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
.
6
,
Dec
em
b
er
2
0
2
0
,
p
p
.
5
9
0
9
~
5
9
1
6
I
SS
N:
2
0
8
8
-
8708
,
DOI
: 1
0
.
1
1
5
9
1
/
i
j
ec
e
.
v
1
0
i
6
.
pp
5
9
0
9
-
5
9
1
6
5909
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
I
m
pro
v
ing
k
ey
w
o
rd e
x
traction
in
m
ul
tilingua
l t
ex
ts
B
a
ha
re
h H
a
s
he
m
za
deh
1
,
M
a
j
id Abdo
lra
zz
a
g
h
-
Nez
ha
d
2
1
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter an
d
I
n
f
o
rm
a
ti
o
n
T
e
c
h
n
o
lo
g
y
,
F
a
c
u
lt
y
o
f
En
g
in
e
e
rin
g
,
T
o
rb
a
t
-
E
He
y
d
a
ri
y
e
h
Un
iv
e
rsity
,
Ira
n
2
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter
En
g
in
e
e
rin
g
,
F
a
c
u
lt
y
o
f
En
g
in
e
e
rin
g
,
Bo
z
o
rg
m
e
h
r
Un
iv
e
rsit
y
o
f
Qa
e
n
a
t,
Ira
n
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
u
n
18
,
2
0
1
9
R
ev
i
s
ed
A
p
r
2
9
,
2
0
2
0
A
cc
ep
ted
Ma
y
1
2
,
2
0
2
0
T
h
e
a
c
c
u
ra
c
y
o
f
k
e
y
w
o
rd
e
x
tr
a
c
ti
o
n
is
a
lea
d
in
g
fa
c
to
r
in
in
f
o
rm
a
ti
o
n
re
tri
e
v
a
l
s
y
ste
m
s
a
n
d
m
a
rk
e
ti
n
g
.
In
th
e
re
a
l
w
o
rld
,
tex
t
is
p
ro
d
u
c
e
d
i
n
a
v
a
riet
y
o
f
lan
g
u
a
g
e
s,
a
n
d
th
e
a
b
il
it
y
to
e
x
trac
t
k
e
y
w
o
rd
s
b
a
se
d
o
n
in
f
o
rm
a
ti
o
n
f
ro
m
d
iff
e
r
e
n
t
lan
g
u
a
g
e
s
i
m
p
ro
v
e
s
th
e
a
c
c
u
ra
c
y
o
f
k
e
y
w
o
rd
e
x
trac
ti
o
n
.
In
th
is
p
a
p
e
r,
th
e
a
v
a
il
a
b
le
in
f
o
rm
a
ti
o
n
o
f
a
ll
lan
g
u
a
g
e
s
is
a
p
p
li
e
d
to
im
p
ro
v
e
a
trad
it
io
n
a
l
k
e
y
w
o
rd
e
x
trac
ti
o
n
a
lg
o
rit
h
m
f
ro
m
a
m
u
lt
il
i
n
g
u
a
l
tex
t.
T
h
e
p
ro
p
o
se
d
k
e
y
w
o
rk
e
x
tra
c
ti
o
n
p
ro
c
e
d
u
re
is
a
n
u
n
su
p
e
rv
ise
a
lg
o
rit
h
m
a
n
d
d
e
sig
n
e
d
b
a
se
d
o
n
se
lec
ti
n
g
a
w
o
rd
a
s
a
k
e
y
w
o
rd
o
f
a
g
iv
e
n
tex
t,
if
in
a
d
d
it
i
o
n
to
th
a
t
la
n
g
u
a
g
e
h
o
ld
s
a
h
ig
h
ra
n
k
b
a
se
d
o
n
th
e
k
e
y
w
o
rd
s
c
rit
e
ria
in
o
th
e
r
lan
g
u
a
g
e
s,
a
s
w
e
ll
.
T
o
a
c
h
iev
e
to
th
is
a
im
,
th
e
a
v
e
ra
g
e
T
F
-
IDF
o
f
th
e
c
a
n
d
i
d
a
te
w
o
rd
s
w
e
re
c
a
lcu
late
d
f
o
r
th
e
sa
m
e
a
n
d
t
h
e
o
t
h
e
r
lan
g
u
a
g
e
s.
T
h
e
n
th
e
w
o
rd
s
w
it
h
th
e
h
ig
h
e
r
a
v
e
ra
g
e
s
T
F
-
IDF
we
re
c
h
o
se
n
a
s
th
e
e
x
trac
ted
k
e
y
w
o
rd
s.
T
h
e
o
b
tain
e
d
re
su
lt
s
in
d
ica
t
th
a
t
th
e
a
lg
o
rit
h
m
s’
a
c
c
u
ra
c
is
o
f
th
e
m
u
lt
il
in
g
u
a
l
t
e
x
ts
in
term
f
re
q
u
e
n
c
y
-
in
v
e
rse
d
o
c
u
m
e
n
t
f
re
q
u
e
n
c
y
(
T
F
-
IDF)
a
lg
o
rit
h
m
,
g
ra
p
h
-
b
a
se
d
a
lg
o
rit
h
m
,
a
n
d
th
e
im
p
ro
v
e
d
p
ro
p
o
se
d
a
lg
o
rit
h
m
a
re
8
0
,
6
0
.
6
5
,
a
n
d
9
1
.
3
%
,
re
sp
e
c
ti
v
e
ly
.
K
ey
w
o
r
d
s
:
Data
r
etr
iev
al
Gr
ap
h
-
b
ased
alg
o
r
it
h
m
Ke
y
w
o
r
d
ex
tr
ac
tio
n
L
a
n
g
u
a
g
e
in
d
ep
en
d
e
n
t
T
ex
t m
in
i
n
g
TF
-
I
DF a
lg
o
r
ith
m
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
:
Ma
j
id
A
b
d
o
lr
az
za
g
h
-
Nez
h
ad
,
Dep
ar
t
m
en
t o
f
C
o
m
p
u
ter
E
n
g
i
n
ee
r
in
g
,
B
o
zo
r
g
m
e
h
r
Un
i
v
er
s
i
t
y
o
f
Qa
en
at
,
9
7
6
1
9
8
6
8
4
4
B
o
z
o
r
g
m
eh
r
U
n
i
v
er
s
it
y
o
f
Qae
n
at,
A
b
o
l
m
a
f
ak
h
er
St,
Qae
n
,
So
u
th
K
h
o
r
asa
n
,
I
r
an
.
E
m
ail: a
b
d
o
lr
az
za
g
h
@
b
u
q
ae
n
.
ac
.
ir
1.
I
NT
RO
D
UCT
I
O
N
D
esig
n
i
n
g
d
ata
r
etr
iev
al
s
y
s
te
m
s
o
f
lar
g
e
d
atab
ases
i
s
o
n
e
o
f
t
h
e
r
esear
ch
ar
ea
s
f
o
r
t
h
e
ap
p
licatio
n
o
f
in
f
o
r
m
atio
n
tech
n
o
lo
g
y
in
t
h
e
in
f
o
r
m
atio
n
b
u
s
i
n
es
s
.
We
f
ac
ed
an
i
n
cr
ea
s
i
n
g
d
e
m
an
d
f
o
r
t
y
p
es
o
f
d
ata
r
etr
iev
al
s
y
s
te
m
s
ab
le
to
cr
o
s
s
th
e
i
n
ter
li
n
g
u
al
b
o
u
n
d
ar
ies
,
w
h
ile
te
x
t
d
ata
e
x
p
an
d
s
i
n
d
i
f
f
er
en
t
lan
g
u
ag
e
s
a
n
d
o
n
th
e
w
eb
[1
-
6]
.
T
h
er
ef
o
r
e,
b
y
d
ev
elo
p
in
g
th
e
v
o
lu
m
e
o
f
elec
tr
o
n
ic
d
ata
in
v
ar
io
u
s
l
an
g
u
a
g
es,
th
e
d
ata
r
etr
iev
al,
in
d
ep
en
d
e
n
t o
f
d
o
cu
m
en
t la
n
g
u
ag
e
s
,
h
a
s
g
ai
n
ed
i
m
p
o
r
ta
n
ce
.
T
h
e
ex
tr
ac
tio
n
o
f
ef
f
ec
tiv
e
k
e
y
w
o
r
d
s
is
a
ti
m
e
-
co
n
s
u
m
i
n
g
an
d
h
u
m
a
n
-
p
r
o
ce
s
s
i
n
g
ta
s
k
.
R
ec
e
n
tl
y
,
au
to
m
atic
k
e
y
w
o
r
d
ex
tr
ac
tio
n
,
e
s
p
ec
iall
y
k
e
y
w
o
r
d
ex
tr
ac
tio
n
i
n
d
if
f
er
en
t
lan
g
u
ag
es,
in
tr
o
d
u
ce
d
an
i
n
ter
esti
n
g
t
o
p
ic
f
o
r
tex
t
m
i
n
i
n
g
a
n
d
d
ata
r
etr
iev
al
[7
-
9]
.
T
h
e
f
ield
s
o
f
tex
t
m
in
in
g
an
d
i
n
f
o
r
m
atio
n
r
etr
iev
al
a
n
d
esp
ec
iall
y
th
eir
i
m
p
le
m
e
n
tatio
n
o
n
th
e
d
atab
ase
is
o
f
p
ar
ticu
lar
i
m
p
o
r
ta
n
ce
.
T
h
e
f
ir
s
t
s
tep
is
t
o
id
en
tify
a
n
d
ex
tr
ac
t
k
e
y
w
o
r
d
s
f
r
o
m
th
e
te
x
ts
i
n
th
e
f
ield
s
.
O
n
e
o
f
th
e
m
ai
n
ch
allen
g
es
to
ex
tr
ac
t
k
e
y
w
o
r
d
s
i
s
ex
is
t
in
g
v
er
y
d
iv
er
s
e
lan
g
u
a
g
es
f
o
r
co
n
tex
tu
a
l
in
f
o
r
m
atio
n
an
d
d
ep
en
d
i
n
g
th
e
av
ailab
le
k
e
y
w
o
r
d
e
x
tr
ac
tio
n
m
eth
o
d
s
o
n
t
h
e
la
n
g
u
a
g
e’
s
t
y
p
e
an
d
it
s
v
er
b
al
s
tr
u
ct
u
r
e.
T
h
e
m
u
lti
li
n
g
u
al
k
e
y
w
o
r
d
s
ex
tr
ac
tio
n
is
t
h
e
c
u
r
r
en
t
r
esear
ch
p
r
o
b
le
m
an
d
t
h
e
r
esear
ch
o
b
j
ec
t
is
co
n
s
id
er
ed
b
ased
o
n
d
esi
g
n
in
g
a
n
u
n
s
u
p
er
v
is
ed
la
n
g
u
a
g
e
-
i
n
d
ep
en
d
en
t
a
lg
o
r
it
h
m
to
t
h
e
ex
tr
ac
tio
n
.
So
,
it
i
s
d
o
n
e
b
y
f
o
cu
s
i
n
g
o
n
t
h
e
p
r
o
p
er
t
y
o
f
r
ep
ea
tin
g
k
e
y
w
o
r
d
s
i
n
ea
ch
tex
t
an
d
t
h
eir
i
n
ten
s
i
f
y
i
n
g
in
o
t
h
er
tex
t
s
b
y
u
tili
zi
n
g
th
e
T
F
-
I
D
F a
lg
o
r
it
h
m
.
T
h
e
r
est
o
f
th
e
cu
r
r
en
t
p
ap
er
is
o
r
g
an
ized
as
f
o
llo
w
s
:
Sectio
n
2
r
ev
ie
w
s
th
e
s
tate
-
of
-
t
h
e
-
ar
t
k
e
y
w
o
r
d
s
ex
tr
ac
tio
n
m
et
h
o
d
s
.
T
h
e
p
r
o
b
le
m
o
f
k
e
y
w
o
r
d
s
ex
tr
ac
tio
n
d
escr
id
s
in
Sectio
n
3
.
T
h
e
p
r
o
p
o
s
ed
lan
g
u
ag
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
.
6
,
Dec
em
b
er
2
0
2
0
:
5
9
0
9
-
5
9
1
6
5910
in
d
ep
en
d
en
t
k
e
y
w
o
r
d
s
e
x
tr
ac
tio
n
al
g
o
r
ith
m
a
n
d
it
s
e
x
p
er
im
en
tal
r
es
u
lt
s
ar
e
d
is
c
u
s
s
ed
in
Sectio
n
4
an
d
Sectio
n
5
.
Fin
al
l
y
,
a
co
n
cl
u
s
io
n
an
d
r
ec
o
m
m
en
d
atio
n
s
ar
e
d
escr
ib
ed
in
s
ec
tio
n
6
.
2.
L
I
T
E
R
AT
U
RE
R
E
VI
E
W
Sev
er
al
m
et
h
o
d
s
w
er
e
p
r
o
p
o
s
e
d
s
o
f
ar
f
o
r
th
e
id
e
n
ti
f
icatio
n
an
d
ex
tr
ac
tio
n
o
f
k
e
y
w
o
r
d
s
,
al
l
o
f
w
h
ic
h
co
u
ld
b
e
class
i
f
ied
in
to
t
w
o
g
r
o
u
p
s
o
f
s
u
p
er
v
is
ed
a
n
d
u
n
s
u
p
er
v
is
ed
m
et
h
o
d
s
[
1
0
-
12]
.
