I
nte
rna
t
io
na
l J
o
urna
l o
f
Adv
a
nces in Applie
d Science
s
(
I
J
AAS)
Vo
l.
4
,
No
.
1
,
M
ar
ch
2
0
1
5
,
p
p
.
6
~
12
I
SS
N:
2252
-
8814
6
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ia
e
s
jo
u
r
n
a
l.c
o
m/o
n
lin
e/in
d
ex
.
p
h
p
/I
J
AAS
An Integra
t
ed A
p
pro
a
ch f
o
r Co
m
p
endiu
m
G
ene
ra
tor
using
Custo
m
i
z
ed
Alg
o
rith
m
s
M
.
Su
m
a
n,
T
ha
run M
a
dd
u,
M
.
M
o
ha
n
De
p
a
rtme
n
t
o
f
El
e
c
tro
n
ics
a
n
d
C
o
m
p
u
ter E
n
g
in
e
e
rin
g
,
K.L
.
Un
iv
e
rsity
,
In
d
ia
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Dec
1
2
,
2
0
1
4
R
ev
i
s
ed
Feb
15
,
2
0
1
5
A
cc
ep
ted
Feb
2
8
,
2
0
1
5
T
e
x
t
S
u
m
m
a
riza
ti
o
n
is
a
p
ro
c
e
ss
th
a
t
is
to
g
iv
e
th
e
sh
o
rter
v
e
rsio
n
o
f
a
tex
t
d
o
c
u
m
e
n
t.
F
o
r
m
a
n
y
re
se
a
rc
h
sc
h
o
lars
w
h
o
w
a
n
t
to
d
o
th
e
ir
re
se
a
rc
h
o
n
a
sp
e
c
if
ic
d
o
m
a
in
h
a
s
to
se
a
rc
h
a
lo
t
o
f
d
o
c
u
m
e
n
ts
o
n
th
a
t
to
p
ic
re
late
d
to
a
sp
e
c
if
ic
d
o
m
a
in
.
It
is
a
lso
d
if
f
i
c
u
lt
to
g
o
t
h
ro
u
g
h
th
e
l
o
t
o
f
th
e
re
se
a
r
c
h
p
a
p
e
rs
p
re
se
n
t
i
n
t
h
a
t
p
a
rti
c
u
lar
d
o
m
a
in
w
h
ich
tak
e
s
a
lo
t
o
f
ti
m
e
a
t
th
is
m
o
m
e
n
t
o
f
ti
m
e
th
e
re
a
r
e
lo
ts
o
f
c
h
a
n
c
e
s
in
m
is
sin
g
so
m
e
k
e
y
w
o
rd
s
p
re
se
n
t
in
th
o
se
re
se
a
r
c
h
p
a
p
e
rs.
S
o
th
a
t
S
u
m
m
a
riz
e
r
is
u
se
d
to
g
i
v
e
th
e
su
m
m
a
r
y
o
f
a
p
a
p
e
r.
T
h
e
a
i
m
o
f
o
u
r
p
ro
jec
t
is
to
re
d
u
c
e
th
e
b
o
d
y
o
f
th
e
tex
t
a
n
d
m
a
in
tain
in
g
c
o
h
e
re
n
c
e
a
n
d
a
v
o
id
i
n
g
re
d
u
n
d
a
n
c
y
.
W
in
n
o
w
in
g
is
a
n
a
lg
o
rit
h
m
th
a
t
g
iv
e
s
th
e
c
o
h
e
re
n
c
e
b
e
tw
e
e
n
th
e
m
u
lt
ip
le
p
a
p
e
rs
w
h
e
n
m
u
lt
ip
le
p
a
p
e
rs
a
re
g
iv
e
n
a
s
th
e
in
p
u
t
.
Re
d
u
n
d
a
n
c
y
th
a
t
is
th
e
re
p
e
a
ted
w
o
rd
s
o
r
se
n
ten
c
e
s
c
a
n
b
e
a
v
o
id
e
d
u
sin
g
t
h
e
M
M
R
a
lg
o
rit
h
m
.
K
ey
w
o
r
d
:
C
o
h
er
en
ce
L
e
x
ical
s
i
m
ilar
it
y
Re
d
u
n
d
an
c
y
Sen
te
n
ce
p
o
s
itio
n
Sen
te
n
ce
r
ese
m
b
la
n
ce
Su
m
m
ar
izer
Co
p
y
rig
h
t
©
201
5
In
s
t
it
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
:
M.
Su
m
an
,
Dep
ar
t
m
en
t o
f
E
lectr
o
n
ics a
n
d
C
o
m
p
u
ter
E
n
g
i
n
ee
r
i
n
g
,
K.
L
.
Un
iv
er
s
it
y
,
Vad
d
es
w
ar
a
m
,
Gu
n
t
u
r
.
E
m
ail:
s
u
m
a
n
.
m
alo
j
i@
k
l
u
n
i
v
e
r
s
it
y
.
i
n
1.
I
NT
RO
D
UCT
I
O
N
T
h
e
r
ap
i
d
g
r
o
w
th
o
f
t
h
e
I
n
ter
n
et
y
ield
ed
a
m
as
s
i
v
e
in
cr
ea
s
e
o
f
th
e
a
m
o
u
n
t
o
f
i
n
f
o
r
m
atio
n
av
ailab
le,
esp
ec
iall
y
r
eg
ar
d
in
g
tex
t
d
o
cu
m
en
ts
(
e.
g
.
n
e
w
s
ar
ticles,
elec
tr
o
n
ic
b
o
o
k
s
,
s
cien
tific
p
ap
er
s
,
b
lo
g
s
,
etc.
)
.
D
u
e
to
th
e
h
u
g
e
v
o
lu
m
e
o
f
i
n
f
o
r
m
atio
n
i
n
th
e
I
n
t
er
n
et,
it
h
a
s
b
ec
o
m
e
u
n
f
ea
s
ib
le
to
ef
f
ic
ien
tl
y
s
ie
v
e
u
s
e
f
u
l
in
f
o
r
m
atio
n
f
r
o
m
t
h
e
h
u
g
e
m
a
s
s
o
f
d
o
cu
m
en
ts
.
T
h
u
s
,
it
is
n
ec
ess
ar
y
to
u
s
e
a
u
to
m
a
tic
m
et
h
o
d
s
to
u
n
d
er
s
ta
n
d
,
in
d
ex
,
clas
s
i
f
y
a
n
d
p
r
esen
t
a
ll
in
f
o
r
m
atio
n
in
a
clea
r
an
d
co
n
cise
w
a
y
,
allo
w
i
n
g
u
s
er
s
to
s
av
e
ti
m
e
a
n
d
r
eso
u
r
ce
s
.
T
h
e
n
ee
d
f
o
r
a
to
o
l
th
a
t
ta
k
es
a
te
x
t
an
d
s
h
o
r
ten
s
it
i
n
to
a
b
r
ie
f
a
n
d
s
u
cc
i
n
ct
s
u
m
m
ar
y
h
as
n
e
v
er
b
ee
n
g
r
ea
ter
th
an
n
o
w
.
