I
AE
S
I
nte
rna
t
io
na
l J
o
urna
l o
f
Art
if
icia
l In
t
ellig
ence
(
I
J
-
AI
)
Vo
l.
3
,
No
.
2
,
J
u
n
e
201
4
,
p
p
.
7
3
~7
8
I
SS
N:
2252
-
8938
73
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
AI
Ex
tractive
B
a
sed
Sing
le Docu
m
en
t
Tex
t
Su
mm
a
ri
z
a
t
io
n Using
Clustering
Appro
a
ch
P
a
nk
a
j
B
ho
le
,
A.
J
.
Ag
ra
w
a
l
De
p
a
rte
m
e
n
t
o
f
Co
m
p
u
ter S
c
ien
c
e
a
n
d
E
n
g
in
e
e
rin
g
,
S
RCOEM
,
Na
g
p
u
r
,
I
n
d
ia
Art
icle
I
nfo
AB
ST
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Dec
2
2
,
2
0
1
3
R
ev
i
s
ed
Ma
r
2
2
,
2
0
1
4
A
cc
ep
ted
A
p
r
2
8
,
2
0
1
4
T
e
x
t
su
m
m
a
riza
ti
o
n
is
a
n
o
ld
c
h
a
ll
e
n
g
e
in
te
x
t
m
in
in
g
b
u
t
in
d
ire
n
e
e
d
o
f
re
se
a
rc
h
e
r’s
a
tt
e
n
ti
o
n
in
t
h
e
a
re
a
s
o
f
c
o
m
p
u
tatio
n
a
l
i
n
telli
g
e
n
c
e
,
m
a
c
h
in
e
lea
rn
in
g
a
n
d
n
a
tu
ra
l
lan
g
u
a
g
e
p
ro
c
e
ss
in
g
.
W
e
e
x
trac
t
a
se
t
o
f
fe
a
tu
re
s f
ro
m
e
a
c
h
se
n
ten
c
e
th
a
t
h
e
lp
s
id
e
n
ti
fy
it
s
i
m
p
o
rtan
c
e
in
th
e
d
o
c
u
m
e
n
t.
Ev
e
r
y
ti
m
e
re
a
d
in
g
f
u
ll
tex
t
is
ti
m
e
c
o
n
su
m
i
n
g
.
Clu
ste
rin
g
a
p
p
ro
a
c
h
is
u
se
f
u
l
to
d
e
c
i
d
e
w
h
ich
t
y
p
e
o
f
d
a
ta
p
re
se
n
t
in
d
o
c
u
m
e
n
t.
In
t
h
is
p
a
p
e
r
w
e
in
tro
d
u
c
e
th
e
c
o
n
c
e
p
t
o
f
k
-
m
e
a
n
c
lu
ste
rin
g
f
o
r
n
a
tu
ra
l
lan
g
u
a
g
e
p
ro
c
e
ss
in
g
o
f
te
x
t
f
o
r
w
o
rd
m
a
tch
in
g
a
n
d
i
n
o
r
d
e
r
to
e
x
trac
t
m
e
a
n
in
g
f
u
l
in
f
o
rm
a
ti
o
n
f
ro
m
la
rg
e
se
t
o
f
o
f
f
li
n
e
d
o
c
u
m
e
n
ts,
d
a
ta m
in
in
g
d
o
c
u
m
e
n
t
c
lu
ste
rin
g
a
lg
o
rit
h
m
a
re
a
d
o
p
te
d
.
K
ey
w
o
r
d
:
K
-
m
ea
n
cl
u
s
ter
in
g
Ste
m
m
i
n
g
T
er
m
Fre
q
u
en
c
y
T
ex
t su
m
m
ar
izatio
n
Co
p
y
rig
h
t
©
201
4
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
:
P
an
k
aj
B
h
o
le,
Dep
ar
te
m
en
t
o
f
C
o
m
p
u
ter
Sci
en
ce
an
d
E
n
g
i
n
ee
r
in
g
,
Sh
r
i Ra
m
d
eo
b
ab
a
C
o
lleg
e
o
f
E
n
g
i
n
ee
r
i
n
g
a
n
d
Ma
n
e
g
m
en
t,
Nag
p
u
r
E
m
ail: b
h
o
lep
a
n
k
aj
1
2
3
@
g
m
ai
l.c
o
m
1.