I
n
th
e
f
o
llo
w
i
n
g
,
w
e
d
is
cu
s
s
s
h
o
r
tl
y
ab
o
u
t
t
h
e
p
r
o
p
o
s
ed
m
et
h
o
d
s
to
r
ea
lize
th
e
p
r
o
b
ab
le
r
esear
ch
ch
alle
n
g
e
s
.
T
h
e
f
ir
s
t
g
r
o
u
p
i
s
th
e
s
u
p
er
v
i
s
ed
m
eth
o
d
s
.
I
n
t
h
is
g
r
o
u
p
,
th
er
e
i
s
a
tr
ai
n
i
n
g
d
ata
s
et,
b
y
lear
n
i
n
g
o
f
w
h
ic
h
a
m
o
d
el
is
d
esig
n
ed
an
d
b
y
in
co
r
p
o
r
atin
g
t
h
is
m
o
d
el
o
n
n
e
w
d
o
cu
m
e
n
t
t
h
e
p
h
r
ases
w
i
ll
d
i
v
id
ed
in
to
t
w
o
c
lass
es
o
f
k
e
y
a
n
d
n
o
n
-
k
e
y
p
h
r
ase
s
.
T
h
e
s
u
p
er
v
i
s
ed
m
et
h
o
d
o
f
w
o
r
d
ex
tr
ac
tio
n
is
co
n
s
id
er
ed
as
a
clu
s
ter
in
g
p
r
o
b
lem
,
w
h
ic
h
s
h
o
u
ld
b
e
tr
ain
ed
lik
e
a
g
e
n
etic
alg
o
r
it
h
m
[
1
3
,
1
4
]
.
I
n
B
ay
es
l
in
ea
r
a
lg
o
r
ith
m
,
w
h
ic
h
is
ca
lled
a
k
e
y
p
h
r
ase
e
x
tr
ac
tio
n
alg
o
r
ith
m
(
KE
A
)
a
n
d
p
r
o
p
o
s
ed
b
y
[
1
5
]
,
T
F
-
I
DF
a
n
d
k
e
y
p
h
r
ase
r
elati
v
e
d
is
ta
n
ce
f
r
o
m
th
e
b
e
g
in
n
i
n
g
o
f
th
e
tex
t
ar
e
t
w
o
al
g
o
r
ith
m
i
n
p
u
ts
[
1
6
]
.
T
h
ey
also
u
s
ed
a
b
in
ar
y
cl
u
s
ter
i
n
g
alg
o
r
ith
m
t
h
a
t
its
in
p
u
t
f
ea
t
u
r
es
in
cl
u
d
e
s
o
m
e
r
ef
er
e
n
ce
s
to
th
e
tex
t.
Dec
is
io
n
tr
ee
o
f
[
1
7
]
,
co
n
d
itio
n
al
r
an
d
o
m
f
ield
o
f
[
1
8
]
,
an
d
a
ty
p
e
o
f
KE
A
in
[
1
9
]
ar
e
a
m
o
n
g
o
t
h
er
t
y
p
es
o
f
s
u
p
er
v
i
s
ed
w
o
r
d
ex
tr
ac
tio
n
.
T
h
e
f
u
n
ctio
n
a
lit
y
o
f
th
is
m
et
h
o
d
is
h
i
g
h
l
y
d
ep
en
d
en
t
o
n
tr
ain
in
g
d
ata
an
d
lack
o
f
s
u
c
h
h
i
g
h
q
u
alit
y
d
at
a
co
u
ld
ca
u
s
e
a
n
ef
f
icie
n
c
y
d
r
o
p
in
th
e
s
y
s
te
m
o
f
k
e
y
p
h
r
ase
ex
tr
ac
tio
n
.
I
n
t
h
i
s
m
et
h
o
d
,
th
e
d
esig
n
ed
m
o
d
e
l
is
s
p
ec
i
f
ic
to
a
d
o
m
ain
a
n
d
w
o
r
k
s
b
ased
o
n
th
e
d
o
m
ai
n
o
f
u
s
ag
e.
An
o
th
er
ap
p
r
o
ac
h
to
e
x
tr
ac
ti
n
g
k
e
y
w
o
r
d
s
is
th
r
o
u
g
h
u
n
s
u
p
er
v
is
ed
m
et
h
o
d
s
.
I
n
t
h
e
s
e
m
et
h
o
d
s
,
w
o
r
d
ex
tr
ac
tio
n
i
s
d
ea
lt
w
it
h
as
a
r
an
k
i
n
g
is
s
u
e
[
2
0
]
,
th
e
m
o
s
t
i
m
p
o
r
tan
t
o
f
w
h
ich
is
t
h
e
TF
-
I
DF.
I
n
th
i
s
m
et
h
o
d
,
th
e
r
elatio
n
b
et
w
ee
n
t
h
e
n
u
m
b
er
o
f
a
w
o
r
d
r
ep
etitio
n
w
i
th
i
n
a
te
x
t
is
ca
lc
u
lated
ac
co
r
d
in
g
to
th
e
n
u
m
b
er
o
f
it
s
r
ep
letio
n
in
o
th
er
tex
t
s
[
2
1
]
.
Gr
a
p
h
-
b
ased
m
eth
o
d
s
ar
e
also
a
m
o
n
g
th
e
u
n
s
u
p
er
v
is
e
d
m
et
h
o
d
s
[
2
2
]
.
T
h
e
w
o
r
k
s
o
f
[
22
-
24]
ar
e
ex
a
m
p
le
s
o
f
g
r
ap
h
-
b
a
s
ed
m
et
h
o
d
s
f
o
r
w
o
r
d
ex
tr
ac
tio
n
.
I
n
u
n
s
u
p
er
v
i
s
ed
m
et
h
o
d
s
,
th
er
e
is
n
o
n
ee
d
f
o
r
tr
ain
in
g
d
ata
an
d
th
e
m
o
s
t
i
m
p
o
r
tan
t
co
n
te
x
tu
a
l
p
h
r
ase
s
co
u
ld
b
e
ex
tr
ac
ted
b
y
u
s
i
n
g
th
e
r
a
n
k
in
g
s
tr
ateg
ies.
U
n
li
k
e
t
h
e
s
u
p
er
v
is
ed
m
et
h
o
d
s
,
t
h
e
u
n
s
u
p
e
r
v
is
ed
m
eth
o
d
s
ar
e
ap
p
licab
le
f
o
r
ea
ch
tex
t
to
an
y
d
o
m
ain
t
y
p
e
in
d
ep
en
d
en
t
o
f
d
o
m
ai
n
o
f
u
s
ag
e.
B
y
t
h
e
q
u
al
itativ
e
a
n
al
y
s
is
a
n
d
co
m
p
ar
is
o
n
o
f
th
e
p
r
o
p
o
s
ed
m
et
h
o
d
s
s
ev
er
al
ad
v
an
tag
e
s
an
d
d
is
ad
v
an
ta
g
es
w
er
e
f
o
u
n
d
,
w
h
ic
h
co
u
ld
b
e
n
o
ted
as f
o
llo
w
s
.
T
h
e
f
ir
s
t
ad
v
an
ta
g
e
o
f
t
h
e
u
n
s
u
p
er
v
is
ed
m
et
h
o
d
s
is
t
h
eir
ap
p
licatio
n
s
i
n
co
n
s
tr
u
ct
i
n
g
m
o
d
els
o
f
a
n
y
tex
t
t
y
p
e
a
n
d
d
o
m
ai
n
.
No
e
f
f
i
cien
c
y
d
r
o
p
s
in
ca
s
e
o
f
e
x
is
te
n
ce
o
f
p
o
o
r
q
u
alit
y
d
ata,
i
n
d
ep
en
d
en
tl
y
of
tr
ai
n
in
g
d
ata,
lo
w
er
t
i
m
e
co
n
s
u
m
p
tio
n
f
o
r
k
e
y
w
o
r
d
ex
tr
ac
tio
n
,
co
m
p
ar
ed
w
it
h
th
e
s
u
p
er
v
is
ed
m
eth
o
d
s
,
u
s
e
f
u
l
f
u
n
c
tio
n
ali
t
y
f
o
r
h
ig
h
-
v
o
lu
m
e
d
ata,
an
d
h
ig
h
ac
cu
r
a
c
y
ar
e
a
m
o
n
g
th
e
ad
v
a
n
ta
g
es
o
f
th
e
u
n
s
u
p
er
v
i
s
ed
m
et
h
o
d
s
.
I
n
co
n
tr
ast
to
th
es
e
ad
v
an
tag
e
s
,
lo
w
co
m
p
at
ib
ilit
y
is
t
h
e
m
o
s
t
tan
g
ib
le
s
h
o
r
tco
m
in
g
o
f
t
h
es
e
m
et
h
o
d
s
.
As
m
e
n
tio
n
ed
p
r
ev
io
u
s
l
y
,
th
er
e
ar
e
s
o
m
e
d
i
s
ad
v
an
ta
g
e
s
/ad
v
a
n
ta
g
es
of
t
h
e
s
u
p
er
v
is
ed
m
et
h
o
d
s
,
a
m
o
n
g
w
h
ic
h
w
e
co
u
ld
r
ef
er
t
o
th
e
e
x
is
te
n
ce
o
f
tr
ai
n
i
n
g
d
at
a
w
ith
th
e
q
u
ali
t
y
o
f
r
e
g
u
lar
d
ata
ca
teg
o
r
izatio
n
.
Ho
w
e
v
er
,
o
n
e
o
f
t
h
e
s
i
g
n
i
f
ica
n
t
s
h
o
r
tco
m
in
g
s
o
f
th
i
s
m
et
h
o
d
is
t
h
at
it
i
s
d
ep
en
d
en
t
o
n
th
e
tr
ain
i
n
g
d
ata
a
n
d
lack
h
i
g
h
-
q
u
alit
y
d
ata
co
u
ld
lead
to
an
ef
f
icie
n
c
y
d
r
o
p
o
f
th
e
k
e
y
w
o
r
d
ex
tr
ac
tio
n
s
y
s
t
e
m
,
th
e
co
n
s
tr
u
cted
m
o
d
el
is
f
o
r
o
n
e
d
o
m
a
in
o
n
l
y
,
an
d
it
ac
ts
b
a
s
ed
o
n
t
h
e
d
o
m
a
in
o
f
u
s
a
g
e.
P
r
o
v
id
in
g
tr
ain
i
n
g
d
ata
i
s
a
ti
m
e
-
co
n
s
u
m
in
g
an
d
lab
o
r
i
o
u
s
ta
s
k
.
Mo
r
eo
v
er
,
ev
al
u
ati
o
n
s
w
h
ic
h
ar
e
m
ad
e
b
a
s
ed
o
n
f
r
eq
u
e
n
c
y
ar
e
n
o
t
ap
p
l
y
i
n
g
f
o
r
h
i
g
h
-
v
o
l
u
m
e
d
at
a.
On
e
o
f
th
e
c
h
alle
n
g
es
o
f
s
u
ch
a
m
et
h
o
d
is
th
at
p
r
o
v
id
i
n
g
tr
ai
n
i
n
g
d
ata
is
ti
m
e
-
co
n
s
u
m
i
n
g
an
d
i
f
s
u
c
h
d
ata
ar
e
n
o
t a
v
ailab
le,
t
h
e
al
g
o
r
ith
m
f
ac
es p
r
o
b
le
m
s
a
n
d
h
a
s
l
o
w
e
f
f
icien
c
y
,
b
u
t
it
is
n
o
t t
h
e
ca
s
e
in
t
h
e
u
n
s
u
p
er
v
is
ed
m
et
h
o
d
[
1
,
3
]
.
Hen
ce
,
w
e
e
m
p
lo
y
t
h
is
m
et
h
o
d
f
o
r
th
e
p
r
o
p
o
s
ed
alg
o
r
ith
m
.
Desp
ite
th
e
s
i
m
p
licit
y
,
T
F
-
I
DF
alg
o
r
it
h
m
i
s
o
n
e
o
f
th
e
ef
f
ec
tiv
e
m
et
h
o
d
s
f
o
r
k
e
y
w
o
r
d
ex
tr
ac
tio
n
[
1
6
,
2
5
]
.
T
h
e
p
r
ac
tical
s
i
m
p
licit
y
a
n
d
ef
f
icie
n
c
y
o
f
t
h
i
s
al
g
o
r
ith
m
h
as
at
tr
ac
ted
a
co
n
s
id
er
ab
le
atten
tio
n
.
A
lo
g
ar
it
h
m
is
p
r
o
p
o
s
ed
f
o
r
w
o
r
d
ex
tr
ac
tio
n
i
n
th
e
p
r
esen
t
s
tu
d
y
to
i
m
p
r
o
v
e
T
F
-
I
DF.
T
h
is
m
et
h
o
d
is
b
ased
o
n
T
F
-
I
DF,
b
u
t
u
s
es
t
h
e
i
n
f
o
r
m
atio
n
o
f
ea
ch
te
x
t i
n
s
ev
er
al
lan
g
u
ag
e
s
to
e
n
h
an
ce
k
e
y
w
o
r
d
e
x
tr
ac
tio
n
b
ased
o
n
T
F
-
I
DF.
T
o
im
p
le
m
en
t
s
u
ch
a
n
o
b
j
ec
tiv
e,
w
e
co
n
ce
n
tr
ated
o
n
th
e
r
ep
etitio
n
o
f
w
o
r
d
s
in
th
e
co
n
tex
t
an
d
d
elete
d
t
h
e
co
n
j
u
n
ctio
n
s
,
p
r
e
p
o
s
itio
n
s
,
a
n
d
v
er
b
s
.