W
ith
th
e
h
u
g
e
a
m
o
u
n
t
o
f
in
f
o
r
m
a
tio
n
o
n
th
e
in
ter
n
et
an
d
th
e
n
ec
es
s
it
y
to
g
et
t
h
e
ess
e
n
tial
o
f
th
i
s
in
f
o
r
m
atio
n
in
a
s
h
o
r
t
tim
e,
th
e
n
ee
d
f
o
r
s
u
m
m
ar
izer
s
b
ec
o
m
es e
v
er
y
d
a
y
p
r
ess
i
n
g
,
esp
ec
iall
y
,
f
o
r
p
eo
p
le
w
ith
s
p
ec
ial
n
ee
d
s
lik
e
b
li
n
d
o
r
eld
er
ly
p
eo
p
le.
Fo
r
th
o
s
e
p
eo
p
le
it
is
v
ital
to
g
o
d
ir
ec
tl
y
to
t
h
e
ess
e
n
tial
i
n
f
o
r
m
atio
n
r
at
h
er
th
an
h
av
in
g
to
r
ea
d
th
r
o
u
g
h
m
a
n
y
p
as
s
ag
e
s
.
On
e
s
o
lu
tio
n
i
s
u
s
e
tex
t
s
u
m
m
ar
izatio
n
tec
h
n
iq
u
e
s
.
T
e
x
t
s
u
m
m
ar
izatio
n
(
T
S)
is
th
e
p
r
o
ce
s
s
o
f
au
to
m
atica
ll
y
cr
ea
tin
g
a
co
m
p
r
ess
ed
v
er
s
io
n
o
f
o
n
e
o
r
m
o
r
e
d
o
cu
m
en
ts
.
I
t
atte
m
p
ts
to
g
et
th
e
m
ea
n
in
g
o
f
d
o
cu
m
e
n
ts
.
E
s
s
en
tiall
y
,
T
S
tech
n
iq
u
e
s
ar
e
class
i
f
ied
as
E
x
tr
ac
ti
v
e
a
n
d
A
b
s
tr
ac
ti
v
e.
E
x
tr
ac
tiv
e
s
u
m
m
ar
ies
p
r
o
d
u
ce
a
s
et
o
f
t
h
e
m
o
s
t
s
i
g
n
if
ican
t
s
en
te
n
ce
s
f
r
o
m
a
d
o
cu
m
en
t,
ex
ac
tl
y
as
t
h
e
y
ap
p
ea
r
.
A
b
s
tr
ac
tiv
e
s
u
m
m
ar
ies
atte
m
p
t
to
i
m
p
r
o
v
e
th
e
co
h
er
en
c
e
a
m
o
n
g
s
e
n
ten
ce
s
b
y
eli
m
in
a
ti
n
g
r
ed
u
n
d
an
cie
s
an
d
clar
if
y
i
n
g
th
e
co
n
te
s
t
o
f
s
e
n
te
n
ce
s
.
I
t
m
a
y
e
v
en
p
r
o
d
u
ce
n
e
w
s
en
ten
ce
s
to
th
e
s
u
m
m
ar
y
.
C
u
r
r
en
tl
y
,
t
h
e
e
x
tr
ac
tiv
e
s
u
m
m
ar
ie
s
ar
e
co
m
m
o
n
l
y
u
s
e
d
b
ec
au
s
e
t
h
e
y
ar
e
ea
s
ier
to
cr
ea
te.
E
x
tr
ac
tiv
e
m
e
th
o
d
s
ar
e
u
s
u
all
y
p
er
f
o
r
m
ed
in
th
r
ee
s
tep
s
.
1.
C
r
ea
te
an
i
n
ter
m
ed
iate
r
ep
r
ese
n
tatio
n
o
f
th
e
o
r
ig
in
al
te
x
t,
2.
Sen
te
n
ce
s
co
r
in
g
,
3.
Select
h
i
g
h
s
co
r
es se
n
ten
ce
s
t
o
th
e
s
u
m
m
ar
y
.
Evaluation Warning : The document was created with Spire.PDF for Python.
IJ
AA
S
I
SS
N:
2252
-
8814
A
n
I
n
teg
r
a
ted
A
p
p
r
o
a
ch
fo
r
C
o
mp
en
d
iu
m
Gen
era
t
o
r
u
s
in
g
C
u
s
to
miz
ed
A
lg
o
r
ith
ms
(
M.
S
u
ma
n
)
7
T
h
e
f
ir
s
t
s
tep
cr
ea
tes
a
r
ep
r
esen
tatio
n
o
f
t
h
e
d
o
cu
m
e
n
t.
U
s
u
all
y
,
it
d
iv
id
e
s
t
h
e
te
x
t
i
n
to
p
ar
ag
r
ap
h
s
,
s
en
te
n
ce
s
,
an
d
to
k
e
n
s
.
So
m
et
i
m
es
s
o
m
e
p
r
ep
r
o
ce
s
s
in
g
,
s
u
c
h
a
s
s
to
p
w
o
r
d
r
e
m
o
v
al
is
al
s
o
p
er
f
o
r
m
ed
.
T
h
e
s
ec
o
n
d
s
tep
tr
ies
to
d
eter
m
i
n
e
w
h
ich
s
en
te
n
ce
s
ar
e
i
m
p
o
r
ta
n
t
to
th
e
d
o
cu
m
en
t
o
r
to
w
h
ic
h
ex
ten
t
it
co
m
b
in
e
s
in
f
o
r
m
atio
n
ab
o
u
t
d
if
f
er
e
n
t
to
p
ics,
b
y
s
e
n
te
n
ce
s
co
r
in
g
.
T
h
e
s
co
r
e
s
h
o
u
ld
b
e
a
m
ea
s
u
r
e
o
f
h
o
w
s
ig
n
i
f
ica
n
t
a
s
en
te
n
ce
i
s
to
t
h
e
u
n
d
er
s
tan
d
i
n
g
o
f
th
e
tex
t
as
a
w
h
o
le.
T
h
e
last
s
tep
co
m
b
i
n
es
t
h
e
s
co
r
e
p
r
o
v
id
ed
b
y
th
e
p
r
ev
io
u
s
s
tep
s
an
d
g
e
n
er
ates a
s
u
m
m
ar
y
.
I
n
o
r
d
er
to
b
e
ab
le
to
m
ak
e
g
o
in
g
t
h
r
o
u
g
h
I
E
E
E
p
ap
er
s
a
lo
t
ea
s
ier
an
d
a
lo
t
m
o
r
e
ef
f
ec
tiv
e,
t
h
e
co
m
p
e
n
d
i
u
m
g
en
er
ato
r
an
al
y
s
es
th
e
p
ap
er
an
d
s
h
o
w
s
th
e
u
s
er
d
etails
f
o
r
h
i
m
/
h
er
an
d
co
m
p
r
e
h
e
n
d
w
h
at
t
h
e
p
ap
er
is
ab
o
u
t.
