E
.
[2
2
]
F
a
jar,
A
h
m
a
d
Nu
ru
l,
a
n
d
Im
a
m
M
a
rz
u
k
i
S
h
o
f
i
,
“
G
o
a
l
M
o
d
e
l
to
Bu
sin
e
ss
P
r
o
c
e
ss
M
o
d
e
l:
A
M
e
th
o
d
o
l
o
g
y
f
o
r
En
terp
rise
G
o
v
e
rn
m
e
n
t
T
o
u
rism
S
y
ste
m
D
e
v
e
lo
p
m
e
n
t
”
,
In
ter
n
a
ti
o
n
a
l
J
o
u
r
n
a
l
o
f
El
e
c
t
ric
a
l
a
n
d
Co
mp
u
ter
En
g
i
n
e
e
rin
g
(
IJ
ECE
)
,
v
o
l.
6
,
n
o
.
6
,
2
0
1
6
.
[2
3
]
He
rb
st
J
,
Ka
ra
g
ian
n
is
D
,
“
A
n
in
d
u
c
ti
v
e
a
p
p
ro
a
c
h
to
t
h
e
a
c
q
u
isit
io
n
a
n
d
a
d
a
p
tati
o
n
o
f
w
o
rk
flo
w
m
o
d
e
ls
”
,
In
Pro
c
e
e
d
in
g
s o
f
th
e
IJ
CAI
1
9
9
9
Au
g
,
v
o
l.
9
9
,
p
p
.
5
2
-
57
.
[2
4
]
Blu
m
b
e
rg
R,
A
tr
e
S
,
“
T
h
e
p
ro
b
lem
w
it
h
u
n
stru
c
t
u
re
d
d
a
ta
”
,
Dm
R
e
v
iew
,
2
0
0
3
F
e
b
,
v
o
l.
13
,
42
-
49
,
62
.
[2
5
]
L
a
p
o
rti
V
,
Bo
rg
e
s
M
R,
Bra
g
a
n
h
o
lo
V
,
“
A
th
e
n
a
:
A
c
o
ll
a
b
o
ra
ti
v
e
a
p
p
ro
a
c
h
t
o
re
q
u
irem
e
n
ts
e
li
c
it
a
ti
o
n
”
,
C
o
mp
u
ter
s
in
In
d
u
stry
,
2
0
0
9
A
u
g
3
1
,
v
o
l
.
60
,
n
o
.
6
,
p
p
.
3
6
7
-
3
80
.
[2
6
]
Rief
e
r
M
,
Tern
is
S
F
,
T
h
a
ler
T
,
“
M
in
in
g
p
r
o
c
e
ss
m
o
d
e
ls
f
ro
m
n
a
tu
ra
l
l
a
n
g
u
a
g
e
te
x
t:
A
sta
te
-
of
-
th
e
-
a
rt
a
n
a
l
y
sis
”
,
M
u
lt
iko
n
fer
e
n
z W
irtsc
h
a
f
tsin
f
o
rm
a
ti
k
(
M
KW
I
-
1
6
),
M
a
rc
h
,
p
p
.
9
-
11
[2
7
]
P
i
tt
k
e
F
,
L
e
o
p
o
ld
H,
M
e
n
d
li
n
g
J
,
“
W
h
e
n
lan
g
u
a
g
e
m
e
e
ts
lan
g
u
a
g
e
:
A
n
ti
p
a
tt
e
rn
s
re
su
lt
i
n
g
f
ro
m
m
ix
i
n
g
n
a
tu
ra
l
a
n
d
m
o
d
e
li
n
g
lan
g
u
a
g
e
”
,
In
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
B
u
sin
e
ss
P
ro
c
e
ss
M
a
n
a
g
e
me
n
t
2
0
1
4
S
e
p
7
,
p
p
.
1
1
8
-
1
2
9
,
S
p
rin
g
e
r,
C
h
a
m
.