I
NT
RO
D
UCT
I
O
N
W
ith
th
e
r
ap
id
g
r
o
w
i
n
g
p
o
p
u
l
ar
it
y
o
f
t
h
e
I
n
ter
n
et
a
n
d
a
v
ar
i
et
y
o
f
i
n
f
o
r
m
atio
n
s
er
v
ices,
o
b
tain
i
n
g
th
e
d
esire
d
in
f
o
r
m
atio
n
w
it
h
i
n
a
s
h
o
r
t
a
m
o
u
n
t
o
f
t
i
m
e
b
ec
o
m
es
a
s
er
io
u
s
p
r
o
b
le
m
i
n
th
e
in
f
o
r
m
atio
n
a
g
e.
Au
to
m
a
tic
te
x
t s
u
m
m
ar
izatio
n
p
r
o
v
id
es a
n
e
f
f
ec
tiv
e
m
ea
n
s
t
o
ac
ce
s
s
th
e
ex
p
o
n
e
n
tial
l
y
i
n
c
r
ea
s
ed
co
llectio
n
o
f
in
f
o
r
m
atio
n
.
Do
cu
m
e
n
t
s
u
m
m
ar
izatio
n
ca
n
g
e
n
er
at
e
a
s
u
m
m
ar
y
t
h
at
co
n
tai
n
s
t
h
e
m
o
s
t
im
p
o
r
ta
n
t
p
o
in
ts
o
f
a
d
o
cu
m
en
t,
w
h
ic
h
h
a
s
b
ee
n
ap
p
lied
to
m
an
y
s
p
ec
i
f
ic
d
o
m
ai
n
s
i
n
clu
d
i
n
g
b
io
m
ed
ical
(
L
i
n
g
et
al.
,
2
0
0
7
)
,
em
ail
th
r
ea
d
s
s
u
m
m
ar
izat
io
n
(
Z
aj
ic
et
al.
,
2
0
0
8
)
an
d
p
aten
t
d
o
cu
m
e
n
t
a
n
al
y
s
i
s
(
T
s
en
g
et
a
l
.
2
0
0
7
)
[
3
]
.
T
h
is
tech
n
o
lo
g
y
m
a
y
also
b
en
e
f
it
tex
t
p
r
o
ce
s
s
in
g
s
u
c
h
as
d
o
cu
m
e
n
t
clas
s
i
f
icatio
n
(
Sh
e
n
et
al.
2
0
0
4
)
[
4
]
an
d
q
u
esti
o
n
a
n
s
w
er
in
g
(
De
m
n
er
-
Fu
s
h
m
a
n
an
d
L
in
2
0
0
6
)
[
5
]
.
Au
to
m
a
ted
tex
t
s
u
m
m
ar
izatio
n
f
o
cu
s
ed
t
w
o
m
ain
id
ea
s
h
av
e
em
er
g
ed
to
d
ea
l
w
i
th
t
h
is
ta
s
k
;
t
h
e
f
ir
s
t
w
a
s
h
o
w
a
s
u
m
m
ar
izer
h
as
to
tr
ea
t
a
h
u
g
e
q
u
a
n
tit
y
o
f
d
ata
a
n
d
th
e
s
ec
o
n
d
,
h
o
w
it
m
a
y
b
e
p
o
s
s
ib
le
to
p
r
o
d
u
ce
a
h
u
m
an
q
u
ali
t
y
s
u
m
m
ar
y
.
Dep
en
d
in
g
o
n
t
h
e
n
at
u
r
e
o
f
tex
t
r
ep
r
esen
tatio
n
in
th
e
s
u
m
m
ar
y
,
s
u
m
m
ar
y
ca
n
b
e
ca
teg
o
r
ized
as
an
ab
s
tr
ac
t
a
n
d
an
e
x
tr
ac
t.