I
t
allo
w
s
th
e
u
s
er
to
s
av
e
th
is
s
h
o
r
t
s
u
m
m
ar
y
i
n
ca
s
e
m
u
ltip
le
p
ap
er
s
ar
e
b
ein
g
r
ef
er
r
ed
to
.
T
h
is
m
ak
e
s
it
s
i
m
p
le
to
k
ee
p
a
tr
ac
k
o
f
all
r
ef
er
en
c
es.
Usi
n
g
an
al
g
o
r
ith
m
t
h
at
co
m
b
in
es
T
F/IDF,
C
u
e
-
P
h
r
ases
,
an
d
R
e
s
e
m
b
lan
ce
to
t
itle,
r
esu
lt
s
ar
e
p
r
o
v
en
to
b
e
m
o
s
t
ef
f
ec
ti
v
e.
T
h
e
o
r
d
er
o
f
th
e
s
en
te
n
ce
s
ar
e
k
ep
t
in
tact.
T
h
e
to
o
l
al
s
o
allo
w
s
t
h
e
u
s
er
to
co
m
p
ar
e
t
w
o
o
r
m
o
r
e
p
ap
er
s
g
i
v
i
n
g
an
o
u
tp
u
t
o
f
a
j
o
in
t
n
o
n
r
ed
u
n
d
a
n
t
s
u
m
m
ar
y
,
w
h
ic
h
ca
n
f
o
r
m
t
h
e
b
asis
f
o
r
a
n
e
w
p
ap
er
.
I
t
h
elp
s
u
s
to
d
eter
m
i
n
e
co
h
er
e
n
ce
o
r
h
o
w
s
tr
o
n
g
l
y
t
h
e
p
ap
er
s
p
er
tain
in
g
to
t
h
e
s
a
m
e
d
o
m
ai
n
ar
e
lin
k
ed
.
Fin
g
er
p
r
in
ts
ar
e
g
e
n
er
ated
t
o
ch
ec
k
h
o
w
s
tr
o
n
g
t
h
e
r
elev
an
ce
b
et
w
ee
n
t
w
o
d
o
cu
m
en
ts
i
s
.
W
in
n
o
w
i
n
g
alg
o
r
ith
m
is
u
s
e
d
to
d
ete
r
m
i
n
e
t
h
is
.
T
h
ese
ar
e
m
e
th
o
d
s
u
s
ed
to
d
eter
m
i
n
e
p
lag
iar
is
m
,
w
it
h
a
d
eg
r
ee
o
f
m
o
d
if
ica
tio
n
it
h
as b
ee
n
u
s
ed
to
d
eter
m
i
n
e
d
eg
r
ee
o
f
r
elev
an
ce
.
2.
L
I
T
E
R
AT
U
RE
SU
RVE
Y
T
h
er
e
ar
e
p
len
t
y
o
f
s
u
m
m
ar
izer
s
av
ailab
le.
T
h
e
o
n
lin
e
s
u
m
m
a
r
izer
s
d
o
n
o
t
p
r
o
v
e
to
b
e
v
e
r
y
ef
f
ec
ti
v
e
as
o
n
l
y
s
e
n
ten
ce
s
w
it
h
m
o
r
e
n
o
o
f
w
o
r
d
s
ar
e
ch
o
s
e
n
,
n
o
t
n
ec
ess
ar
il
y
t
h
e
s
e
n
te
n
ce
s
w
it
h
k
e
y
w
o
r
d
s
o
r
i
m
p
o
r
tan
t
s
e
n
ten
ce
s
th
at
r
ese
m
b
le
th
e
titl
e
o
f
th
e
d
o
cu
m
en
t
.
’
A
C
o
n
te
x
t
B
ased
T
ex
t
Su
m
m
ar
izatio
n
S
y
s
te
m
’
,
ex
p
lain
s
h
o
w
co
m
b
i
n
in
g
al
g
o
r
ith
m
s
ca
n
p
r
o
v
id
e
m
o
r
e
ef
f
ec
tiv
e
r
es
u
lt
s
[
2
]
.
Dep
en
d
in
g
o
n
t
h
e
co
n
te
x
t,
h
o
w
ev
er
,
s
o
m
e
tech
n
iq
u
e
s
m
a
y
y
ie
ld
b
etter
r
esu
lts
t
h
a
n
s
o
m
e
o
th
er
s
.
’
Ass
e
s
s
i
n
g
s
en
ten
ce
s
co
r
in
g
tec
h
n
iq
u
e
s
f
o
r
ex
tr
ac
tiv
e
te
x
t
s
u
m
m
ar
iz
atio
n
’
p
r
o
p
o
s
es
a
n
e
w
s
u
m
m
ar
iza
tio
n
s
y
s
te
m
t
h
at
ea
s
il
y
co
m
b
i
n
es
d
if
f
er
en
t
s
en
te
n
ce
s
co
r
in
g
m
et
h
o
d
s
in
o
r
d
er
to
o
b
tain
th
e
b
est
s
u
m
m
ar
ies
d
ep
en
d
in
g
o
n
t
h
e
co
n
t
ex
t
[
4
]
.
T
h
e
f
i
f
tee
n
s
en
te
n
ce
s
co
r
in
g
m
et
h
o
d
s
m
o
s
t
w
id
el
y
u
s
ed
an
d
r
ef
er
e
n
ce
d
in
th
e
tec
h
n
ical
liter
at
u
r
e
in
t
h
e
last
1
0
y
ea
r
s
ar
e
ap
p
lied
to
s
in
g
le
d
o
cu
m
e
n
t
s
u
m
m
ar
izat
io
n
.
B
o
th
q
u
an
t
itati
v
e
an
d
q
u
alitat
iv
e
m
ea
s
u
r
es
a
r
e
u
s
ed
to
ev
alu
ate
w
h
ic
h
co
m
b
in
at
io
n
o
f
t
h
e
s
en
ten
ce
s
co
r
in
g
m
et
h
o
d
s
y
ie
ld
b
etter
r
esu
lts
f
o
r
ea
ch
co
n
tex
t.
C
o
m
b
i
n
in
g
3
to
5
s
p
ec
if
ic
s
e
n
te
n
ce
s
s
co
r
in
g
m
et
h
o
d
s
in
a
ce
r
tain
co
n
tex
t p
r
o
v
id
es
m
u
c
h
b
etter
q
u
alit
y
r
es
u
lts
.
T
h
e
ch
o
ice
o
f
th
o
s
e
m
et
h
o
d
s
d
ep
en
d
o
n
co
n
tex
t
o
f
t
h
e
d
o
cu
m
en
t.