Fu
r
t
h
er
,
w
e
u
s
ed
s
i
m
u
lta
n
eo
u
s
m
u
lti
lin
g
u
al
in
f
o
r
m
atio
n
f
o
r
a
ce
r
tain
tex
t,
to
i
m
p
r
o
v
e
its
u
s
a
g
e.
T
h
is
p
r
o
ce
s
s
is
el
u
cid
ated
in
d
etail
s
in
th
e
f
o
llo
w
i
n
g
.
3.
P
RO
B
L
E
M
DIS
CRIPT
I
O
N
O
F
K
E
YWO
RDS
E
XT
R
AC
T
I
O
N
Data
r
etr
iev
al
is
u
s
ed
ex
te
n
s
iv
el
y
i
n
th
e
e
v
er
y
d
a
y
li
f
e
o
f
p
eo
p
le.
E
n
h
an
cin
g
e
f
f
ic
ien
c
y
a
n
d
i
m
p
r
o
v
i
n
g
p
er
f
o
r
m
a
n
ce
is
o
f
g
r
ea
t
i
m
p
o
r
tan
ce
f
o
r
th
e
d
esig
n
er
s
o
f
d
ata
r
etr
iev
al
s
y
s
t
e
m
s
.
A
s
m
en
tio
n
ed
p
r
ev
io
u
s
l
y
,
o
n
e
w
a
y
to
in
cr
e
ase
th
e
p
r
o
d
u
ctiv
it
y
o
f
d
ata
r
etr
iev
al
s
y
s
te
m
s
i
s
th
r
o
u
g
h
t
h
e
u
s
e
o
f
s
tatis
t
ical
p
lan
s
.
I
n
th
e
s
e
p
lan
s
,
a
f
r
eq
u
e
n
c
y
is
s
et
of
k
e
y
w
o
r
d
s
,
b
ased
o
n
w
h
ich
w
o
r
d
s
w
it
h
t
h
e
h
ig
h
est
f
r
eq
u
e
n
c
y
ar
e
s
elec
ted
as k
e
y
w
o
r
d
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:
2
0
8
8
-
8708
I
mp
r
o
vin
g
ke
ywo
r
d
ex
tr
a
ctio
n
in
mu
ltil
in
g
u
a
l te
xts (
B
a
h
a
r
eh
Ha
s
h
emza
d
eh
)
5911
I
n
ai
m
o
f
t
h
e
p
r
esen
t
s
tu
d
y
was
to
p
r
o
p
o
s
e
an
alg
o
r
ith
m
,
wh
ich
h
a
s
th
e
r
eq
u
ir
ed
f
ea
t
u
r
es,
in
cl
u
d
in
g
n
o
n
-
s
u
p
er
v
i
s
o
r
y
,
lan
g
u
a
g
e
-
in
d
ep
en
d
en
t,
s
i
m
p
lici
t
y
,
an
d
h
i
g
h
s
p
ee
d
f
o
r
p
r
o
ce
s
s
in
g
co
n
s
id
er
ab
le
am
o
u
n
t
o
f
d
ata.
B
y
u
s
i
n
g
t
h
e
p
r
o
p
o
s
ed
alg
o
r
ith
m
alo
n
g
w
it
h
t
h
e
T
F
-
I
DF,
w
h
ic
h
i
s
a
s
tatis
tical,
s
i
m
p
le,
la
n
g
u
a
g
e
in
d
ep
en
d
en
t
a
n
d
n
o
n
-
s
u
p
er
v
is
o
r
y
al
g
o
r
ith
m
,
b
y
r
el
y
in
g
o
n
a
s
eq
u
en
ce
o
f
ca
lls
w
i
th
U
n
ic
o
d
e
f
o
r
m
at,
a
n
d
b
y
d
esig
n
in
g
a
n
o
n
li
n
e
d
atab
ase
k
e
y
w
o
r
d
co
u
ld
b
e
ex
tr
ac
ted
in
d
ep
en
d
en
tl
y
o
f
la
n
g
u
a
g
e
in
lar
g
e
d
atab
ases
.
B
y
as
s
es
s
in
g
t
h
e
ap
p
licatio
n
s
o
f
d
ata
r
etr
iev
al
an
d
tex
t
m
i
n
in
g
,
w
e
co
u
ld
r
ea
lize
th
at
ex
is
ti
n
g
k
e
y
w
o
r
d
s
w
i
th
in
a
tex
t
p
la
y
a
s
ig
n
i
f
ica
n
t
r
o
le
a
n
d
f
ac
i
litate
th
e
p
r
o
ce
s
s
i
n
t
h
i
s
f
ield
.
Fo
r
e
x
a
m
p
le,
b
y
f
in
d
i
n
g
i
m
p
o
r
tan
t
w
o
r
d
s
i
n
t
h
e
n
e
w
s
an
d
b
y
d
etec
ti
n
g
s
e
n
ten
ce
s
with
m
o
r
e
i
m
p
o
r
tan
t
w
o
r
d
s
,
w
e
co
u
ld
ex
tr
ac
t
t
h
a
t
s
en
te
n
ce
i
n
t
h
e
ab
s
tr
ac
t
an
d
b
etter
co
m
p
r
eh
e
n
d
th
e
tex
t.
Sin
c
e
i
m
p
o
r
tan
t
w
o
r
d
s
ar
e
o
f
ten
i
n
h
ea
d
i
n
g
s
a
n
d
i
m
p
o
r
tan
t sect
io
n
s
,
b
y
r
ea
liz
in
g
th
e
s
tr
u
ct
u
r
e
o
f
a
te
x
t a
n
d
b
y
ex
tr
ac
tin
g
k
e
y
w
o
r
d
s
o
u
t o
f
th
ese
p
ar
ts
,
w
e
co
u
ld
g
et
ac
ce
s
s
to
th
e
s
e
w
o
r
d
s
w
i
th
a
m
i
n
i
m
u
m
o
f
ti
m
e.
Feed
o
r
R
SS
is
u
s
ed
f
o
r
r
ea
d
in
g
n
e
w
s
,
w
h
ic
h
m
a
k
e
a
n
e
w
s
ex
tr
ac
t
av
ailab
le
i
n
a
s
tr
u
ct
u
r
ed
w
a
y
b
y
XM
L
f
o
r
m
a
t.
Ne
w
s
r
ea
d
in
g
an
d
s
a
v
i
n
g
te
m
p
late
ar
e
Un
ico
d
e.
Fo
r
ex
tr
ac
tin
g
k
e
y
w
o
r
d
s
o
f
n
e
w
s
tex
ts
,
w
e
n
ee
d
w
eb
s
ites
w
it
h
p
r
o
p
er
an
d
au
th
e
n
tic
f
ee
d
ad
d
r
ess
es.
Hen
ce
,
w
e
s
elec
t
t
h
o
s
e
f
ee
d
s
,
w
h
ic
h
p
r
o
v
id
e
ap
p
r
o
p
r
iate
in
f
o
r
m
at
io
n
.
T
h
ese
f
ee
d
s
,
h
o
w
e
v
er
,
ar
e
s
elec
ted
f
o
r
ev
er
y
la
n
g
u
a
g
e.
Af
ter
ca
lli
n
g
in
f
o
r
m
a
tio
n
f
r
o
m
f
ee
d
s
,
th
e
y
w
i
ll
b
e
s
av
ed
in
a
d
atab
ase.
So
m
e
w
o
r
d
s
ar
e
av
ailab
le
w
i
th
h
ig
h
f
r
eq
u
e
n
c
y
i
n
al
l
te
x
ts
w
it
h
n
o
co
n
tex
tu
al
v
al
u
e,
li
k
e
p
r
o
n
o
u
n
s
,
ad
v
er
b
s
,
p
r
e
p
o
s
itio
n
s
,
co
n
j
u
n
ctio
n
s
,
a
n
d
s
o
m
e
f
r
eq
u
e
n
t
v
er
b
s
.
T
h
ese
ele
m
en
t
s
ar
e
c
alled
p
u
b
lic
w
o
r
d
s
.
B
y
o
m
i
tti
n
g
t
h
e
p
u
b
lic
w
o
r
d
s
in
s
tat
is
tica
l
tex
t
m
i
n
i
n
g
,
w
e
h
av
e
le
s
s
ca
lc
u
latio
n
s
a
n
d
h
i
g
h
er
ef
f
icie
n
c
y
.
W
o
r
d
s
tak
e
a
n
eq
u
al
w
eig
h
t
b
ased
o
n
th
e
ir
f
r
eq
u
e
n
c
y
i
n
t
h
e
d
o
cu
m
en
t.
A
ct
u
all
y
,
t
h
is
w
eig
h
ti
n
g
s
y
s
te
m
s
h
o
w
s
h
o
w
m
u
c
h
a
wo
r
d
is
i
m
p
o
r
tan
t
f
o
r
a
d
o
cu
m
e
n
t.
T
h
is
f
ac
t
h
as
n
o
f
u
n
ct
io
n
alit
y
i
n
d
ata
r
etr
ie
v
a
l.
T
h
e
w
ei
g
h
t
o
f
a
w
o
r
d
in
a
tex
t
i
n
cr
ea
s
e
s
b
y
th
e
n
u
m
b
er
o
f
r
ep
etitio
n
s
i
n
t
h
at
te
x
t,
b
u
t
it
i
s
co
n
tr
o
lled
b
y
th
e
n
u
m
b
er
o
f
w
o
r
d
s
i
n
th
e
tex
t.
T
h
is
m
eth
o
d
i
s
an
u
n
s
u
p
er
v
is
ed
o
n
e,
w
h
ic
h
i
s
ap
p
li
ed
to
a
s
i
m
p
le
te
x
t.
I
n
co
n
tr
ast
to
t
h
e
s
u
p
er
v
is
ed
m
e
th
o
d
s
,
t
h
is
m
et
h
o
d
d
o
es
n
o
t
n
ee
d
th
e
tr
ain
in
g
d
ataset,
in
th
at
p
r
o
v
in
g
an
ap
p
r
o
p
r
iate
tr
ain
in
g
d
ata
is
a
tim
e
-
co
n
s
u
m
in
g
an
d
n
o
t
an
ea
s
y
tas
k
a
n
d
i
n
ca
s
e
t
h
e
d
ata
lack
th
e
d
esire
d
q
u
ali
t
y
,
th
e
y
r
ed
u
ce
t
h
e
e
f
f
icie
n
c
y
o
f
th
e
s
u
p
er
v
is
ed
k
e
y
w
o
r
d
ex
tr
ac
tio
n
s
y
s
te
m
.
4.
T
H
E
P
RO
P
O
SE
D
AL
G
O
RI
T
H
M
Fig
u
r
e
1
p
r
esen
t
s
t
h
e
o
er
all
s
tr
u
ctu
r
e
o
f
t
h
e
p
r
o
p
o
s
ed
alg
o
r
ith
m
i
n
s
e
v
e
n
s
tep
s
,
w
h
ic
h
i
ts
d
et
ail
i
s
d
is
cu
s
s
ed
as f
o
llo
w
s
:
Fig
u
r
e
1
.
T
h
e
o
v
er
all
s
tr
u
ctu
r
e
o
f
th
e
p
r
o
p
o
s
ed
alg
o
r
ith
m
Step
1
(
s
elec
tin
g
f
ee
d
s
a
n
d
r
etr
iev
al)
:
in
o
r
d
er
to
g
ain
ac
ce
s
s
to
v
ar
io
u
s
d
o
cu
m
en
t
s
o
f
d
if
f
er
en
t
lan
g
u
a
g
es,
w
e
tr
ied
to
s
ele
ct
th
e
ap
p
r
o
p
r
iate
f
ee
d
s
.
Data
r
etr
iev
al
o
f
ea
c
h
d
o
cu
m
en
t,
lik
e
titl
e
o
r
b
o
d
y
is
ca
r
r
ied
o
u
t
in
th
is
s
tep
.
Sin
ce
o
u
r
alg
o
r
ith
m
is
lan
g
u
ag
e
i
n
d
ep
en
d
en
t,
in
f
o
r
m
atio
n
i
s
r
e
ad
b
y
th
e
u
n
ico
d
e
f
o
r
m
a
t.
Step
2
(
s
av
i
n
g
d
o
cu
m
en
t
i
n
f
o
r
m
atio
n
in
th
e
lar
g
e
d
atab
ase)
:
t
h
e
r
ea
d
in
f
o
r
m
atio
n
i
s
s
to
r
ed
in
th
e
d
atab
ase,
s
ep
ar
atel
y
.
Data
ar
e
s
to
r
ed
in
th
e
Un
ico
d
e
f
o
r
m
at.
T
h
is
f
o
r
m
at
co
v
er
s
m
o
s
t
o
f
1
-
R
e
ad
i
n
g
Fe
e
d
Data
2
-
S
av
i
n
g
D
ata
In
Th
e
Datab
ase
3
-
Wor
d
E
xtr
ac
tion
4
-
Ca
lcula
t
ing
T
F
-
I
DF
I
n
E
v
er
y
T
ex
t
And E
v
er
y
L
a
ng
ua
g
e
5
-
S
av
i
n
g
Th
e
Ob
taine
d
TF
-
ID
F
Cal
c
u
l
ation
s
6
-
I
m
pro
v
ing
K
ey
w
o
rd
E
x
t
ra
ct
io
n
B
a
s
ed
O
n T
F
-
I
DF
7
-
d
e
p
i
c
ting R
e
su
tls
8
-
e
v
al
u
ating
Th
e
Ac
c
u
r
ac
y
R
ate
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
.