An
e
x
tr
ac
t
i
s
a
s
u
m
m
ar
y
co
n
s
is
t
in
g
o
f
a
n
u
m
b
er
o
f
s
alie
n
t
tex
t
u
n
its
s
elec
ted
f
r
o
m
t
h
e
in
p
u
t.
An
ab
s
tr
ac
t
i
s
a
s
u
m
m
ar
y
,
w
h
ic
h
r
ep
r
esen
t
s
t
h
e
s
u
b
j
ec
t
m
atter
o
f
t
h
e
ar
ticle
w
it
h
th
e
te
x
t
u
n
its
,
w
h
i
ch
ar
e
g
en
er
ated
b
y
r
ef
o
r
m
u
la
tin
g
th
e
s
alie
n
t
u
n
it
s
s
elec
ted
f
r
o
m
th
e
i
n
p
u
t.
An
ab
s
tr
ac
t
m
a
y
co
n
tain
s
o
m
e
t
ex
t
u
n
its
,
w
h
ic
h
ar
e
n
o
t
p
r
es
en
t
i
n
to
t
h
e
i
n
p
u
t
tex
t.
I
n
g
en
er
al,
th
e
tas
k
o
f
d
o
cu
m
en
t
s
u
m
m
ar
iza
tio
n
co
v
er
s
g
en
er
ic
s
u
m
m
ar
izatio
n
an
d
q
u
er
y
-
o
r
ien
ted
s
u
m
m
ar
i
za
tio
n
.
T
h
e
q
u
er
y
-
o
r
ien
ted
m
eth
o
d
g
e
n
er
ates
s
u
m
m
ar
ies
o
f
d
o
cu
m
e
n
t
s
ac
co
r
d
in
g
to
g
i
v
en
q
u
er
ie
s
o
r
to
p
i
cs,
an
d
th
e
g
e
n
er
ic
m
et
h
o
d
s
u
m
m
ar
izes t
h
e
o
v
er
al
l sen
s
e
o
f
th
e
d
o
cu
m
e
n
t
w
it
h
o
u
t a
n
y
ad
d
itio
n
al
i
n
f
o
r
m
atio
n
.
Yo
n
g
et
al.
[
6
]
w
o
r
k
ed
o
n
d
ev
elo
p
in
g
a
n
a
u
to
m
atic
tex
t
s
u
m
m
ar
izatio
n
s
y
s
te
m
b
y
co
m
b
in
i
n
g
b
o
th
a
s
tatis
t
ical
ap
p
r
o
ac
h
an
d
a
n
e
u
r
al
n
et
w
o
r
k
.
Mo
h
a
m
ed
A
b
d
el
Fattah
&
F
u
j
i
R
e
n
[
7
]
ap
p
lied
a
m
o
d
el
b
ased
o
n
a
g
en
et
ic
alg
o
r
it
h
m
(
G
A
)
a
n
d
m
at
h
e
m
atica
l
r
e
g
r
ess
io
n
(
MR)
in
o
r
d
er
to
o
b
tain
a
s
u
ita
b
le
co
m
b
i
n
atio
n
o
f
f
ea
t
u
r
e
w
e
ig
h
t
s
to
s
u
m
m
ar
ize
o
n
e
h
u
n
d
r
ed
E
n
g
lis
h
ar
ticle
s
.
Ha
m
id
et
al.
[
8
]
p
r
o
p
o
s
ed
a
n
e
w
tec
h
n
iq
u
e
to
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8938
IJ
-
AI
Vo
l.
3
,
No
.