’
Get
O
n
l
y
t
h
e
E
s
s
en
t
ial
in
f
o
r
m
atio
n
: T
ex
t s
u
m
m
ar
izer
b
ased
o
n
i
m
p
licit d
ata
’
w
a
s
u
s
ed
to
ex
p
er
i
m
e
n
t a
n
d
d
eter
m
i
n
e
t
h
e
b
est p
o
s
s
ib
le
co
m
b
i
n
at
io
n
to
s
u
m
m
ar
ize
p
ap
er
s
[
1
]
.
T
h
er
eb
y
cr
ea
ti
n
g
a
cu
s
to
m
ized
al
g
o
r
ith
m
i
n
cl
u
d
in
g
,
C
u
e
-
P
h
r
ase
s
,
R
ese
m
b
lan
ce
to
titl
e
an
d
T
F/IDF
d
r
asti
ca
ll
y
i
m
p
r
o
v
es
ac
cu
r
ac
y
.
T
h
is
h
elp
s
u
s
to
s
u
m
m
ar
ize
a
s
in
g
le
d
o
cu
m
en
t
w
it
h
o
u
t
m
i
s
s
i
n
g
an
y
i
m
p
o
r
ta
n
t
s
e
n
te
n
ce
s
a
n
d
th
e
co
n
tex
t
o
f
t
h
e
p
ap
er
is
also
p
r
eser
v
ed
.
R
ec
en
t
r
esear
ch
i
n
m
u
lti
-
d
o
cu
m
en
t
s
u
m
m
ar
izat
io
n
h
as
f
o
c
u
s
ed
o
n
r
e
m
o
v
i
n
g
r
ed
u
n
d
a
n
c
y
an
d
s
tat
is
tic
ap
p
r
o
ac
h
es
i
n
m
ac
h
in
e
lear
n
i
n
g
a
n
d
lan
g
u
ag
e
m
o
d
elin
g
to
f
i
n
d
i
m
p
o
r
ta
n
t
s
en
te
n
ce
s
a
n
d
w
o
r
d
s
i
n
m
u
lti
p
le
d
o
cu
m
en
t
s
.
’
A
C
o
n
te
x
t
u
a
l
Q
u
er
y
E
x
p
a
n
s
io
n
B
ased
Mu
lti
-
d
o
cu
m
e
n
t
Su
m
m
ar
izer
f
o
r
S
m
ar
t
L
ea
r
n
i
n
g
’
,
p
r
o
v
id
es
in
s
i
g
h
t
o
n
h
o
w
r
ed
u
n
d
a
n
c
y
ca
n
b
e
r
e
m
o
v
ed
u
s
in
g
a
tec
h
n
iq
u
e
ca
lled
Ma
x
i
m
u
m
Ma
r
g
i
n
al
R
ele
v
a
n
c
e
(
MM
R
)
[
6
]
.
T
h
is
tech
n
iq
u
e
i
s
p
r
o
p
o
s
ed
as
a
r
elativ
el
y
b
etter
ap
p
r
o
ac
h
to
tack
le
r
ed
u
n
d
an
c
y
.
[
3
]
’
A
s
u
r
v
e
y
o
f
te
x
t
s
u
m
m
ar
izatio
n
tec
h
n
iq
u
es
’
ex
p
lain
s
t
h
at
P
r
ec
is
io
n
is
d
ef
i
n
e
d
as
th
e
p
er
ce
n
tag
e
o
f
th
e
r
el
ev
an
t
ite
m
s
in
t
h
e
r
etu
r
n
ed
s
et
an
d
R
ec
all
is
t
h
e
p
er
ce
n
tag
e
o
f
t
h
e
r
elev
a
n
t
it
e
m
s
i
n
t
h
e
r
etu
r
n
ed
s
et
co
m
p
ar
ed
to
th
o
s
e
in
th
e
co
llectio
n
.
I
f
t
h
e
w
h
o
le
co
llect
io
n
is
r
etr
ie
v
ed
,
th
e
n
t
h
e
R
ec
a
ll
is
m
a
x
i
m
u
m
,
b
u
t
P
r
ec
is
io
n
i
s
lo
w
.
Mo
s
t
s
ea
r
c
h
en
g
i
n
e
s
s
u
f
f
er
f
r
o
m
th
i
s
p
r
o
b
le
m
(
h
i
g
h
R
ec
all
a
n
d
lo
w
P
r
ec
is
io
n
)
.
I
f
s
ea
r
ch
en
g
i
n
es
s
ea
r
c
h
o
n
l
y
a
d
o
cu
m
e
n
ts
p
r
i
m
ar
y
id
ea
s
,
in
s
tead
o
f
ev
er
y
w
o
r
d
,
th
e
n
R
ec
all
w
il
l
lik
el
y
n
o
t
b
e
d
ec
r
ea
s
ed
b
u
t
P
r
ec
is
io
n
w
ill
li
k
el
y
i
m
p
r
o
v
e
.
Hen
ce
,
a
n
a
u
to
m
ated
f
ac
ilit
y
f
o
r
s
u
m
m
ar
iz
in
g
d
o
cu
m
en
ts
to
i
m
p
r
o
v
e
p
r
o
d
u
c
tiv
it
y
is
d
es
ir
ab
le.
A
g
o
o
d
s
u
m
m
ar
izatio
n
s
y
s
te
m
s
h
o
u
ld
i
n
clu
d
e
o
n
l
y
s
e
n
ten
ce
s
th
at
ar
e
m
o
s
t
i
m
p
o
r
ta
n
t
to
a
d
o
cu
m
e
n
ts
t
h
e
m
e
;
it
m
u
s
t
als
o
co
v
er
all
d
o
cu
m
e
n
ts
to
p
ics.
Usi
n
g
a
s
u
m
m
ar
y
in
s
tead
o
f
t
h
e
w
h
o
le
d
o
cu
m
e
n
ts
as
a
r
ep
r
esen
ta
tiv
e
o
f
w
h
a
t
th
e
d
o
cu
m
e
n
ts
ar
e
ab
o
u
t
w
o
u
l
d
m
ea
n
p
r
o
ce
s
s
i
n
g
a
f
r
ac
tio
n
(
2
0
p
er
ce
n
t
o
r
le
s
s
)
o
f
t
h
e
d
o
cu
m
e
n
ts
te
x
t,
y
et
y
ie
ld
b
etter
p
r
ec
is
io
n
a
n
d
le
s
s
er
p
r
o
ce
s
s
in
g
ti
m
e.
I
n
o
r
d
er
to
d
eter
m
i
n
e
t
h
e
r
eq
u
ir
em
en
ts
o
f
a
g
o
o
d
s
u
m
m
ar
izati
o
n
s
y
s
te
m
,
m
a
n
y
tex
t
s
u
m
m
ar
izatio
n
ap
p
r
o
ac
h
es
w
er
e
r
ev
ie
w
ed
.
A
n
i
n
-
d
ep
t
h
r
ev
ie
w
o
f
tex
t
s
u
m
m
ar
izatio
n
liter
atu
r
e
w
a
s
co
n
d
u
cted
an
d
r
esu
lts
f
r
o
m
t
h
i
s
s
tu
d
y
alo
n
g
w
i
th
a
d
escr
ip
tio
n
o
f
ea
ch
alg
o
r
it
h
m
.