[2
8
]
V
e
rsle
y
Y,
P
o
n
z
e
tt
o
S
P
,
P
o
e
sio
M
,
Ei
d
e
lm
a
n
V
,
Je
rn
A
,
S
m
it
h
J,
Ya
n
g
X
,
M
o
sc
h
it
ti
A
,
“
BA
R
T
:
A
m
o
d
u
lar
to
o
lk
i
t
f
o
r
c
o
re
f
e
r
e
n
c
e
re
so
lu
ti
o
n
”
,
I
n
P
ro
c
e
e
d
in
g
s
o
f
th
e
4
6
th
An
n
u
a
l
M
e
e
ti
n
g
o
f
t
h
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
Hu
m
a
n
L
a
n
g
u
a
g
e
T
e
c
h
n
o
lo
g
ies
:
De
mo
S
e
ss
io
n
2
0
0
8
J
u
n
1
6
,
p
p
.
9
-
12
,
As
so
c
iatio
n
f
o
r
Co
m
p
u
tatio
n
a
l
L
in
g
u
ist
ics
.
[2
9
]
S
to
y
a
n
o
v
V
,
Ca
rd
ie
C,
G
il
b
e
rt
N,
Ril
o
f
f
E,
Bu
tt
ler
D,
H
y
so
m
D
,
“
Re
c
o
n
c
il
e
:
A
c
o
re
f
e
re
n
c
e
re
so
lu
ti
o
n
re
se
a
rc
h
p
latf
o
rm
”
,
2
0
1
0
A
p
r
1
3
.
[3
0
]
T
o
u
tan
o
v
a
K,
Kle
in
D,
M
a
n
n
in
g
CD,
S
in
g
e
r
Y
,
“
F
e
a
tu
re
-
rich
p
a
rt
-
of
-
sp
e
e
c
h
ta
g
g
in
g
w
it
h
a
c
y
c
li
c
d
e
p
e
n
d
e
n
c
y
n
e
tw
o
rk
”
,
In
Pro
c
e
e
d
in
g
s
o
f
th
e
2
0
0
3
C
o
n
fer
e
n
c
e
o
f
t
h
e
No
rth
Ame
ric
a
n
Ch
a
p
ter
o
f
t
h
e
Asso
c
ia
ti
o
n
f
o
r
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
p
h
o
r
a
R
eso
lu
tio
n
i
n
B
u
s
in
ess
P
r
o
ce
s
s
R
eq
u
ir
eme
n
t E
n
g
i
n
ee
r
in
g
(
R
ia
d
S
o
n
b
o
l
)
1773
Co
mp
u
t
a
ti
o
n
a
l
L
i
n
g
u
i
stics
o
n
Hu
ma
n
L
a
n
g
u
a
g
e
T
e
c
h
n
o
l
o
g
y
-
Vo
lu
me
1
2
0
0
3
M
a
y
2
7
,
p
p
.
1
7
3
-
1
8
0
,
A
s
so
c
iatio
n
f
o
r
Co
m
p
u
tatio
n
a
l
L
in
g
u
ist
ics
.
[3
1
]
Ch
e
n
D,
M
a
n
n
i
n
g
C
,
“
A
f
a
st
a
n
d
a
c
c
u
ra
te
d
e
p
e
n
d
e
n
c
y
p
a
rse
r
u
sin
g
n
e
u
ra
l
n
e
tw
o
rk
s
”
,
In
Pro
c
e
e
d
in
g
s
o
f
t
h
e
2
0
1
4
c
o
n
fer
e
n
c
e
o
n
e
m
p
irica
l
me
th
o
d
s
in
n
a
t
u
ra
l
l
a
n
g
u
a
g
e
p
ro
c
e
ss
in
g
(
EM
NL
P)
2
0
1
4
,
p
p
.
7
4
0
-
7
5
0
.
[3
2
]
W
u
Z,
P
a
lm
e
r
M
,
“
V
e
rb
s
se
m
a
n
ti
c
s
a
n
d
lex
ica
l
s
e
lec
ti
o
n
”
,
In
Pro
c
e
e
d
in
g
s
o
f
th
e
3
2
n
d
a
n
n
u
a
l
me
e
ti
n
g
o
n
Asso
c
ia
ti
o
n
f
o
r Co
m
p
u
t
a
ti
o
n
a
l
L
i
n
g
u
isti
c
s 1
9
9
4
J
u
n
2
7
,
p
p
.
1
3
3
-
1
3
8
,
A
ss
o
c
iatio
n
f
o
r
Co
m
p
u
tati
o
n
a
l
L
in
g
u
isti
c
s.
Evaluation Warning : The document was created with Spire.PDF for Python.