2
,
J
u
n
e
201
4
:
73
–
78
74
o
p
tim
ize
tex
t
s
u
m
m
ar
izatio
n
b
ased
o
n
f
u
zz
y
lo
g
ic
b
y
s
ele
ctin
g
a
s
et
o
f
f
ea
tu
r
e
s
n
a
m
e
l
y
s
e
n
ten
ce
le
n
g
th
,
en
ten
ce
p
o
s
itio
n
,
ti
tles
s
i
m
il
ar
it
y
,
k
e
y
w
o
r
d
s
s
i
m
ila
r
it
y
,
s
e
n
ten
ce
-
to
-
s
e
n
te
n
ce
co
h
es
io
n
a
n
d
o
cc
u
r
r
en
ce
o
f
p
r
o
p
er
n
a
m
es
[9
]
.
T
r
a
d
itio
n
al
d
o
cu
m
e
n
ts
cl
u
s
ter
in
g
al
g
o
r
it
h
m
s
u
s
e
th
e
f
u
ll
-
te
x
t
in
t
h
e
d
o
cu
m
en
ts
to
g
e
n
er
ate
f
ea
t
u
r
e
v
ec
to
r
s
.
Su
c
h
m
e
th
o
d
s
o
f
te
n
p
r
o
d
u
ce
u
n
s
atis
f
ac
to
r
y
r
es
u
l
ts
b
ec
au
s
e
t
h
er
e
is
m
u
c
h
n
o
i
s
y
i
n
f
o
r
m
atio
n
i
n
d
o
cu
m
en
ts
.
T
h
e
v
ar
y
i
n
g
-
len
g
t
h
p
r
o
b
le
m
o
f
t
h
e
d
o
cu
m
en
ts
i
s
also
a
s
i
g
n
if
ican
t
n
e
g
ati
v
e
f
ac
to
r
af
f
ec
tin
g
t
h
e
p
er
f
o
r
m
a
n
ce
.
T
h
is
tec
h
n
iq
u
e
r
etr
iev
es
i
m
p
o
r
tan
t
s
en
te
n
ce
e
m
p
h
a
s
ize
o
n
h
i
g
h
in
f
o
r
m
a
ti
o
n
r
ich
n
es
s
i
n
t
h
e
s
en
te
n
ce
as
w
ell
as
h
ig
h
in
f
o
r
m
atio
n
r
etr
iev
al.
T
h
ese
m
u
lt
ip
le
f
ac
to
r
s
h
elp
to
m
a
x
i
m
ize
co
v
er
ag
e
o
f
ea
ch
s
en
te
n
ce
b
y
ta
k
i
n
g
i
n
to
ac
co
u
n
t th
e
s
en
ten
ce
r
elate
d
n
e
s
s
to
all
o
th
er
d
o
cu
m
e
n
t se
n
te
n
ce
.
T
h
ese
r
elate
d
m
a
x
i
m
u
m
s
e
n
t
en
ce
g
en
er
ated
s
co
r
es
ar
e
cl
u
s
ter
ed
to
g
e
n
er
ate
t
h
e
s
u
m
m
ar
y
o
f
t
h
e
d
o
cu
m
en
t.
T
h
u
s
w
e
u
s
e
k
-
m
ea
n
cl
u
s
ter
i
n
g
to
th
e
s
e
m
a
x
i
m
u
m
s
e
n
te
n
ce
s
o
f
t
h
e
d
o
cu
m
e
n
t
an
d
f
i
n
d
t
h
e
r
elatio
n
to
ex
tr
ac
t
cl
u
s
ter
s
w
it
h
m
o
s
t
r
elev
an
t
s
et
s
i
n
t
h
e
d
o
cu
m
en
t,
t
h
ese
h
elp
s
to
f
i
n
d
t
h
e
s
u
m
m
ar
y
o
f
th
e
d
o
cu
m
e
n
t.
T
h
e
m
ai
n
p
u
r
p
o
s
e
o
f
k
-
m
ea
n
clu
s
ter
i
n
g
al
g
o
r
ith
m
i
s
to
g
en
er
ate
p
r
e
d
ef
i
n
e
len
g
t
h
o
f
s
u
m
m
ar
y
h
a
v
i
n
g
m
ax
i
m
u
m
in
f
o
r
m
a
tiv
e
s
en
te
n
ce
s
.