C
o
h
er
e
n
ce
’
W
in
n
o
w
in
g
:
L
o
ca
l
A
l
g
o
r
i
th
m
s
f
o
r
Do
cu
m
e
n
t
Fin
g
er
p
r
in
ti
n
g
’
p
r
o
v
id
es
in
s
i
g
h
t
o
n
p
lag
iar
is
m
d
etec
t
io
n
tec
h
n
iq
u
es.
A
tech
n
iq
u
e
to
g
e
n
e
r
ate
u
n
iq
u
e
v
al
u
es
f
o
r
ch
u
n
k
s
o
f
te
x
t
[
5
]
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8814
IJ
AA
S
Vo
l.
4
,
No
.
1
,
Ma
r
ch
201
5
:
6
–
12
8
3.
P
RO
P
O
SE
D
SYS
T
E
M
T
o
d
esig
n
a
co
m
p
en
d
i
u
m
g
e
n
er
ato
r
th
er
e
ar
e
s
o
m
e
s
p
ec
i
f
ic
atio
n
s
s
u
c
h
as
f
u
n
ctio
n
al
s
p
e
cif
icatio
n
s
an
d
p
r
o
g
r
am
s
p
ec
if
ica
tio
n
s
.
3
.
1
.
F
un
ct
io
na
l Specif
ica
t
io
n
s
1.
T
h
e
co
m
p
en
d
i
u
m
g
e
n
er
ato
r
m
ai
n
l
y
ai
m
s
to
g
en
er
ate
i
m
p
o
r
tan
t
s
en
te
n
ce
s
a
f
ter
p
ass
i
n
g
th
r
o
u
g
h
th
e
d
o
cu
m
e
n
t.
A
l
s
o
w
h
e
n
t
wo
o
r
m
o
r
e
ac
ad
e
m
ic
p
ap
er
s
ar
e
g
i
v
en
as
i
n
p
u
t
t
h
en
a
co
m
b
i
n
ed
n
o
n
r
ed
u
n
d
an
t
s
u
m
m
ar
y
i
s
g
e
n
er
ated
2.
B
y
cr
ea
tin
g
a
c
u
s
to
m
ized
al
g
o
r
ith
m
th
a
t
d
r
asti
ca
l
l
y
i
m
p
r
o
v
es
ac
cu
r
ac
y
o
f
t
h
e
s
u
m
m
ar
y
.
T
h
is
h
elp
s
u
s
s
u
m
m
ar
ize
a
s
i
n
g
le
d
o
cu
m
e
n
t
w
it
h
o
u
t
m
is
s
in
g
a
n
y
i
m
p
o
r
tan
t se
n
te
n
ce
s
a
n
d
p
r
ese
r
v
in
g
t
h
e
co
n
te
x
t o
f
th
e
p
ap
er
.
3.
Ma
in
tai
n
i
n
g
co
r
r
elatio
n
w
i
th
t
h
e
m
ai
n
id
ea
,
i
s
k
e
y
to
p
r
o
v
id
i
n
g
t
h
e
id
ea
l
s
u
m
m
ar
y
.
T
h
u
s
m
u
ltip
le
d
o
cu
m
en
ts
b
elo
n
g
i
n
g
to
t
h
e
s
a
m
e
d
o
m
ai
n
ca
n
b
e
s
u
m
m
ar
ize
d
.
3
.
2
.
P
r
o
g
ra
m
S
pecif
ica
t
io
ns
3
.
2
.
1
.
T
o
k
enizer
1.
E
v
er
y
w
o
r
d
n
ee
d
s
to
b
e
s
p
lit in
to
in
d
i
v
id
u
al
to
k
en
s
,
ev
er
y
wo
r
d
b
ec
o
m
es a
to
k
en
.
2.
P
UNKT
m
o
d
u
le
in
N
L
T
K
is
u
s
ed
f
o
r
th
is
.
3
.
2
.
2
.
Sto
p Re
m
o
v
a
l
1.
NL
T
K
s
to
p
w
o
r
d
s
p
ac
k
ag
e
i
s
u
s
ed
to
r
em
o
v
e
s
to
p
w
o
r
d
s
.
2.
T
h
is
h
elp
s
i
m
p
r
o
v
e
ca
lc
u
lat
io
n
o
f
w
o
r
d
f
r
eq
u
en
c
y
.
3
.
2
.
3
.
Ste
m
m
er
a
nd
L
e
mm
a
t
izer
1.
An
i
n
b
u
ilt le
m
m
atize
r
ca
lled
W
o
r
d
n
et
is
u
s
ed
.
2.
T
h
e
Ste
m
m
er
u
s
ed
is
S
n
o
w
b
al
l ste
m
m
er
.
3
.
2
.
4
.
Cue
-
P
hra
s
e
1.
A
co
r
p
u
s
o
f
c
u
e
p
h
r
ase
s
th
a
t a
r
e
m
o
s
t c
o
m
m
o
n
l
y
u
s
ed
in
r
es
ea
r
ch
p
ap
er
s
is
cr
ea
ted
.
2.
I
n
s
u
m
m
ar
y
,
i
n
co
n
cl
u
s
io
n
,
o
u
r
in
v
e
s
tig
a
tio
n
,
t
h
e
p
ap
er
d
esc
r
ib
es,
etc.
ar
e
a
f
e
w
ex
a
m
p
les.
3
.
2
.
5
.
Rese
m
bla
nce
t
o
T
it
le
1.
A
li
s
t
t
h
at
s
to
r
es
t
h
e
ti
tle
is
cr
ea
ted
an
d
s
en
te
n
ce
s
t
h
at
h
av
e
r
ese
m
b
la
n
ce
to
t
h
ese
w
o
r
d
s
ar
e
r
an
k
ed
h
i
g
h
er
.
2.
T
h
is
h
elp
s
m
ain
tain
t
h
e
co
r
e
ess
e
n
ce
o
f
th
e
p
ap
er
.
3
.
2
.
6
.
TF
-
I
DF
1.
A
n
u
m
er
ical
s
tatis
t
ic
th
at
i
s
in
te
n
d
ed
to
r
ef
lect
h
o
w
i
m
p
o
r
tan
t
a
w
o
r
d
is
to
a
d
o
cu
m
e
n
t
in
a
co
llectio
n
o
r
co
r
p
u
s
2.
I
t
u
s
es
th
e
m
o
s
t
n
o
o
f
o
cc
u
r
r
en
ce
s
as
an
u
p
p
er
en
d
v
alu
e.
T
h
e
o
th
er
f
r
eq
u
en
c
ies
ar
e
co
m
p
ar
ed
t
o
th
is
v
al
u
e.
3.
A
c
u
s
to
m
co
m
b
in
a
tio
n
o
f
t
h
ese
th
r
ee
a
lg
o
r
it
h
m
s
r
a
n
k
s
s
e
n
ten
ce
s
ap
tl
y
f
o
r
ac
ad
e
m
ic
r
esear
ch
p
ap
er
s
.