6
,
Dec
em
b
er
2
0
2
0
:
5
9
0
9
-
5
9
1
6
5912
th
e
la
n
g
u
a
g
e
s
.
Step
3
(
w
o
r
d
ex
tr
ac
tio
n
)
:
a
ll
w
o
r
d
s
ar
e
ex
tr
ac
ted
f
r
o
m
t
h
e
tex
t
a
n
d
o
m
itted
i
n
th
e
s
tep
r
elate
d
to
th
i
s
ac
tio
n
.
E
v
er
y
la
n
g
u
a
g
e
h
a
s
a
lis
t
o
f
r
e
p
etitiv
e
w
o
r
d
s
,
w
h
ic
h
s
h
o
u
l
d
b
e
d
elete
d
f
r
o
m
th
e
ex
tr
ac
ted
w
o
r
d
s
.
Step
4
(
T
F
-
I
DF
ca
lcu
latio
n
s
)
:
TF
-
I
DF
ca
lcu
latio
n
s
ar
e
ca
r
r
ied
o
u
t
in
t
h
e
s
tep
f
o
r
ev
er
y
te
x
t
an
d
lan
g
u
a
g
e
an
d
f
i
n
all
y
t
h
e
ca
lcu
lated
T
F
-
I
DF
o
f
ea
ch
te
x
t
in
a
d
if
f
er
e
n
t
lan
g
u
ag
e
i
s
u
s
ed
f
o
r
i
m
p
r
o
v
i
n
g
th
e
k
e
y
w
o
r
d
s
.
I
n
th
i
s
m
et
h
o
d
,
ea
ch
w
o
r
d
h
as
a
f
r
eq
u
en
c
y
-
b
ased
w
eig
h
t
i
n
th
e
d
o
cu
m
e
n
t.
A
ctu
a
ll
y
,
s
u
c
h
w
ei
g
h
ti
n
g
s
y
s
te
m
s
h
o
w
s
h
o
w
m
u
c
h
a
w
o
r
d
is
i
m
p
o
r
tan
t
f
o
r
a
p
ar
ticu
lar
d
o
cu
m
e
n
t.
T
h
is
p
r
o
ce
s
s
is
u
s
ed
f
r
eq
u
en
tl
y
i
n
d
ata
r
etr
ie
v
al.
T
h
e
w
ei
g
h
t
o
f
a
w
o
r
d
i
s
i
n
cr
ea
s
ed
b
y
t
h
e
in
cr
ea
s
e
o
f
its
r
ep
etitio
n
in
a
ce
r
tai
n
tex
t,
b
u
t
is
co
n
tr
o
lled
b
y
t
h
e
n
u
m
b
er
o
f
w
o
r
d
s
in
t
h
e
co
n
te
x
t
,
b
ec
au
s
e
i
f
t
h
e
tex
t
i
s
len
g
t
h
y
s
o
m
e
w
o
r
d
s
w
o
u
ld
b
e
r
ep
ea
ted
,
n
atu
r
all
y
,
th
o
u
g
h
th
e
y
d
o
n
o
t
h
av
e
a
n
y
s
i
g
n
if
ica
n
ce
in
t
h
e
m
ea
n
in
g
.
T
er
m
f
r
eq
u
en
c
y
is
a
cr
iter
io
n
f
o
r
th
e
r
an
g
e
o
f
co
m
m
o
n
a
n
d
r
ep
etitiv
e
w
o
r
d
s
in
a
te
x
t,
w
h
ic
h
is
ca
lc
u
lated
as
f
o
llo
w
s
:
(
,
)
=
0
.
5
+
0
.
5
×
(
,
)
{
(
,
)
:
∈
}
(
1
)
w
h
er
e
in
t
h
e
n
u
m
er
ato
r
,
d
is
th
e
n
u
m
b
er
o
f
w
o
r
d
s
in
t
h
e
s
elec
ted
tex
t.
w
is
t
h
e
m
o
s
t
f
r
eq
u
en
t
w
o
r
d
s
in
th
e
s
elec
ted
te
x
t.
I
DF
(
in
v
er
s
e
d
o
cu
m
e
n
t
Fre
q
u
en
c
y
)
is
a
cr
iter
io
n
f
o
r
th
e
r
an
g
e
o
f
t
h
e
m
o
s
t
f
r
eq
u
e
n
t
a
n
d
r
ep
etitiv
e
w
o
r
d
s
.
T
h
is
cr
iter
io
n
is
ac
h
i
ev
ed
b
y
d
i
v
id
in
g
t
h
e
to
tal
n
u
m
b
er
o
f
te
x
ts
in
t
h
e
n
u
m
b
e
r
o
f
te
x
ts
in
cl
u
d
i
n
g
th
e
co
m
m
o
n
w
o
r
d
.
Fo
r
ex
a
m
p
le:
s
u
p
p
o
s
e
t
h
at
t
h
er
e
ar
e
1
0
0
0
tex
ts
in
t
h
e
w
h
o
le
d
atab
ases
.
I
f
th
er
e
i
s
a
ce
r
tain
w
o
r
d
in
a
ll
o
f
th
e
m
(
li
k
e,
i
s
)
t
h
e
r
es
u
lt
o
f
an
alg
o
r
it
h
m
is
1
0
0
0
d
iv
id
ed
b
y
1
0
0
0
,
w
h
ich
is
0
,
th
at
is
,
th
i
s
w
o
r
d
is
a
m
o
n
g
t
h
e
co
m
m
o
n
w
o
r
d
s
an
d
m
u
s
t
b
e
tak
e
n
t
h
e
co
e
f
f
ici
en
t
o
f
0
.
Ho
w
e
v
er
,
i
f
t
h
e
r
e
p
etitio
n
i
s
o
cc
u
r
r
ed
in
5
0
0
tex
ts
,
th
e
r
es
u
lt
is
1
a
n
d
t
ak
es
t
h
e
co
ef
f
ic
ien
t
o
f
1
.
T
h
e
m
o
r
e
t
h
e
r
ep
etitio
n
o
f
a
w
o
r
d
,
th
e
le
s
s
i
s
t
h
e
I
DF
w
ei
g
h
t.
I
n
ca
s
e
a
w
o
r
d
h
as
n
o
r
ep
etitio
n
an
d
d
o
m
i
n
ato
r
b
ec
o
m
e
s
0
,
w
e
p
u
t
+1
in
d
o
m
i
n
ato
r
,
w
h
ic
h
i
s
ca
lcu
lated
th
r
o
u
g
h
s
ec
o
n
d
f
o
r
m
u
la:
(
,
)
=
(
1
+
{
∈
:
∈
}
)
(
2
)
w
h
er
e,
D
is
th
e
n
u
m
b
er
o
f
e
x
is
t
in
g
tex
t
s
i
n
th
e
n
u
m
er
ato
r
an
d
t
h
e
n
u
m
b
er
o
f
te
x
t
s
b
e
ar
in
g
t
h
e
w
o
r
d
i
n
th
e
d
o
m
i
n
ato
r
.
T
h
e
T
F
-
I
DF is
ca
lcu
lated
th
r
o
u
g
h
f
o
r
m
u
la
(
3
)
as f
o
llo
w
s
:
_
(
,
,
)
=
(
,
)
∗
(
,
)
(
3
)
Step
5
(
s
av
i
n
g
ca
lc
u
latio
n
s
i
n
th
e
d
atab
ase)
:
t
h
e
p
er
f
o
r
m
ed
c
alcu
latio
n
s
ar
e
s
av
ed
i
n
th
e
d
a
tab
ase
b
y
TF
-
I
DF
alg
o
r
it
h
m
.
Step
6
(
i
m
p
r
o
v
in
g
th
e
e
x
tr
ac
tio
n
o
f
t
h
e
p
r
o
p
o
s
ed
T
F
-
I
DF)
:
in
t
h
e
co
n
v
en
t
io
n
al
T
F
-
I
D
F,
in
a
te
x
t
in
a
ce
r
tai
n
lan
g
u
ag
e,
w
o
r
d
s
w
it
h
t
h
e
h
i
g
h
e
s
t
f
r
e
q
u
en
c
y
o
f
T
F
-
I
DF
ar
e
co
n
s
id
er
ed
as
k
e
y
w
o
r
d
s
in
th
at
tex
t
w
it
h
th
e
s
a
m
e
lan
g
u
ag
e.
Ho
w
ev
er
,
in
t
h
e
p
r
o
p
o
s
ed
m
e
th
o
d
,
w
o
r
d
s
ar
e
ca
l
le
d
k
e
y
w
o
r
d
s
i
f
t
h
eir
av
er
ag
es
T
F
-
I
DF
ar
e
h
i
g
h
f
o
r
th
at
tex
t
w
it
h
t
h
e
s
a
m
e
la
n
g
u
ag
e
a
n
d
o
th
er
la
n
g
u
a
g
es.
T
h
e
r
ef
o
r
e,
th
e
a
v
er
ag
e
TF
-
I
DF
is
co
n
s
id
er
ed
f
o
r
a
tex
t
w
it
h
th
e
s
a
m
e
la
n
g
u
a
g
e
an
d
o
th
er
lan
g
u
ag
e
s
an
d
in
s
te
ad
o
f
u
s
i
n
g
T
F
-
I
DF
o
f
a
tex
t
i
n
a
la
n
g
u
a
g
e,
its
a
v
er
a
g
e
T
F
-
I
DF
i
s
u
s
ed
in
a
v
ailab
l
e
lan
g
u
a
g
es.
T
h
is
s
i
m
p
le,
b
u
t
u
s
e
f
u
l
m
eth
o
d
co
u
ld
i
m
p
r
o
v
e
t
h
e
ex
tr
ac
tio
n
o
f
k
e
y
w
o
r
d
s
,
s
i
g
n
if
ican
tl
y
.
I
n
th
i
s
p
ap
er
,
av
er
ag
e
an
d
m
a
x
i
m
u
m
T
F
-
I
DF
m
et
h
o
d
f
o
r
a
tex
t
in
d
i
f
f
er
en
t
la
n
g
u
a
g
es
i
s
also
test
ed
,
th
e
r
es
u
lt
o
f
w
h
ich
o
u
t
w
ei
g
h
ed
th
e
co
n
v
e
n
tio
n
al
o
n
e.
Ho
w
ev
er
,
th
e
m
e
th
o
d
,
w
h
ic
h
ca
lc
u
lates t
h
e
av
er
a
g
e
T
F
-
I
DF
h
a
s
th
e
h
i
g
h
est ac
c
u
r
ac
y
.
Step
7
(
d
e
p
ictin
g
r
es
u
lts
)
:
t
h
is
s
tep
s
h
o
w
s
t
h
o
s
e
k
e
y
w
o
r
d
s
,
w
h
ic
h
w
er
e
ex
tr
ac
ted
b
y
T
F
-
I
D
F
i
m
p
r
o
v
ed
al
g
o
r
ith
m
.
Step
8
(
ev
alu
a
tin
g
th
e
ac
cu
r
ac
y
r
ate)
:
in
t
h
is
s
tep
,
t
h
e
k
e
y
w
o
r
d
ex
t
r
ac
tio
n
ac
cu
r
ac
y
o
f
th
e
alg
o
r
it
h
m
is
ca
lc
u
lated
t
h
r
o
u
g
h
th
e
f
o
llo
w
i
n
g
f
o
r
m
u
la:
=
.
.
×
100
(
4
)
w
h
er
e,
th
e
n
u
m
b
er
o
f
co
r
r
ec
t
ex
tr
ac
ted
k
e
y
w
o
r
d
s
ar
e
th
o
s
e
w
o
r
d
s
,
w
h
ich
ar
e
co
m
m
o
n
b
et
w
ee
n
ac
t
u
al
k
e
y
w
o
r
d
s
a
n
d
t
h
e
e
x
tr
ac
ted
o
n
e
b
y
t
h
e
al
g
o
r
ith
m
.
T
h
e
d
o
m
in
ato
r
is
also
th
e
to
tal
n
u
m
b
er
o
f
e
x
tr
ac
ted
w
o
r
d
s
b
y
t
h
e
al
g
o
r
ith
m
as a
k
e
y
w
o
r
d
.
T
h
e
p
s
eu
d
o
-
co
d
e
o
f
t
h
e
p
r
o
p
o
s
ed
k
ey
w
o
r
d
s
ex
tr
ac
tio
n
alg
o
r
ith
m
is
p
r
esen
ted
in
Fig
u
r
e
2
.
T
h
e
alg
o
r
ith
m
i
s
u
n
s
u
p
er
v
is
ed
an
d
co
u
ld
b
e
r
u
n
o
n
th
e
s
i
m
p
le
tex
t.
I
t
m
ea
n
s
th
at
u
n
lik
e
s
u
p
er
v
is
ed
k
e
y
w
o
r
d
ex
tr
ac
tio
n
al
g
o
r
ith
m
s
,
t
h
er
e
is
n
o
n
ee
d
f
o
r
ap
p
r
o
p
r
iate
t
r
ain
in
g
d
ata
s
ets.
As
k
n
o
w
n
as,
p
r
o
v
id
in
g
ap
p
r
o
p
r
iate
tr
ain
i
n
g
d
ata
is
ti
m
e
co
n
s
u
m
i
n
g
an
d
d
i
f
f
ic
u
lt.