I
n
th
is
p
ap
er
w
e
p
r
esen
t
t
h
e
ap
p
r
o
ac
h
f
o
r
au
to
m
atic
tex
t
s
u
m
m
ar
izatio
n
b
y
ex
tr
ac
tio
n
o
f
s
en
te
n
ce
s
f
r
o
m
t
h
e
R
eu
ter
s
-
2
1
5
7
8
co
r
p
u
s
w
h
i
ch
i
n
cl
u
d
e
n
e
w
s
p
ap
er
ar
ticle
s
an
d
u
s
ed
clu
s
ter
i
n
g
ap
p
r
o
ac
h
f
o
r
ex
tr
ac
tio
n
s
u
m
m
ar
y
.
W
o
r
k
d
o
n
e
f
o
r
T
ex
t
Su
m
m
ar
izat
io
n
is
g
i
v
e
n
in
t
h
e
s
ec
tio
n
(
I
I
)
.
Sectio
n
(
I
I
I
)
p
r
o
v
id
ed
o
u
r
m
e
th
o
d
o
lo
g
y
f
o
r
T
ex
t
Su
m
m
ar
izatio
n
,
Sectio
n
(
I
V)
p
r
o
v
id
e
th
e
r
esu
lt
o
f
o
u
r
te
x
t
s
u
m
m
ar
izatio
n
s
y
s
te
m
.
1
.
1
.
M
o
t
iv
a
t
io
n
T
h
e
m
o
ti
v
atio
n
o
f
n
at
u
r
al
la
n
g
u
a
g
e
b
ased
tex
t
s
u
m
m
ar
iz
atio
n
s
y
s
te
m
o
n
n
e
w
s
p
ap
er
co
m
e
f
r
o
m
n
e
w
s
b
ased
ap
p
licatio
n
f
o
r
m
o
b
ile.
E
v
er
y
p
er
s
o
n
w
an
t
s
to
b
e
g
lo
b
alize
d
w
ith
k
n
o
w
led
g
e
an
d
i
n
f
o
r
m
atio
n
.
Mo
s
t
o
f
th
e
u
s
er
r
ea
d
n
e
w
s
o
n
m
o
b
ile
ap
p
licatio
n
.
B
u
t
t
h
e
n
e
w
s
al
w
a
y
s
v
er
y
lar
g
e
a
n
d
d
escr
ip
tiv
e.
I
n
m
o
d
er
n
w
o
r
ld
ev
er
y
o
n
e
w
a
n
ts
f
ast
a
n
d
f
u
l
l
i
n
f
o
r
m
atio
n
,
s
o
in
th
is
ca
s
e
r
ea
d
in
g
co
m
p
lete
n
e
w
s
ti
m
e
co
n
s
u
m
i
n
g
.
So
f
o
r
f
a
s
te
n
an
d
i
m
p
o
r
tan
t
n
e
w
s
w
e
ca
n
p
r
o
v
id
e
te
x
t
s
u
m
m
ar
izatio
n
s
y
s
te
m
t
h
at
w
ill
a
n
al
y
s
i
s
te
x
t
in
f
o
r
m
a
tio
n
an
d
g
e
n
er
ate
s
h
o
r
t,
o
p
tim
a
l,
k
n
o
w
led
g
e
b
ased
s
u
m
m
ar
y
to
en
d
u
s
er
.
T
h
is
will
h
e
lp
u
s
to
s
a
v
e
ti
m
e
a
n
d
w
i
ll h
elp
s
in
b
etter
s
u
m
m
ar
y
.
2.
P
RO
P
O
SE
D
M
E
T
H
O
D
Au
to
m
a
tic
T
ex
t
Su
m
m
ar
izatio
n
i
m
p
o
r
tan
t
f
o
r
s
e
v
er
al
tas
k
s
,
s
u
c
h
as
i
n
s
ea
r
ch
e
n
g
in
e
w
h
ic
h
p
r
o
v
id
e
s
h
o
r
ter
in
f
o
r
m
atio
n
as
r
es
u
lt.