3.
2
.
7
.
Sente
nce
Select
io
n
T
h
e
s
en
ten
ce
s
w
h
ich
h
av
e
a
r
a
n
k
ab
o
v
e
t
h
e
th
r
e
s
h
o
ld
r
an
k
ar
e
s
elec
ted
.
3
.
2
.
8
.
Redund
a
ncy
Re
m
o
v
a
l
1.
Ma
x
i
m
u
m
Ma
r
g
in
a
l Rele
v
an
c
e
alg
o
r
ith
m
is
u
s
ed
to
r
e
m
o
v
e
r
ed
u
n
d
an
c
y
.
2.
A
co
m
b
i
n
ed
n
o
n
r
ed
u
n
d
an
t s
u
m
m
ar
y
is
g
e
n
er
ated
f
o
r
m
u
ltip
le
d
o
cu
m
en
ts
.
3
.
2
.
9
.
F
ing
er
printing
1.
C
r
ea
ted
a
h
as
h
v
al
u
e
f
u
n
ctio
n
u
s
in
g
len
g
t
h
o
f
f
in
g
er
p
r
i
n
t
a
s
2
0
.
T
h
is
i
s
a
n
id
ea
l
n
u
m
b
er
as
it
is
lo
w
e
n
o
u
g
h
to
p
r
o
v
id
e
ac
cu
r
at
e
r
esu
lts
.
I
t is lar
g
e
en
o
u
g
h
to
b
e
co
m
p
u
tab
le.
2.
A
f
o
r
m
u
la
f
r
o
m
th
e
p
ap
er
is
u
s
ed
to
g
en
er
ate
u
n
iq
u
e
f
i
n
g
er
p
r
in
ts
.
3
.
2
.
1
0
.
Winn
o
w
ing
An
al
g
o
r
ith
m
p
r
i
m
ar
i
l
y
u
s
e
d
to
d
etec
t
p
lag
iar
is
m
m
o
d
if
ied
to
d
eter
m
i
n
e
r
ele
v
an
ce
b
et
w
ee
n
d
o
cu
m
en
ts
.
Used
to
id
en
ti
f
y
le
v
el
o
f
co
h
er
e
n
ce
b
et
w
ee
n
d
o
cu
m
e
n
t
s
b
ased
o
n
th
e
f
i
n
g
er
p
r
i
n
ts
m
atc
h
ed
.
Evaluation Warning : The document was created with Spire.PDF for Python.
IJ
AA
S
I
SS
N:
2252
-
8814
A
n
I
n
teg
r
a
ted
A
p
p
r
o
a
ch
fo
r
C
o
mp
en
d
iu
m
Gen
era
t
o
r
u
s
in
g
C
u
s
to
miz
ed
A
lg
o
r
ith
ms
(
M.
S
u
ma
n
)
9
4.
I
M
P
L
E
M
E
NT
AT
I
O
N
4
.
1
.
T
ex
t
Seg
m
ent
a
t
io
n
T
h
r
ee
m
ai
n
p
r
o
c
ess
es ta
k
e
p
lace
in
th
i
s
m
o
d
u
le.
4
.
1
.
1
.
T
o
k
eniza
t
io
n
Sp
litt
in
g
a
s
e
n
te
n
ce
in
to
i
n
d
iv
i
d
u
al
w
o
r
d
s
.
N
L
T
K
P
UNKT
is
u
s
ed
.
4
.
1
.
2
.
L
e
mm
a
t
iza
t
io
n
C
o
n
v
er
tin
g
a
w
o
r
d
to
its
r
o
o
t f
o
r
m
.
E
.
g
.
s
a
y
s
,
s
aid
,
s
a
y
i
n
g
w
i
ll a
ll
m
ap
to
r
o
o
t f
o
r
m
–
s
a
y
.
4
.
1
.
3
.
Ste
m
m
er
I
t
is
s
i
m
ilar
to
a
le
m
m
atize
,
b
u
t
it
s
te
m
s
a
w
o
r
d
r
ath
er
th
an
g
et
to
th
e
r
o
o
t
f
o
r
m
.
eg
.
L
a
u
g
h
ed
,
lau
g
h
i
n
g
w
ill
s
te
m
to
la
u
g
h
.
Ho
w
e
v
er
,
s
aid
,
s
a
y
i
n
g
w
ill
m
ap
to
s
a
-
w
h
ic
h
is
n
o
t
p
ar
t
icu
lar
l
y
en
l
ig
h
te
n
i
n
g
i
n
ter
m
s
o
f
w
h
at,
”
s
a”
m
ea
n
s
.
Sto
p
w
o
r
d
r
em
o
v
al
also
tak
e
s
p
lace
w
h
er
e
co
n
s
ta
n
tl
y
r
ep
ea
ted
w
o
r
d
s
ar
e
r
e
m
o
v
ed
.
4
.
2
.
Sente
nce
Ra
nk
ing
Sin
ce
th
e
w
o
r
d
s
ar
e
to
k
e
n
ized
,
th
e
y
ar
e
n
o
w
r
a
n
k
ed
ac
co
r
d
in
g
to
C
u
e
P
h
r
ase,
Sen
ten
ce
P
o
s
itio
n
a
n
d
R
es
e
m
b
lan
ce
to
titl
e
al
g
o
r
ith
m
s
.
4
.
2
.
1
.
Cue
P
hra
s
e
C
u
e
-
P
h
r
ase
s
:
I
n
g
e
n
er
al,
th
e
s
en
ten
ce
s
s
tar
ted
b
y
i
n
s
u
m
m
a
r
y
,
i
n
co
n
clu
s
io
n
,
o
u
r
in
v
esti
g
atio
n
,
th
e
p
ap
er
d
escr
ib
es
an
d
e
m
p
h
asiz
es
s
u
c
h
as
t
h
e
b
est,
t
h
e
m
o
s
t
i
m
p
o
r
tan
t,
ac
co
r
d
in
g
to
t
h
e
s
t
u
d
y
,
s
ig
n
i
f
ica
n
tl
y
,
i
m
p
o
r
tan
t,
i
n
p
ar
ticu
lar
,
h
ar
d
l
y
,
i
m
p
o
s
s
ib
le
as
w
ell
a
s
d
o
m
ai
n
-
s
p
ec
if
ic
b
o
n
u
s
p
h
r
ases
ter
m
s
ca
n
b
e
g
o
o
d
in
d
icato
r
s
o
f
s
i
g
n
i
f
ican
t c
o
n
te
n
t o
f
a
te
x
t d
o
cu
m
e
n
t.
4
.
2
.
2
.