I
f
t
h
e
d
ata
i
s
n
o
t
o
f
g
o
o
d
q
u
alit
y
,
it
w
i
ll
l
ea
d
to
a
d
ec
lin
e
in
th
e
ef
f
icie
n
c
y
o
f
t
h
e
s
u
p
er
v
is
e
d
k
e
y
w
o
r
d
ex
tr
ac
tio
n
al
g
o
r
ith
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:
2
0
8
8
-
8708
I
mp
r
o
vin
g
ke
ywo
r
d
ex
tr
a
ctio
n
in
mu
ltil
in
g
u
a
l te
xts (
B
a
h
a
r
eh
Ha
s
h
emza
d
eh
)
5913
1.
B
e
g
i
n
2.
I
f
d
a
t
a
h
a
v
e
A
S
C
I
f
o
r
mat
,
c
h
a
n
g
e
t
h
e
m t
o
U
n
i
c
o
d
e
f
o
r
mat
.
3.
R
e
a
d
i
n
f
o
r
ma
t
i
o
n
f
r
o
m fe
e
d
s w
i
t
h
U
n
i
c
o
d
e
b
y
G
e
t
R
S
S
d
a
t
a
f
u
n
c
t
i
o
n
.
4.
S
t
o
r
e
t
h
e
i
n
f
o
r
mat
i
o
n
i
n
a
d
a
t
a
b
a
se
.
5.
G
e
n
e
r
a
t
e
I
g
n
o
r
e
a
r
r
a
y
b
a
se
d
o
n
p
r
e
p
o
si
t
i
o
n
s,
c
o
n
j
u
n
c
t
i
o
n
s,
a
d
v
e
r
b
s a
n
d
v
e
r
b
s.
6.
R
e
a
d
a
l
l
w
o
r
d
s b
y
G
e
t
W
o
r
d
f
u
n
c
t
i
o
n
a
n
d
s
a
v
e
t
h
e
m i
n
K
e
y
_
w
o
r
d
a
r
r
a
y
.
7.
R
e
mo
v
e
t
h
e
w
o
r
d
s o
f
I
g
n
o
r
e
a
r
r
a
y
f
r
o
m K
e
y
_
w
o
r
d
a
r
r
a
y
.
8.
C
a
l
c
u
l
a
t
e
E
q
u
.
(
3
)
f
o
r
K
e
y
_
w
o
r
d
a
r
r
a
y
b
y
r
u
n
n
i
n
g
T
F
-
I
D
F
a
l
g
o
r
i
t
h
m
.
9.
C
a
l
c
u
l
a
t
e
t
h
e
a
v
e
r
a
g
e
o
f
TF
-
I
D
F
f
o
r
K
e
y
_
w
o
r
d
a
r
r
a
y
i
n
d
i
f
f
e
r
e
n
t
l
a
n
g
u
a
g
e
s.
1
0
.
S
a
v
e
a
n
y
w
o
r
d
s o
f
K
e
y
_
w
o
r
d
a
r
r
a
y
a
s k
e
y
w
o
r
d
s i
f
t
h
e
i
r
a
v
e
r
a
g
e
s T
F
-
I
D
F
a
r
e
h
i
g
h
f
o
r
t
h
e
sa
me
a
n
d
t
h
e
o
t
h
e
r
l
a
n
g
u
a
g
e
s.
1
1
.
C
a
l
c
u
l
a
t
e
E
q
u
.
(
4
)
f
o
r
t
h
e
i
d
e
n
t
i
f
i
e
d
k
e
y
w
o
r
d
s.
1
2
.
En
d
Fig
u
r
e
2
.
T
h
e
p
s
eu
d
o
-
co
d
e
o
f
th
e
p
r
o
p
o
s
ed
alg
o
r
ith
m
5.
E
XP
E
R
I
M
E
NT
A
L
RE
SUL
T
S
T
h
e
p
r
o
p
o
s
ed
alg
o
r
ith
m
w
a
s
p
r
o
g
r
a
m
ed
in
SQ
L
Ser
v
e
r
2
0
1
2
an
d
Vis
u
al
St
u
d
io
2
0
1
3
an
d
s
i
m
u
lat
io
n
s
w
er
e
p
er
f
o
r
m
ed
o
n
t
h
e
I
n
tel
C
o
r
e
i5
,
6
4
B
,
C
P
U
2
.
5
0
GHz
an
d
R
A
M
2
1
GB
.
T
h
e
d
atab
ase
u
s
ed
f
o
r
ev
al
u
ati
n
g
t
h
e
ef
f
icie
n
c
y
an
d
p
er
f
o
r
m
a
n
ce
o
f
t
h
e
p
r
o
p
o
s
ed
k
e
y
w
o
r
d
e
x
tr
ac
tio
n
al
g
o
r
ith
m
h
as
b
ee
n
a
n
o
n
lin
e
d
ata
s
et
co
n
tai
n
i
n
g
2
0
0
n
e
w
s
co
llected
f
r
o
m
B
B
C
w
e
b
s
ite
in
v
ar
io
u
s
la
n
g
u
a
g
es.
E
a
ch
n
e
w
s
i
s
i
n
eig
h
t
lan
g
u
a
g
es.
T
h
e
r
ea
s
o
n
f
o
r
u
s
i
n
g
s
u
c
h
a
d
ataset
w
as
to
p
r
o
v
id
e
u
p
d
ated
in
f
o
r
m
atio
n
,
w
h
i
ch
ar
e
p
r
o
ce
s
s
ed
a
t
th
e
s
a
m
e
ti
m
e
.
T
h
e
p
r
o
p
o
s
ed
m
e
th
o
d
is
ass
es
s
ed
b
y
co
u
n
tin
g
th
e
n
u
m
b
er
o
f
m
a
tch
i
n
g
b
et
w
ee
n
ex
tr
ac
ted
k
e
y
w
o
r
d
s
b
y
t
h
e
p
r
o
p
o
s
ed
m
et
h
o
d
an
d
g
i
v
en
k
e
y
w
o
r
d
s
.
5
.
1
.
T
he
re
s
ults o
f
t
he
pro
po
s
ed
a
lg
o
rit
h
m
An
alg
o
r
it
h
m
is
d
esi
g
n
ed
i
n
t
h
is
s
tu
d
y
,
w
h
ic
h
is
la
n
g
u
a
g
e
in
d
ep
en
d
en
t
a
n
d
h
as
a
s
i
m
p
le
s
tr
u
ct
u
r
e.
I
n
co
n
tr
ac
t
to
lan
g
u
ag
e
-
d
ep
en
d
en
t
al
g
o
r
ith
m
s
(
l
ik
e
[
2
6
]
)
,
w
h
ic
h
ar
e
u
s
i
n
g
t
h
e
P
er
s
ian
r
o
o
ts
f
o
r
k
e
y
w
o
r
d
ex
tr
ac
tio
n
,
t
h
is
al
g
o
r
ith
m
i
s
s
i
m
p
l
y
f
u
n
ct
io
n
al
f
o
r
lar
g
e
d
atab
ases
in
e
v
er
y
la
n
g
u
a
g
e.
I
n
t
h
e
TF
-
I
DF a
lg
o
r
ith
m
,
h
ig
h
-
f
r
eq
u
en
c
y
w
o
r
d
s
in
a
t
ex
t,
b
u
t
i
n
all
lan
g
u
ag
e
s
(
T
F
-
I
DF
m
ea
n
in
all
la
n
g
u
a
g
e
s
)
w
er
e
s
elec
ted
a
s
k
e
y
w
o
r
d
s
a
n
d
t
h
e
ac
c
u
r
ac
y
o
f
t
h
e
al
g
o
r
ith
m
,
co
n
s
id
er
i
n
g
t
h
e
te
x
t
i
n
v
ar
io
u
s
la
n
g
u
ag
e
s
i
s
i
m
p
r
o
v
ed
.
I
t
is
n
o
te
w
o
r
t
h
y
th
at
i
n
a
tex
t
,
n
o
n
-
k
e
y
w
o
r
d
s
,
in
cl
u
d
in
g
v
e
r
b
s
an
d
p
r
e
p
o
s
itio
n
s
ar
e
r
ep
e
ated
,
co
n
s
id
er
ab
ly
,
s
o
,
w
e
s
et
all
n
o
n
-
k
e
y
w
o
r
d
s
a
s
id
e
at
th
e
v
er
y
b
eg
in
n
i
n
g
.
T
h
e
p
r
o
p
o
s
ed
alg
o
r
ith
m
i
s
ap
p
licab
le
to
all
m
u
ltil
i
n
g
u
al
w
eb
s
ites
a
n
d
h
er
e
th
e
r
esu
lts
w
er
e
s
h
o
w
n
j
u
s
t
o
n
B
B
C
Ne
w
s
W
eb
s
ite.
T
h
e
d
atab
ase
u
s
ed
is
co
m
p
r
is
ed
o
f
2
0
0
n
e
w
s
co
lle
cted
f
r
o
m
B
B
C
W
eb
s
ite
in
ei
g
h
t
la
n
g
u
a
g
es
(
a
to
tal
o
f
1
6
0
0
n
e
w
s
)
.
As
ca
n
b
e
s
ee
n
i
n
T
ab
le
1
,
w
o
r
d
s
w
it
h
r
elativ
el
y
h
ig
h
T
F
-
I
DF
(
h
er
e
T
F
-
I
DF
m
o
r
e
th
a
n
2
0
)
w
er
e
co
n
s
id
er
ed
,
w
h
ile
in
th
e
co
n
v
e
n
tio
n
al
T
F
-
I
D
F
alg
o
r
ith
m
,
in
e
v
er
y
lan
g
u
ag
e,
t
h
o
s
e
in
d
ep
en
d
en
t
w
o
r
d
s
w
i
th
h
i
g
h
est
T
F
-
I
D
F
v
al
u
e
is
co
u
n
ted
as
k
e
y
w
o
r
d
s
.
A
s
c
an
b
e
s
ee
n
in
T
ab
le
2
,
in
P
e
r
s
ian
lan
g
u
ag
e,
t
h
e
w
o
r
d
“Am
e
r
ica”
is
d
etec
ted
as
a
k
e
y
w
o
r
d
(
in
t
h
ic
k
en
ed
T
ab
le
2
m
is
ta
k
en
l
y
,
w
h
ile
i
n
E
n
g
l
is
h
la
n
g
u
a
g
e,
t
h
r
e
e
w
o
r
d
s
o
f
“Am
er
ica,
E
n
g
l
a
n
d
,
an
d
L
o
n
d
o
n
”
(
in
t
h
ick
e
n
ed
T
a
b
le
2
w
er
e
m
i
s
tak
e
n
l
y
d
etec
te
d
as
a
k
ey
w
o
r
d
.
I
n
o
th
er
lan
g
u
ag
e
s
,
t
w
o
o
r
th
r
ee
k
e
y
w
o
r
d
s
w
er
e
also
k
n
o
w
n
a
s
k
e
y
w
o
r
d
s
,
m
is
ta
k
e
n
l
y
.
T
ab
le
3
illu
s
tr
ates
th
e
p
r
o
p
o
s
ed
alg
o
r
ith
m
r
es
u
lts
f
o
r
th
e
s
elec
ted
t
ex
t.
A
s
ca
n
b
e
s
ee
n
i
n
t
h
e
tab
le,
th
e
m
ea
n
T
F
-
I
DF
is
ca
lcu
lated
in
ei
g
h
t
la
n
g
u
a
g
es
(
t
h
e
p
r
o
p
o
s
ed
alg
o
r
i
th
m
)
f
o
r
ea
ch
w
o
r
d
d
ep
icted
in
T
ab
le
1
an
d
s
ev
e
n
k
e
y
w
o
r
d
s
w
er
e
s
elec
ted
.
T
h
e
s
elec
ted
k
e
y
w
o
r
d
s
in
th
is
m
et
h
o
d
ar
e
co
n
s
id
er
ed
f
o
r
all
eig
h
t
lan
g
u
a
g
es,
s
u
c
h
th
at
f
o
r
all
la
n
g
u
a
g
es
in
th
is
te
x
t,
k
e
y
w
o
r
d
s
in
th
e
m
ea
n
m
et
h
o
d
,
w
h
ich
ar
e
s
h
o
w
n
i
n
T
ab
le
3
in
cl
u
d
e
Qu
d
s
,
Z
io
n
is
t,
Am
er
i
ca
,
d
em
o
n
s
tr
atio
n
,
p
eo
p
le,
P
a
lest
i
n
e,
an
d
I
r
an
,
i
n
w
h
ich
Am
er
ica
is
d
etec
ted
m
is
tak
e
n
l
y
as
a
k
e
y
w
o
r
d
f
o
r
all
lan
g
u
a
g
e
s
.
Ho
w
ev
er
,
as
w
e
m
en
tio
n
ed
in
T
ab
le
2
,
in
th
e
co
n
v
e
n
tio
n
al
TF
-
I
DF
m
eth
o
d
t
h
e
n
u
m
b
er
o
f
w
r
o
n
g
d
etec
ted
k
e
y
w
o
r
d
s
is
d
if
f
er
en
t
a
n
d
m
o
r
e
th
a
n
o
n
e
w
o
r
d
f
o
r
m
o
s
t
lan
g
u
a
g
es.