Ass
u
m
in
g
t
h
at
t
h
e
s
u
m
m
ar
iza
tio
n
tas
k
is
to
f
i
n
d
th
e
s
u
b
s
et
o
f
s
en
ten
ce
s
in
tex
t
w
h
ic
h
i
n
s
o
m
e
w
a
y
r
ep
r
ese
n
ts
m
a
in
co
n
ten
t
o
f
s
o
u
r
ce
te
x
t,
t
h
en
ar
i
s
es
a
n
at
u
r
al
q
u
es
tio
n
:
‘
w
h
a
t
ar
e
th
e
p
r
o
p
er
ties
o
f
tex
t
t
h
at
s
h
o
u
ld
b
e
r
ep
r
ese
n
ted
o
r
r
etain
ed
in
a
s
u
m
m
ar
y
’
.
A
s
u
m
m
ar
y
w
il
l
b
e
co
n
s
id
er
ed
g
o
o
d
,
if
t
h
e
s
u
m
m
ar
y
r
ep
r
ese
n
ts
th
e
w
h
o
le
co
n
te
n
t
o
f
t
h
e
d
o
cu
m
en
t.
Mo
tiv
ated
f
r
o
m
T
ex
t
S
u
m
m
ar
izatio
n
,
w
e
h
av
e
u
s
ed
d
ec
id
ed
to
u
s
e
th
is
ap
p
r
o
ac
h
f
o
r
in
f
o
r
m
atio
n
e
x
tr
a
ctio
n
.
T
h
is
is
v
er
y
d
i
f
f
icu
l
t
to
d
o
ab
s
tr
ac
tiv
e
s
u
m
m
ar
izatio
n
b
ec
a
u
s
e
o
f
v
e
r
y
lar
g
e
te
x
t
a
n
d
th
e
ir
in
ter
d
ep
en
d
en
ce
b
et
w
ee
n
s
e
n
ten
ce
s
,
d
if
f
ic
u
lt
to
m
a
k
e
ab
s
tr
ac
tiv
e
s
u
m
m
ar
y
.
W
e
h
av
e
p
r
o
p
o
s
ed
T
ex
t Su
m
m
ar
izat
i
o
n
m
et
h
o
d
o
lo
g
y
as
f
o
llo
w
s
.
I
n
th
i
s
s
ec
tio
n
,
w
e
d
escr
ib
e
in
d
etail
t
h
e
v
ar
io
u
s
co
m
p
o
n
en
t
s
o
f
t
h
e
f
r
a
m
e
w
o
r
k
o
f
th
e
o
u
r
m
et
h
o
d
o
lo
g
y
T
h
e
m
aj
o
r
co
m
p
o
n
e
n
ts
ar
e:
a.
P
r
e
-
p
r
o
ce
s
s
in
g
b.
Sen
te
n
ce
clu
s
ter
i
n
g
c.
C
lu
s
ter
o
r
d
er
in
g
d.
R
ep
r
esen
tat
iv
e
s
e
n
te
n
ce
s
elec
t
io
n
e.
Su
m
m
ar
y
g
en
er
atio
n
Fig
u
r
e
1
.
T
h
e
f
r
am
e
w
o
r
k
o
f
t
h
e
p
r
o
p
o
s
ed
s
en
ten
ce
cl
u
s
ter
i
n
g
b
ased
s
u
m
m
ar
izatio
n
s
y
s
te
m
Evaluation Warning : The document was created with Spire.PDF for Python.
IJ
-
AI
I
SS
N:
2252
-
8938
E
xtra
ctive
B
a
s
ed
S
in
g
le
Do
c
u
men
t Tex
t S
u
mma
r
iz
a
tio
n
Usi
n
g
C
lu
s
teri
n
g
A
p
p
r
o
a
ch
(
P
a
n
ka
j B
h
o
le
)
75
2
.
1
.
P
re
-
P
ro
ce
s
s
ing
W
e
p
r
o
v
id
e
th
e
in
p
u
t
i
n
th
e
f
o
r
m
o
f
tex
t
d
o
cu
m
en
t.