TF
-
I
DF
T
FID
F,
s
h
o
r
t f
o
r
ter
m
f
r
eq
u
en
c
y
in
v
er
s
e
d
o
cu
m
e
n
t
f
r
eq
u
en
c
y
,
is
a
n
u
m
er
ical
s
tatis
t
ic
th
a
t i
s
in
te
n
d
ed
to
r
ef
lect
h
o
w
i
m
p
o
r
tan
t
a
w
o
r
d
is
to
a
d
o
cu
m
e
n
t
in
a
co
llec
tio
n
o
r
co
r
p
u
s
.
I
t
u
s
es
th
e
m
o
s
t
n
o
o
f
o
cc
u
r
r
e
n
ce
s
as a
n
u
p
p
er
en
d
v
al
u
e.
T
h
e
o
th
er
f
r
eq
u
en
cie
s
ar
e
co
m
p
ar
ed
to
th
is
v
a
lu
e.
4
.
3
.
Sente
nce
Select
io
n
Sen
te
n
ce
s
w
i
th
r
an
k
ab
o
v
e
t
h
r
esh
o
ld
f
r
eq
u
e
n
c
y
ar
e
s
e
lecte
d
.
4
.
4
.
Redund
a
ncy
Re
m
o
v
a
l
As
m
u
ltip
le
d
o
cu
m
e
n
ts
ar
e
b
ein
g
s
u
m
m
ar
ized
,
s
o
m
e
d
o
cu
m
en
ts
m
a
y
h
a
v
e
p
o
in
ts
t
h
at
ar
e
r
ep
ea
ted
.
W
h
en
a
co
m
b
i
n
ed
s
u
m
m
ar
y
o
f
all
th
e
d
o
cu
m
e
n
ts
i
s
b
ein
g
d
is
p
la
y
ed
th
i
s
r
ed
u
n
d
an
c
y
co
n
ti
n
u
es.
MM
R
alg
o
r
ith
m
is
u
s
ed
to
g
et
r
id
o
f
th
is
r
ed
u
n
d
an
c
y
.
4
.
5
.
F
ing
er
printing
Fin
g
er
p
r
in
ti
n
g
is
a
tec
h
n
iq
u
e
u
s
ed
to
d
etec
t
P
la
g
iar
is
m
i
n
a
ca
d
em
ic
d
o
cu
m
en
ts
.
T
h
is
m
et
h
o
d
f
o
r
m
s
r
ep
r
esen
tativ
e
d
i
g
est
s
o
f
d
o
cu
m
en
ts
b
y
s
elec
ti
n
g
a
s
et
o
f
m
u
ltip
le
s
u
b
s
t
r
in
g
s
(
n
-
g
r
a
m
s
)
f
r
o
m
t
h
e
m
.
So
th
e
f
ir
s
t
s
tep
is
to
d
o
a
tex
t
s
e
g
m
e
n
tat
io
n
as
m
atc
h
es
s
h
o
u
ld
b
e
u
n
a
f
f
ec
ted
b
y
ex
tr
a
s
p
ac
e,
ca
p
ital
s
an
d
p
u
n
ct
u
atio
n
,
etc.
T
h
en
k
-
g
r
a
m
s
ar
e
f
o
r
m
ed
w
h
er
e
k
i
s
2
0
.
I
t is f
o
u
n
d
to
b
e
th
e
id
ea
l v
al
u
e.
4
.
6
.
Winn
o
w
ing
T
h
is
h
elp
s
u
n
d
er
s
ta
n
d
h
o
w
s
t
r
o
n
g
l
y
v
ar
io
u
s
p
ap
er
s
p
er
tain
i
n
g
to
a
s
in
g
le
d
o
m
a
in
ar
e
li
n
k
ed
.
I
t
g
iv
es
u
s
a
g
o
o
d
p
er
s
p
ec
tiv
e
o
f
h
o
w
t
h
e
d
ata
ca
n
b
e
o
r
g
an
ized
an
d
u
s
ed
.
L
e
v
el
o
f
s
i
m
ilar
it
y
th
at
n
ee
d
s
to
b
e
m
atc
h
ed
is
g
iv
e
n
a
v
alu
e.
A
lo
w
er
t
h
r
esh
o
ld
w
o
u
ld
b
e
a
n
o
is
e
t
h
r
es
h
o
ld
th
a
t
d
eter
m
i
n
es
if
t
h
er
e’
s
s
o
m
e
a
m
o
u
n
t
o
f
s
i
m
ilar
it
y
b
et
w
ee
n
th
e
d
o
cu
m
en
t
s
b
ein
g
co
m
p
a
r
ed
.
Fro
m
t
h
er
e
o
n
th
r
e
s
h
o
ld
s
ar
e
s
et
at
cu
s
to
m
p
o
in
ts
th
a
t d
eter
m
i
n
e
s
i
m
ilar
it
y
.
5.
RE
SU
L
T
S
5
.
1
.
M
o
du
le
1
Su
m
m
ar
izatio
n
f
o
r
th
e
s
i
n
g
le
o
r
m
u
ltip
le
I
E
E
E
p
ap
er
s
.
E
n
ter
th
e
n
u
m
b
er
o
f
p
ap
er
s
to
s
u
m
m
ar
ize
.
I
np
ut
s
:
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8814
IJ
AA
S
Vo
l.
4
,
No
.
1
,
Ma
r
ch
201
5
:
6
–
12
10
Fig
u
r
e
1
.
T
o
en
ter
th
e
n
u
m
b
er
o
f
p
ap
er
s
P
ap
er
1
:
Fig
u
r
e
2
.
I
E
E
E
p
a
p
er
1
as I
n
p
u
t
P
ap
er
2
:
Fig
u
r
e
3
.
I
E
E
E
p
a
p
er
2
as I
n
p
u
t
Evaluation Warning : The document was created with Spire.PDF for Python.
IJ
AA
S
I
SS
N:
2252
-
8814
A
n
I
n
teg
r
a
ted
A
p
p
r
o
a
ch
fo
r
C
o
mp
en
d
iu
m
Gen
era
t
o
r
u
s
in
g
C
u
s
to
miz
ed
A
lg
o
r
ith
ms
(
M.
S
u
ma
n
)
11
O
utput
:
Fig
u
r
e
4
.
Ou
tp
u
t o
f
m
u
ltip
le
p
ap
er
s
5
.
2
.
M
o
du
le
2
T
o
ch
ec
k
th
e
co
h
er
en
ce
f
o
r
th
e
m
u
l
tip
le
I
E
E
E
p
ap
er
s
.
I
np
ut:
P
ap
er
1
Fig
u
r
e
5
.
I
E
E
E
p
a
p
er
2
as in
p
u
t
P
ap
er
2
Fig
u
r
e
6
.
I
E
E
E
p
a
p
er
2
as in
p
u
t
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8814
IJ
AA
S
Vo
l.
4
,
No
.
1
,
Ma
r
ch
201
5
:
6
–
12
12
O
utput
:
Fig
u
r
e
7
.
Ou
tp
u
t
f
o
r
C
o
h
er
en
c
e
6.