I
f
w
e
ev
al
u
ate
t
h
e
ac
cu
r
ac
y
o
f
m
ea
n
T
F
-
I
DF
alg
o
r
it
h
m
(
t
h
e
p
r
o
p
o
s
ed
o
n
e)
an
d
th
at
o
f
th
e
co
n
v
en
t
io
n
al
al
g
o
r
ith
m
,
t
h
e
co
n
v
e
n
tio
n
a
l
al
g
o
r
ith
m
(
wh
ich
i
s
s
h
o
w
n
i
n
T
ab
le
2
)
6
o
f
7
P
er
s
ian
w
o
r
d
s
,
4
o
f
7
E
n
g
li
s
h
w
o
r
d
s
,
an
d
3
o
f
7
A
r
ab
ic
w
o
r
d
s
,
a
s
w
ell
a
s
o
th
er
w
o
r
d
s
i
n
o
th
er
la
n
g
u
a
g
es
w
er
e
d
etec
ted
,
co
r
r
ec
tly
.
I
n
to
tal,
i
n
8
lan
g
u
ag
e
s
an
d
a
m
o
n
g
5
6
-
7
*
8
co
r
r
ec
t
k
e
y
w
o
r
d
s
,
3
9
w
er
e
d
etec
ted
co
r
r
ec
tly
an
d
th
e
ac
c
u
r
ac
y
o
f
th
e
a
lg
o
r
it
h
m
is
0
.
6
9
=3
9
/5
6
,
w
h
ile
in
th
e
m
ea
n
T
F
-
I
DF
m
et
h
o
d
,
6
o
f
7
w
o
r
d
s
w
er
e
d
etec
ted
co
r
r
ec
tly
f
o
r
all
lan
g
u
a
g
es
a
n
d
th
e
ac
cu
r
ac
y
o
f
th
e
alg
o
r
it
h
m
i
s
0
.
8
5
=6
/7
.
T
h
is
is
th
e
ca
s
e
of
th
e
m
ea
n
an
d
m
ax
i
m
u
m
m
eth
o
d
.
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
.
6
,
Dec
em
b
er
2
0
2
0
:
5
9
0
9
-
5
9
1
6
5914
T
ab
le
1
.
T
h
e
T
F
-
I
DF v
al
u
e
f
o
r
w
o
r
d
s
th
at
ar
e
m
o
s
t li
k
el
y
to
b
e
am
o
n
g
t
h
e
k
e
y
w
o
r
d
s
f
o
r
th
e
s
elec
ted
tex
t
T
ab
le
2
.
T
h
e
r
esu
lts
o
f
t
y
p
ical
T
FID
F a
lg
o
r
ith
m
s
,
th
ick
w
o
r
d
s
ar
e
m
is
ta
k
e
n
f
o
r
k
e
y
w
o
r
d
s
T
ab
le
3
.
R
esu
lts
o
f
th
e
p
r
o
p
o
s
ed
alg
o
r
ith
m
,
T
FID
F i
m
p
r
o
v
e
d
t
h
ick
w
o
r
d
s
ar
e
w
o
r
d
s
th
at
ar
e
m
i
s
ta
k
en
l
y
id
en
tifie
d
as k
e
y
w
o
r
d
s
M
a
x
i
m
u
m
M
e
t
h
o
d
(
S
e
l
e
c
t
e
d
K
e
y
w
o
r
d
s fo
r
A
n
y
8
L
a
n
g
u
a
g
e
s)
M
e
d
i
u
m
M
e
t
h
o
d
(
S
e
l
e
c
t
e
d
K
e
y
w
o
r
d
s fo
r
A
l
l
8
L
a
n
g
u
a
g
e
s)
A
v
e
r
a
g
e
me
t
h
o
d
(
S
e
l
e
c
t
e
d
k
e
y
w
o
r
d
s fo
r
a
l
l
8
l
a
n
g
u
a
g
e
s)
R
i
g
h
t
k
e
y
w
o
r
d
s
50
M
a
r
c
h
50
M
a
r
c
h
47
G
h
o
d
s
M
a
r
c
h
47
G
h
o
d
s
47
G
h
o
d
s
4
0
.
1
2
Z
i
o
n
i
st
G
h
o
d
s
43
Z
i
o
n
i
st
43
Z
i
o
n
i
st
3
8
.
8
7
A
m
e
r
i
c
a
G
l
o
b
a
l
43
A
m
e
r
i
c
a
43
A
m
e
r
i
c
a
3
6
.
8
7
M
a
r
c
h
Z
i
o
n
i
st
40
P
a
l
e
st
i
n
e
38
P
e
o
p
l
e
2
9
.
2
5
P
e
o
p
l
e
I
r
a
n
29
T
e
r
r
o
r
i
st
2
3
.
5
P
a
l
e
st
i
n
e
2
5
.
8
7
P
a
l
e
st
i
n
e
P
e
o
p
l
e
38
P
e
o
p
l
e
21
I
r
a
n
22
I
r
a
n
P
a
l
e
st
i
n
e
5
.
2
.
T
he
co
m
pa
riso
n o
f
t
he
o
bta
ined re
s
ults
w
it
h
t
he
o
t
her
re
la
t
ed
a
lg
o
rit
hm
s
T
o
ev
alu
ate
th
e
e
f
f
icien
c
y
a
n
d
p
er
f
o
r
m
an
ce
,
t
h
e
r
ate
o
f
ac
cu
r
ac
y
o
f
th
e
p
r
o
p
o
s
ed
alg
o
r
ith
m
is
co
m
p
ar
ed
w
it
h
th
at
o
f
th
e
o
th
er
m
et
h
o
d
s
.
T
h
e
alg
o
r
ith
m
w
as
te
s
ted
w
it
h
2
0
0
tex
ts
i
n
eig
h
t
la
n
g
u
a
g
es,
w
h
ic
h
ar
e
s
h
o
w
n
i
n
T
ab
le
1
,
an
d
1
2
0
0
co
r
r
ec
t
k
e
y
wo
r
d
s
w
er
e
ac
h
iev
ed
.
T
h
e
r
ate
o
f
ac
cu
r
ac
y
of
th
e
co
n
v
e
n
tio
n
al
T
F
-
I
DF
al
g
o
r
ith
m
f
o
r
1
0
1
4
c
o
r
r
ec
t
w
o
r
d
s
an
d
1
6
7
2
o
b
tain
ed
k
ey
w
o
r
d
s
is
6
0
.
6
%
,
w
h
ile
t
h
e
p
r
o
p
o
s
ed
alg
o
r
ith
m
,
n
a
m
el
y
t
h
e
m
ea
n
.
TF
-
I
DF,
f
o
r
1
1
6
4
c
o
r
r
ec
t
w
o
r
d
s
o
f
1
2
7
5
w
o
r
d
s
,
th
e
r
ate
is
9
1
.
3
%.
I
n
th
e
p
r
o
p
o
s
ed
alg
o
r
ith
m
w
it
h
th
e
m
ed
ia
n
m
et
h
o
d
,
1
0
9
2
c
o
r
r
e
ct
w
o
r
d
s
o
f
1
4
5
6
w
o
r
d
s
in
d
icate
th
e
r
ate
o
f
7
5
%.
Mo
r
eo
v
er
,
if
w
e
ca
lc
u
late
th
e
ac
c
u
r
ac
y
r
ate
f
o
r
th
e
m
a
x
i
m
u
m
m
et
h
o
d
,
1
0
2
1
co
r
r
ec
t
w
o
r
d
s
o
f
1
5
3
1
w
o
r
d
s
b
y
t
h
e
ac
c
u
r
ac
y
r
ate
o
f
6
6
.
6
%
is
o
b
tai
n
ed
.
T
h
e
r
ate
o
f
ac
cu
r
ac
y
f
o
r
g
r
ap
h
-
b
a
s
ed
alg
o
r
it
h
m
[
2
7
]
f
o
r
th
ese
d
ata
is
8
0
%.
C
o
n
c
er
n
in
g
th
e
o
b
tain
ed
r
ates,
m
ea
n
w
ith
t
h
e
ac
cu
r
ac
y
r
ate
o
f
9
1
.
3
%
is
th
e
b
est
m
et
h
o
d
.
T
ab
le
4
s
h
o
w
s
t
h
e
s
u
m
m
ar
y
o
f
r
e
s
u
lt
s
o
n
B
B
C
d
at
a.
T
h
is
s
u
g
g
e
s
ts
t
h
at
t
h
e
p
r
o
p
o
s
ed
alg
o
r
ith
m
n
o
t
o
n
l
y
e
x
tr
ac
ted
th
e
k
e
y
w
o
r
d
s
l
an
g
u
a
g
e
in
d
ep
en
d
e
n
t
,
b
u
t
h
a
s
ac
h
iev
ed
a
co
n
s
id
er
ab
ly
b
ett
er
r
esu
lts
.
T
ab
le
5
s
h
o
w
s
c
o
m
p
ar
i
s
o
n
t
h
e
alg
o
r
it
h
m
w
it
h
o
th
er
r
elate
d
alg
o
r
ith
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:
2
0
8
8
-
8708
I
mp
r
o
vin
g
ke
ywo
r
d
ex
tr
a
ctio
n
in
mu
ltil
in
g
u
a
l te
xts (
B
a
h
a
r
eh
Ha
s
h
emza
d
eh
)
5915
T
ab
le
4
.
Su
g
g
e
s
ted
alg
o
r
it
h
m
ac
cu
r
ac
y
r
ates a
n
d
k
e
y
w
o
r
d
s
e
x
tr
ac
tio
n
al
g
o
r
ith
m
s
o
n
B
B
C
d
ata
A
l
g
o
r
i
t
h
m
TF
-
I
D
F
M
a
x
i
m
u
m
su
g
g
e
st
i
o
n
TF
-
I
D
F
S
u
g
g
e
st
i
o
n
mi
d
d
l
e
w
a
r
e
TF
-
I
D
F
S
u
g
g
e
st
e
d
a
v
e
r
a
g
e
G
r
a
p
h
[
2
7
]
T
F
-
I
D
F
n
o
r
mal
A
c
c
u
r
a
c
y
r
a
t
e
6
6
.
6
%
7
5
%
9
1
.
3
%
8
0
%
6
0
.
6
%
T
ab
le
5
.
C
o
m
p
ar
in
g
t
h
e
alg
o
r
i
th
m
w
it
h
o
th
er
r
elate
d
alg
o
r
ith
m
s
A
l
g
o
r
i
t
m
A
c
c
u
r
a
c
y
T
h
e
P
r
o
p
o
se
d
A
l
g
o
r
i
t
h
m
9
1
.
3
%
G
r
a
p
h
[
2
7
]
8
0
%
Kp
[
2
8
]
4
7
.
7
%
M
S
F
[
2
9
]
6
0
%
G
A
T
E
[
3
0
]
6
4
.
4
%
H
a
b
i
b
i
[
1
]
7
5
%
S
i
n
g
l
e
-
D
o
c
u
me
n
t
[
3
1
]
8
3
.
2
%
6.
CO
NCLU
SI
O
N
Data
r
etr
iev
al
is
w
id
el
y
ap
p
lied
in
ev
er
y
d
a
y
lif
e.
I
n
cr
ea
s
i
n
g
t
h
e
ef
f
ic
ien
c
y
an
d
p
er
f
o
r
m
an
ce
o
f
in
f
o
r
m
atio
n
r
etr
ie
v
al
s
y
s
te
m
s
is
v
er
y
i
m
p
o
r
tan
t
f
o
r
th
eir
d
esig
n
er
s
.
W
e
r
ea
lized
b
ased
o
n
in
v
e
s
ti
g
ati
n
g
th
e
ap
p
licatio
n
s
o
f
t
h
e
d
ata
r
etr
iev
al
a
n
d
tex
t
m
i
n
i
n
g
th
at
th
e
k
e
y
w
o
r
d
s
o
f
a
tex
t
ar
e
i
m
p
o
r
tan
t
an
d
f
ac
ilit
a
te
th
e
o
r
ian
tatio
n
s
o
f
th
e
p
r
o
ce
s
s
es.
Fo
r
ex
a
m
p
le,
b
y
f
i
n
d
in
g
t
h
e
k
e
y
w
o
r
d
s
i
n
th
e
n
e
w
s
o
r
s
o
m
e
s
en
te
n
ce
s
w
i
th
m
o
r
e
k
e
y
w
o
r
d
s
,
w
e
co
u
ld
s
u
m
m
ar
ize
o
r
co
m
p
r
eh
e
n
d
t
h
e
te
x
t
m
o
r
e
ea
s
i
l
y
.
T
o
ac
h
iev
e
to
t
h
is
ai
m
,
an
u
n
s
u
p
e
r
v
is
ed
k
e
y
w
o
r
d
s
ex
tr
ac
tio
n
alg
o
r
ith
m
is
p
r
o
p
o
s
ed
b
ased
o
n
i
m
p
r
o
v
in
g
th
e
T
F
-
I
DF
al
g
o
r
ith
m
f
o
r
m
u
lti
-
la
n
g
u
a
g
e
tex
ts
.
I
n
t
h
e
p
r
o
p
o
s
ed
alg
o
r
ith
m
,
th
e
av
er
ag
e
T
F
-
I
DF
o
f
th
e
ca
n
d
id
ate
w
o
r
d
s
w
er
e
ca
lcu
lated
f
o
r
th
e
s
a
m
e
an
d
th
e
o
t
h
er
lan
g
u
a
g
es.
T
h
en
t
h
e
w
o
r
d
s
wit
h
t
h
e
h
i
g
h
er
a
v
er
ag
es
T
F
-
I
DF
w
er
e
c
h
o
s
en
a
s
th
e
e
x
tr
ac
ted
k
e
y
w
o
r
d
s
.