E
VA
L
UA
T
I
O
N
R
o
g
u
e
m
et
h
o
d
w
ill
b
e
u
s
ed
to
ev
al
u
ate
t
h
e
s
u
m
m
ar
izer
.
T
h
e
o
f
f
icial
ev
a
lu
at
io
n
to
o
l
k
it
f
o
r
te
x
t
s
u
m
m
ar
izatio
n
i
n
D
UC
,
to
e
v
alu
a
te
th
e
p
er
f
o
r
m
a
n
ce
o
f
o
u
r
s
u
m
m
ar
izatio
n
s
y
s
te
m
.
I
t
in
v
o
l
v
es
m
a
n
u
all
y
s
u
m
m
ar
izin
g
a
d
o
cu
m
e
n
t
a
n
d
th
en
co
m
p
ar
e
i
t
w
it
h
t
h
e
au
to
m
a
ted
s
u
m
m
ar
y
.
Als
o
in
v
o
l
v
es
m
a
n
u
all
y
d
eter
m
in
i
n
g
co
h
er
en
ce
b
et
w
ee
n
d
o
cu
m
e
n
t
s
,
an
d
co
m
p
ar
in
g
i
t
w
it
h
t
h
e
d
o
cu
m
e
n
t
s
.
7.
RE
F
E
R
E
NC
E
S
[1
]
H.
Ch
o
rf
i,
“
G
e
t
o
n
ly
th
e
e
ss
e
n
ti
a
l
in
f
o
rm
a
ti
o
n
:
T
e
x
t
su
m
m
a
riz
e
r
b
a
se
d
o
n
im
p
li
c
it
d
a
ta”
,
p
p
.
1
-
4
,
2
0
1
3
.
[2
]
F
re
it
a
s
F
.
,
e
t
a
l.
,
“
A
c
o
n
tex
t
b
a
se
d
tex
t
su
mm
a
riza
ti
o
n
sy
ste
m
”
,
In
Do
c
u
m
e
n
t
A
n
a
l
y
sis
S
y
st
e
m
s
(D
A
S
),
2
0
1
4
1
1
t
h
IA
P
R
In
tern
a
ti
o
n
a
l
W
o
rk
sh
o
p
,
p
p
.
6
6
–
7
0
,
2
0
1
4
.
[3
]
A
.
N
e
n
k
o
v
a
a
n
d
K.
M
c
Ke
o
w
n
,
“
A
su
rv
e
y
o
f
tex
t
su
m
m
a
riza
ti
o
n
tec
h
n
iq
u
e
s”
,
In
M
in
i
n
g
T
e
x
t
D
a
ta
S
p
rin
g
e
r
US.
,
p
p
.
4
3
-
7
6
,
2
0
1
2
.
[4
]
R.
D.
L
in
s
,
e
t
a
l.
,
“
A
ss
e
ss
in
g
se
n
ten
c
e
sc
o
rin
g
tec
h
n
i
q
u
e
s f
o
r
e
x
trac
ti
v
e
tex
t
su
m
m
a
ri
z
a
ti
o
n
”
,
V
ol
.
4
0
,
2
0
1
3
.
[5
]
W
il
k
e
rso
n
D.
S
.
,
e
t
a
l.
,
“
W
in
n
o
win
g
:
l
o
c
a
l
a
l
g
o
rit
h
ms
fo
r
d
o
c
u
me
n
t
fi
n
g
e
rp
ri
n
ti
n
g
”
,
In
P
r
o
c
e
e
d
in
g
s
o
f
th
e
2
0
0
3
A
CM
S
IG
M
O
D i
n
tern
a
ti
o
n
a
l
c
o
n
f
e
r
e
n
c
e
o
n
M
a
n
a
g
e
m
e
n
t
o
f
d
a
ta
,
p
p
.
7
6
-
8
5
,
2
0
0
3
.
[6
]
W
e
n
D.
,
e
t
a
l
.
,
“
A
c
o
n
tex
tu
a
l
q
u
e
r
y
e
x
p
a
n
sio
n
b
a
se
d
m
u
lt
i
-
d
o
c
u
m
e
n
t
su
m
m
a
rize
r
f
o
r
s
m
a
rt
lea
rn
in
g
”
,
In
S
ig
n
a
l
-
Im
a
g
e
T
e
c
h
n
o
l
o
g
y
a
n
d
In
tern
e
t
-
B
a
se
d
S
y
st
e
m
s (S
IT
IS
)
,
p
p
.
1
0
1
0
-
1
0
1
6
,
2
0
1
3
.
[7
]
I.
Ku
p
iec
,
e
t
a
l.
,
"
A
tra
i
n
a
b
le
d
o
c
u
me
n
t
su
mm
a
rize
r
"
,
In
P
ro
c
e
e
d
i
n
g
s
o
f
th
e
1
8
th
A
CM
S
IG
IR
Co
n
fe
re
n
c
e
,
pp.
68
-
7
3
,
1
9
9
5
.
B
I
O
G
RAP
H
I
E
S
O
F
AUTH
O
RS
Dr.
M
.
S
u
m
a
n
p
ro
f
e
ss
o
r
(S
ig
n
a
ls
a
n
d
S
y
ste
m
s)
in
d
e
p
a
rtm
e
n
t
o
f
El
e
c
tro
n
ics
a
n
d
Co
m
p
u
ter
En
g
in
e
e
rin
g
(ECM
)
h
a
s
e
x
ten
d
e
d
h
is
se
rv
ice
s
a
s
HO
D
in
ECM
d
e
p
a
rtm
e
n
t,
K
L
Un
iv
e
rsit
y
.
He
w
a
s
a
wa
rd
e
d
w
it
h
P
h
.
D.
f
ro
m
JN
T
UH
,
H
y
d
e
ra
b
a
d
f
o
r
th
e
th
e
sis
e
n
ti
tl
e
d
"
ENHA
NCEM
ENT
OF
COMP
R
ES
S
ED
NO
IS
Y S
P
EE
C
H S
IG
N
AL"
.
H
e
is
a
l
so
th
e
li
f
e
m
e
m
b
e
r
o
f
Co
m
p
u
ter S
o
c
iet
y
o
f
In
d
ia (CS
I)
.
T
h
a
ru
n
M
a
d
d
u
stu
d
e
n
t
o
f
El
e
c
tro
n
ics
a
n
d
Co
m
p
u
ter
E
n
g
in
e
e
rin
g
(ECM
)
p
u
rsu
in
g
4
th
y
e
a
r
o
f
B.
T
ECH
in
K
L
Un
iv
e
rsity
.
M
y
p
re
v
io
u
s
re
se
a
rc
h
w
o
rk
s
a
re
b
a
se
d
o
n
d
a
ta
m
in
in
g
.
T
h
e
p
re
se
n
t
w
o
rk
is
re
late
d
to
NL
TK
o
n
w
h
ich
th
e
p
re
se
n
t
p
a
p
e
r
re
se
a
rc
h
is
d
o
n
e
.
Evaluation Warning : The document was created with Spire.PDF for Python.