A
d
at
ab
ase,
w
h
ic
h
w
a
s
co
llected
2
0
0
n
e
w
s
f
r
o
m
B
B
C
w
eb
s
ite
in
v
ar
io
u
s
lan
g
u
ag
e
s
,
w
a
s
co
n
s
id
er
ed
to
ev
al
u
ate
t
h
e
ef
f
icie
n
c
y
o
f
t
h
e
p
r
o
p
o
s
ed
alg
o
r
ith
m
.
T
h
e
e
x
p
er
i
m
e
n
t
al
r
esu
lt
s
s
h
o
w
th
at
th
e
s
elec
ted
k
e
y
w
o
r
d
s
ar
e
m
o
r
e
s
i
m
ilar
to
th
e
m
e
n
tio
n
ed
k
e
y
w
o
r
d
s
b
y
t
h
e
w
eb
s
ite
an
d
th
i
s
co
n
f
ir
m
s
th
e
r
eliab
ilit
y
o
f
th
e
al
g
o
r
ith
m
.
T
h
e
o
v
er
all
ac
cu
r
ac
y
r
ate
o
f
th
e
alg
o
r
it
h
m
i
s
9
1
.
3
%
th
at
it
is
h
ig
h
er
th
a
n
th
e
s
tate
-
of
-
th
e
-
ar
t
k
e
y
w
o
r
d
ex
tr
ac
tio
n
al
g
o
r
it
h
m
s
.
W
e
w
o
u
ld
lik
e
to
i
n
tr
o
d
u
ce
th
r
ee
s
tr
ateg
ies
a
s
o
u
r
f
u
t
u
r
e
w
o
r
k
s
,
to
i
m
p
r
o
v
e
th
e
p
r
o
p
o
s
ed
alg
o
r
ith
m
i
n
ap
p
licatio
n
,
co
m
p
le
x
it
y
an
d
ti
m
e.
Fin
d
i
n
g
co
m
p
le
x
k
e
y
w
o
r
d
s
co
u
ld
b
e
ad
d
ed
t
o
th
e
alg
o
r
ith
m
,
r
ea
l
-
ti
m
e
an
d
o
n
-
l
in
e
b
eh
av
io
u
r
co
u
ld
b
e
cr
ea
ted
b
y
f
o
cu
s
i
n
g
o
n
p
ar
allel
p
r
o
ce
s
s
in
g
a
n
d
n
o
r
m
al
izin
g
t
h
e
f
ee
d
s
’
ad
d
r
ess
e
s
co
u
ld
b
e
co
n
s
id
er
ed
to
f
ac
ilit
ate
ac
ce
s
s
.
RE
F
E
R
E
NC
E
S
[1
]
M.
Ha
b
ib
i
a
n
d
A
.
P
o
p
e
sc
u
-
B
e
li
s,
“
Ke
y
w
o
rd
e
x
trac
ti
o
n
a
n
d
c
lu
ste
rin
g
f
o
r
d
o
c
u
m
e
n
t
re
c
o
m
m
e
n
d
a
ti
o
n
in
c
o
n
v
e
rsa
ti
o
n
s
,”
IEE
E/
ACM
T
ra
n
sa
c
ti
o
n
s
o
n
a
u
d
io
,
sp
e
e
c
h
,
a
n
d
l
a
n
g
u
a
g
e
p
ro
c
e
ss
in
g
,
v
o
l.
23
,
n
o
.
4
,
p
p
.
7
4
6
-
7
5
9
,
2
0
1
5
.
[2
]
M.
S
a
v
ić,
e
t
a
l.
,
“
A
lan
g
u
a
g
e
-
in
d
e
p
e
n
d
e
n
t
a
p
p
r
o
a
c
h
t
o
t
h
e
e
x
trac
ti
o
n
o
f
d
e
p
e
n
d
e
n
c
i
e
s
b
e
tw
e
e
n
so
u
rc
e
c
o
d
e
e
n
ti
ti
e
s
,”
In
f
o
rm
a
ti
o
n
a
n
d
S
o
f
twa
re
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
56
,
n
o
.
10
,
p
p
.
1
2
6
8
-
1
2
8
8
,
2
0
1
4
.
[3
]
S.
S
i
d
d
i
q
i
a
n
d
A
.
S
h
a
ra
n
,
“
Ke
y
w
o
rd
a
n
d
k
e
y
p
h
ra
se
e
x
trac
ti
o
n
tec
h
n
i
q
u
e
s:
a
li
tera
t
u
re
re
v
iew
,”
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
Co
m
p
u
ter
A
p
p
l
ica
ti
o
n
s
,
v
o
l.
1
0
9
,
n
o
.
2
,
p
p
.
1
8
-
2
3
,
2
0
1
5
.
[4
]
T
.
S
.
Ch
u
n
g
,
e
t
a
l.
,
“
A
su
rv
e
y
o
f
f
la
sh
tran
sla
ti
o
n
lay
e
r
,”
J
o
u
rn
a
l
o
f
S
y
ste
ms
Arc
h
it
e
c
tu
re
,
v
o
l.
55
,
n
o
.
5
-
6
,
p
p
.
3
3
2
-
343
,
2
0
0
9
.
[5
]
N.
I.
A
b
d
u
lk
h
a
leq
,
e
t
a
l.
,
“
Im
p
ro
v
in
g
th
e
d
a
ta
re
c
o
v
e
r
y
f
o
r
sh
o
rt
len
g
th
L
T
c
o
d
e
s
,”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
El
e
c
trica
l
&
Co
mp
u
ter
En
g
in
e
e
ri
n
g
,
v
o
l.
10
,
n
o
.
2
,
p
p
.
1
9
7
2
-
1
9
7
9
,
2
0
2
0
.
[6
]
N.
N
.
Ku
lk
a
rn
i
a
n
d
S
.
A
.
Ja
in
,
“
Ch
e
c
k
in
g
in
teg
rit
y
o
f
d
a
ta
a
n
d
re
c
o
v
e
r
y
in
th
e
c
lo
u
d
e
n
v
iro
n
m
e
n
t
,”
In
d
o
n
e
sia
n
J
o
u
rn
a
l
o
f
El
e
c
trica
l
En
g
in
e
e
rin
g
a
n
d
Co
m
p
u
ter
S
c
ien
c
e
(
IJ
EE
CS
)
,
v
o
l.
13
,
n
o
.
2
, p
p
.
6
2
6
-
6
3
3
,
2
0
1
9
.
[7
]
E.
Ca
m
b
ria
a
n
d
B.
W
h
it
e
,
“
Ju
m
p
in
g
NL
P
c
u
rv
e
s:
A
re
v
ie
w
o
f
n
a
tu
r
a
l
la
n
g
u
a
g
e
p
ro
c
e
ss
in
g
re
se
a
rc
h
,”
IEE
E
Co
mp
u
t
a
ti
o
n
a
l
i
n
telli
g
e
n
c
e
ma
g
a
zin
e
,
v
o
l.
9
,
n
o
.
2
,
p
p
.
4
8
-
57
,
2
0
1
4
.
[8
]
V
.
Ja
in
a
n
d
S
.
V.
A
.
V
.
P
ra
sa
d
,
“
On
to
lo
g
y
b
a
se
d
in
f
o
r
m
a
ti
o
n
re
tri
e
v
a
l
m
o
d
e
l
in
se
m
a
n
ti
c
we
b
:
a
re
v
ie
w
,”
In
ter
n
a
t
io
n
a
l
J
o
u
rn
a
l
o
f
Ad
v
a
n
c
e
d
Res
e
a
rc
h
in
Co
mp
u
ter
S
c
ie
n
c
e
a
n
d
S
o
ft
wa
re
En
g
i
n
e
e
rin
g
,
v
o
l.
4
,
n
o
.
8
,
p
p
.
8
3
7
-
8
4
2
,
2
0
1
4
.
[9
]
K.
Kim
,
e
t
a
l.
,
“
L
a
n
g
u
a
g
e
in
d
e
p
e
n
d
e
n
t
se
m
a
n
ti
c
k
e
rn
e
l
s
f
o
r
sh
o
rt
-
tex
t
c
las
sif
ic
a
ti
o
n
,”
Exp
e
rt
S
y
ste
ms
wit
h
Ap
p
li
c
a
ti
o
n
s
,
v
o
l
.
41
,
n
o
.
2
,
p
p
.
7
3
5
-
7
4
3
,
201
4
.
[1
0
]
D.
De
sh
w
a
l,
e
t
a
l.
,
“
F
e
a
tu
re
E
x
trac
ti
o
n
M
e
th
o
d
s
in
L
a
n
g
u
a
g
e
Id
e
n
ti
f
ica
ti
o
n
:
A
S
u
rv
e
y
,”
W
ir
e
les
s
Per
so
n
a
l
Co
mm
u
n
ica
ti
o
n
s
,
v
o
l
.
1
0
7
,
p
p
.
2
0
7
1
-
2
1
0
3
,
2
0
1
9
.
[1
1
]
S
.
K.
Bh
a
rti
a
n
d
K.
S
.
Ba
b
u
,
“
A
u
to
m
a
ti
c
k
e
y
w
o
rd
e
x
trac
ti
o
n
f
o
r
tex
t
su
m
m
a
riz
a
ti
o
n
:
A
su
rv
e
y
,”
a
rXiv
p
re
p
rin
t
a
rXiv:1
7
0
4
.
0
3
2
4
2
,
2
0
1
7
.
[1
2
]
E.
F
e
rra
ra
,
e
t
a
l.
,
“
W
e
b
d
a
ta
e
x
trac
ti
o
n
,
a
p
p
li
c
a
ti
o
n
s
a
n
d
tec
h
n
iq
u
e
s:
A
su
rv
e
y
,”
Kn
o
wled
g
e
-
b
a
se
d
sy
ste
ms
,
v
o
l.
70
,
p
p
.
3
0
1
-
323
,
2
0
1
4
.
[1
3
]
P.
T
u
rn
e
y
,
“
Lea
rn
in
g
to
e
x
trac
t
k
e
y
p
h
ra
se
s f
ro
m
te
x
t
,”
Na
ti
o
n
a
l
Res
e
a
rc
h
Co
u
n
c
il
Ca
n
a
d
a
,
2
0
0
2
.
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
.
6
,
Dec
em
b
er
2
0
2
0
:
5
9
0
9
-
5
9
1
6
5916
[1
4
]
S
.
S
.
Ho
n
g
,
e
t
a
l.
,
“
T
h
e
f
e
a
tu
re
se
lec
ti
o
n
m
e
th
o
d
b
a
se
d
o
n
g
e
n
e
ti
c
a
lg
o
rit
h
m
f
o
r
e
ff
icie
n
t
o
f
te
x
t
c
lu
ste
rin
g
a
n
d
tex
t
c
las
si
f
ica
ti
o
n
,”
In
t
e
rn
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
Ad
v
a
n
c
e
s
in
S
o
ft
Co
mp
u
t
in
g
a
n
d
i
ts
Ap
p
l
ica
ti
o
n
s
,
v
o
l.
7
,
n
o
.
1
,
p
p
.
2
2
-
40
,
2
0
1
5
.
[1
5
]
E.
F
ra
n
k
,
e
t
a
l.
,
“
Do
m
a
in
-
sp
e
c
if
ic
k
e
y
p
h
ra
s
e
e
x
trac
ti
o
n
,”
in
1
6
th
In
ter
n
a
ti
o
n
a
l
j
o
in
t
c
o
n
fer
e
n
c
e
o
n
a
rtif
icia
l
in
telli
g
e
n
c
e
(
IJ
CAI
9
9
)
,
v
o
l.
2
,
p
p
.
6
6
8
-
6
7
3
,
1
9
9
9
.
[1
6
]
C.
Ca
ra
g
e
a
,
e
t
a
l.
,
“
Cit
a
ti
o
n
-
e
n
h
a
n
c
e
d
k
e
y
p
h
ra
se
e
x
tra
c
ti
o
n
f
ro
m
re
s
e
a
rc
h
p
a
p
e
rs:
A
su
p
e
rv
ise
d
a
p
p
ro
a
c
h
,”
in
Pro
c
e
e
d
in
g
s
o
f
th
e
2
0
1
4
C
o
n
fer
e
n
c
e
o
n
Em
p
irica
l
M
e
th
o
d
s
in
Na
t
u
ra
l
L
a
n
g
u
a
g
e
Pr
o
c
e
ss
in
g
(
EM
NL
P)
,
p
p
.
1
4
3
5
-
1
4
4
6
,
2
0
1
4
.
[1
7
]
G
.
Erc
a
n
a
n
d
I.
Cice
k
li
,
“
Us
in
g
lex
ica
l
c
h
a
in
s
f
o
r
k
e
y
w
o
rd
e
x
tra
c
ti
o
n
,”
In
f
o
rm
a
ti
o
n
Pro
c
e
ss
in
g
&
M
a
n
a
g
e
me
n
t
,
v
o
l.
43
,
n
o
.
6
,
p
p
.
1
7
0
5
-
1
7
1
4
,
2
0
0
7
.
[1
8
]
F.
F
k
ih
a
n
d
M
.
N.
Om
ri,
“
Co
m
p
lex
ter
m
in
o
lo
g
y
e
x
trac
ti
o
n
m
o
d
e
l
f
ro
m
u
n
stru
c
tu
re
d
w
e
b
tex
t
b
a
se
d
li
n
g
u
isti
c
a
n
d
sta
ti
stica
l
k
n
o
w
led
g
e
,”
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
I
n
fo
rm
a
ti
o
n
Retrie
v
a
l
Res
e
a
rc
h
,
v
o
l.
2
,
n
o
.
3
,
p
p
.
1
-
18
,
2
0
1
3
.
[1
9
]
G
.
F
ig
u
e
ro
a
,
e
t
a
l.
,
“
Ra
n
k
Up
:
En
h
a
n
c
in
g
g
ra
p
h
-
b
a
se
d
k
e
y
p
h
ra
se
e
x
tra
c
ti
o
n
m
e
th
o
d
s
w
it
h
e
rro
r
-
f
e
e
d
b
a
c
k
p
ro
p
a
g
a
ti
o
n
,”
Co
m
p
u
ter
S
p
e
e
c
h
&
L
a
n
g
u
a
g
e
,
v
o
l.
47
,
p
p
.
1
1
2
-
1
3
1
,
2
0
1
8
.
[2
0
]
S.
L
a
h
iri
,
e
t
a
l.
,
“
Ke
y
wo
rd
a
n
d
k
e
y
p
h
ra
se
e
x
tra
c
ti
o
n
u
sin
g
c
e
n
tr
a
li
ty
m
e
a
su
re
s
o
n
c
o
ll
o
c
a
ti
o
n
n
e
t
w
o
rk
s
,”
a
rXiv
p
re
p
rin
t
a
rXiv:1
4
0
1
.
6
5
7
1
,
2
0
1
4
.
[2
1
]
P.
T
o
n
e
ll
a
,
e
t
a
l.
,
“
Us
in
g
k
e
y
w
o
rd
e
x
trac
ti
o
n
f
o
r
we
b
site
c
lu
ste
rin
g
,”
in
Fi
ft
h
IEE
E
I
n
ter
n
a
t
io
n
a
l
W
o
rk
sh
o
p
o
n
W
e
b
S
it
e
Evo
l
u
ti
o
n
,
2
0
0
3
.
T
h
e
me
:
Arc
h
it
e
c
tu
re
.
Pro
c
e
e
d
i
n
g
s
,
p
p
.
4
1
-
4
8
,
2
0
0
3
.
[2
2
]
S
.
K.
Bisw
a
s,
e
t
a
l.
,
“
A
g
ra
p
h
b
a
se
d
k
e
y
w
o
rd
e
x
trac
ti
o
n
m
o
d
e
l
u
s
in
g
c
o
ll
e
c
ti
v
e
n
o
d
e
w
e
ig
h
t
,”
Exp
e
rt
S
y
ste
ms
wit
h
Ap
p
li
c
a
ti
o
n
s
,
v
o
l
.
97
,
p
p
.
5
1
-
59
,
2
0
1
8
.
[2
3
]
R.
M
ih
a
lce
a
a
n
d
P
.
T
a
ra
u
,
“
T
e
x
tr
a
n
k
:
Brin
g
in
g
o
r
d
e
r
in
t
o
tex
t
,”
i
n
Pro
c
e
e
d
in
g
s
o
f
t
h
e
2
0
0
4
c
o
n
fer
e
n
c
e
o
n
e
mp
irica
l
me
th
o
d
s
i
n
n
a
t
u
ra
l
la
n
g
u
a
g
e
p
ro
c
e
ss
in
g
,
p
p
.
4
0
4
-
4
1
1
,
2
0
0
4
.
[2
4
]
S.
Du
a
ri
a
n
d
V
.
Bh
a
t
n
a
g
a
r,
“
sC
AK
E:
S
e
m
a
n
ti
c
Co
n
n
e
c
ti
v
it
y
Aw
a
r
e
Ke
y
w
o
rd
Ex
trac
ti
o
n
,”
J
o
u
rn
a
l
o
f
In
f
o
rm
a
ti
o
n
S
c
ien
c
e
s
,
v
o
l.
4
7
7
,
p
p
.
1
0
0
-
1
1
7
,
2
0
1
9
.
[2
5
]
K.
S
.
Ha
sa
n
a
n
d
V
.
Ng
,
“
Co
n
u
n
d
ru
m
s
in
u
n
su
p
e
rv
ise
d
k
e
y
p
h
ra
se
e
x
trac
ti
o
n
:
m
a
k
in
g
s
e
n
se
o
f
th
e
sta
te
-
of
-
th
e
-
a
rt
,”
in
Pro
c
e
e
d
i
n
g
s
o
f
t
h
e
2
3
rd
I
n
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
C
o
mp
u
ta
ti
o
n
a
l
L
i
n
g
u
isti
c
s: P
o
ste
rs
,
p
p
.
3
6
5
-
3
7
3
,
2
0
1
0
.
[2
6
]
R
.
F
a
rh
a
d
,
e
t
a
l.
,
“
Im
p
ro
v
e
d
Clu
ste
rin
g
P
e
rsia
n
T
e
x
t
Ba
se
d
o
n
Ke
y
w
o
rd
Us
in
g
L
in
g
u
ist
ic
a
n
d
T
h
e
sa
u
ru
s
Kn
o
w
led
g
e
,”
S
ig
n
a
l
a
n
d
Da
t
a
Pr
o
c
e
ss
in
g
,
v
o
l
.
13
,
n
o
.
1
, p
p
.
8
7
-
1
0
0
,
2
0
1
6
.
[2
7
]
A
.
R.
Na
b
h
a
n
a
n
d
K.
S
h
a
a
lan
,
“
Ke
y
w
o
rd
id
e
n
ti
f
ica
ti
o
n
u
si
n
g
tex
t
g
ra
p
h
let
p
a
tt
e
rn
s
,”
i
n
In
ter
n
a
ti
o
n
a
l
C
o
n
fer
e
n
c
e
o
n
A
p
p
li
c
a
ti
o
n
s
o
f
N
a
tu
r
a
l
L
a
n
g
u
a
g
e
t
o
In
fo
rm
a
ti
o
n
S
y
ste
ms
,
p
p
.
1
5
2
-
1
6
1
,
2
0
1
6
.
[2
8
]
C.
B.
A
li
,
e
t
a
l.
,
“
A
tw
o
-
lev
e
l
k
e
y
p
h
ra
se
e
x
tra
c
ti
o
n
a
p
p
ro
a
c
h
,”
in
In
ter
n
a
ti
o
n
a
l
C
o
n
fer
e
n
c
e
o
n
In
telli
g
e
n
t
T
e
x
t
Pro
c
e
ss
in
g
a
n
d
Co
mp
u
t
a
ti
o
n
a
l
L
i
n
g
u
isti
c
s
,
p
p
.
3
9
0
-
4
0
1
,
2
0
1
5
.
[2
9
]
D.
Y.
L
e
e
,
e
t
a
l.
,
“
A
N
e
w
E
x
trac
ti
o
n
A
l
g
o
rit
h
m
f
o
r
Hie
r
a
rc
h
ica
l
Ke
y
w
o
rd
Us
in
g
Tex
t
S
o
c
ial
Ne
t
w
o
rk
,
”
in
In
fo
rm
a
t
io
n
S
c
ien
c
e
a
n
d
Ap
p
li
c
a
ti
o
n
s (
ICIS
A)
2
0
1
6
,
p
p
.
9
0
3
-
9
1
2
,
2
0
1
6
.
[3
0
]
P.
Ne
si,
e
t
a
l.
,
“
A
Distrib
u
ted
F
ra
m
e
w
o
rk
f
o
r
N
L
P
-
Ba
se
d
Ke
y
w
o
rd
a
n
d
Ke
y
p
h
ra
se
Ex
trac
ti
o
n
F
ro
m
W
e
b
P
a
g
e
s a
n
d
Do
c
u
m
e
n
ts
,”
in
2
1
st
In
ter
n
a
ti
o
n
a
l
Co
n
fer
e
n
c
e
o
n
Distri
b
u
ted
M
u
lt
i
me
d
ia
S
y
ste
ms
(
DM
S
2
0
1
5
)
,
p
p
.
1
-
7,
2
0
1
5
.
[3
1
]
F.
Ro
u
ss
e
a
u
a
n
d
M
.
V
a
z
irg
ian
n
is
,
“
M
a
i
n
c
o
re
re
ten
ti
o
n
o
n
g
ra
p
h
-
of
-
w
o
rd
s
f
o
r
sin
g
le
-
d
o
c
u
m
e
n
t
k
e
y
w
o
rd
e
x
trac
ti
o
n
,”
in
E
u
ro
p
e
a
n
Co
n
fer
e
n
c
e
o
n
I
n
f
o
rm
a
ti
o
n
Retrie
v
a
l
,
p
p
.
3
8
2
-
3
9
3
,
2
0
1
5
.
B
I
O
G
RAP
H
I
E
S
O
F
AUTH
O
RS
B
a
h
a
r
e
H
a
she
m
z
a
d
e
is
lec
tu
rin
g
a
n
d
re
se
a
rc
h
in
g
a
t
El
e
c
tri
c
a
l
a
n
d
Co
m
p
u
ter
En
g
in
e
e
rin
g
,
Un
iv
e
rsit
y
o
f
T
o
rb
a
t
He
y
d
a
rieh
fro
m
2
0
1
6
.
S
h
e
h
a
s
g
ra
d
u
a
ted
a
t
M
.
S
c
.
o
f
In
f
o
rm
a
ti
o
n
S
c
ien
c
e
f
ro
m
Birj
a
n
d
Un
iers
it
y
in
2
0
1
5
.
He
r
in
tere
st
f
ield
s
a
re
in
f
o
r
m
a
ti
o
n
tec
h
n
o
lo
g
y
,
o
b
f
u
sc
a
ti
o
n
a
n
d
d
a
ta m
in
in
g
.
M
a
jid
Abd
o
lr
a
z
z
a
g
h
-
N
e
z
h
a
d
is
lec
tu
rin
g
a
n
d
re
se
a
rc
h
in
g
a
s
a
ss
ist
a
n
t
p
ro
f
e
ss
o
r
a
t
th
e
c
o
m
p
u
ter
e
n
g
in
e
e
rin
g
d
e
p
a
rtme
n
t
o
f
th
e
Un
iv
e
rsit
y
o
f
Bo
z
o
rg
m
e
h
r
Q
a
e
n
a
t
sin
c
e
2
0
1
3
a
n
d
d
e
a
n
th
e
d
e
p
a
rtm
e
n
t
sin
c
e
2
0
1
6
.
He
w
a
s
d
e
a
n
o
f
th
e
f
a
c
u
lt
y
o
f
c
o
m
p
u
ter
sc
ien
c
e
b
e
tw
e
e
n
2
0
1
3
t
o
2
0
1
6
.
A
b
d
o
lraz
z
a
g
h
-
Ne
z
h
a
d
S
u
p
p
o
rts
M
a
ste
r
a
n
d
P
h
D
stu
d
e
n
ts
o
f
Isla
m
i
c
Az
a
d
Un
iv
e
rsit
y
o
f
Birj
a
n
d
si
n
c
e
2
0
1
6
.
He
h
a
s g
ra
d
u
a
ted
a
t
P
h
D i
n
C
o
m
p
u
ter
S
c
ien
c
e
f
ro
m
In
f
o
r
m
a
ti
o
n
S
c
ien
c
e
a
n
d
T
e
c
h
n
o
lo
g
y
,
F
a
c
u
lt
y
o
f
th
e
N
a
ti
o
n
a
l
Un
iv
e
rsit
y
o
f
M
a
la
y
sia
(UK
M
)
in
2
0
1
3
.
A
lso
,
h
e
re
c
e
iv
e
d
h
is
m
a
ste
r
d
e
g
re
e
o
f
Op
e
ra
ti
o
n
R
e
se
a
rc
h
f
ro
m
Un
iv
e
rsit
y
o
f
S
istan
a
n
d
Bl
o
c
h
sta
n
in
2
0
0
7
,
a
n
d
h
is
b
a
c
h
e
lo
r’s
d
e
g
re
e
f
ro
m
Un
iv
e
rs
it
y
o
f
Birj
a
n
d
in
2
0
0
4
.
His
in
tere
st
f
ield
s
a
re
a
rti
f
icia
l
in
telli
g
e
n
t,
o
p
ti
m
iza
ti
o
n
,
d
a
ta
m
in
in
g
,
sc
h
e
d
u
li
n
g
a
n
d
u
n
c
e
rt
a
in
sy
ste
m
s.
He
is
a
y
o
u
n
g
P
r
o
f
e
ss
io
n
a
ls
m
e
m
b
e
r
o
f
th
e
In
stit
u
te
o
f
El
e
c
tri
c
a
l
a
n
d
El
e
c
tro
n
ics
En
g
in
e
e
rin
g
(IE
EE
)
a
n
d
re
v
ie
w
e
r
o
f
v
a
li
d
jo
u
r
n
a
ls
su
c
h
a
s
In
f
o
rm
a
ti
o
n
S
c
ien
c
e
s,
A
p
p
li
e
d
S
o
f
t
Co
m
p
u
ti
n
g
,
S
o
f
t
Co
m
p
u
ti
n
g
,
In
ter
n
a
ti
o
n
a
l
Jo
u
r
n
a
l
o
f
P
ro
d
u
c
ti
o
n
Re
se
a
rc
h
,
IE
EE
T
ra
n
sa
c
ti
o
n
o
n
I
n
d
u
strial
El
e
c
tro
n
ics
a
n
d
IEE
E
T
ra
n
sa
c
ti
o
n
o
n
In
d
u
strial
I
n
f
o
rm
a
ti
c
s.
Evaluation Warning : The document was created with Spire.PDF for Python.