T
h
is
t
ex
t
co
n
tai
n
s
m
a
n
y
u
n
n
ec
es
s
ar
y
te
x
t
d
ata
an
d
s
y
m
b
o
ls
.
So
th
at
tex
t
w
ill
n
o
t
g
i
v
e
a
n
y
o
p
ti
m
al
s
o
l
u
tio
n
.
Fo
r
ef
f
icie
n
t
a
n
d
i
m
p
o
r
tan
t
s
u
m
m
ar
y
w
e
n
ee
d
to
r
e
m
o
v
e
t
h
e
u
n
n
ec
es
s
ar
y
d
ata.
T
h
er
ef
o
r
e
p
r
e
-
p
r
o
ce
s
s
in
g
i
s
th
e
n
ec
ess
ar
y
a
n
d
f
ir
s
t
s
tep
o
f
a
p
p
licatio
n
.
I
n
p
r
e
-
p
r
o
ce
s
s
in
g
w
e
ap
p
l
y
Sto
p
W
o
r
d
R
em
o
v
a
l,
Sto
p
S
y
m
b
o
l
R
e
m
o
v
al,
W
h
ite
s
p
ac
e
r
e
m
o
v
al
,
an
d
Ste
m
m
in
g
to
m
ak
e
r
o
o
t f
o
r
m
o
f
w
o
r
d
in
p
r
e
p
r
o
ce
s
s
tex
t.
Her
e
w
e
u
s
e
t
h
e
W
o
r
d
Net
L
ib
r
ar
y
f
o
r
ef
f
icie
n
t
s
te
m
m
i
n
g
.
I
f
t
h
er
e
ar
e
d
if
f
er
en
t
w
o
r
d
s
b
u
t
s
a
m
e
r
o
o
t f
o
r
m
t
h
e
it c
o
u
n
t a
s
s
in
g
le
w
o
r
d
in
s
tead
o
f
co
u
n
t
in
g
i
n
d
iv
id
u
all
y
.
S
to
p
W
o
r
d
s
={
th
at,
in
,
t
h
is
,
s
o
,
w
e,
is
,
ar
e
,
h
ad
,
h
av
e,
b
ec
au
s
e,
…}
Sto
p
S
y
m
b
o
l={
@
,
&
,
#
,
*
,
(
,
)
,
!
.
”,
+,
_
,
-
,
….
}
Fig
u
r
e
2
.
E
x
a
m
p
le
o
f
s
te
m
m
i
n
g
o
f
d
if
f
er
en
t f
o
r
m
s
o
f
w
o
r
d
b
r
o
k
en
2
.
2
.
So
m
e
F
ea
t
ure
Ca
lcula
t
i
o
n:
Fo
r
ef
f
icie
n
t
s
u
m
m
ar
izatio
n
,
it
is
n
ec
e
s
s
ar
y
to
ca
lc
u
late
s
o
m
e
e
f
f
icie
n
t
f
ea
t
u
r
e
f
o
r
o
p
tim
izi
n
g
t
h
e
clu
s
ter
i
n
g
an
d
s
u
m
m
ar
y
o
f
te
x
t.
a.
T
er
m
F
re
qu
e
ncy
:
T
h
e
h
y
p
o
th
e
s
is
ass
u
m
ed
b
y
t
h
i
s
ap
p
r
o
ac
h
i
s
t
h
at
i
f
t
h
er
e
ar
e
‘
‘
m
o
r
e
s
p
ec
i
f
i
c
w
o
r
d
s
’
’
i
n
a
g
i
v
en
s
en
te
n
ce
,
t
h
en
th
e
s
en
ten
ce
i
s
r
el
ativ
e
l
y
m
o
r
e
i
m
p
o
r
ta
n
t.
T
h
e
tar
g
et
w
o
r
d
s
ar
e
u
s
u
all
y
n
o
u
n
s
e
x
ce
p
t
f
o
r
te
m
p
o
r
al
o
r
ad
v
er
b
ial
n
o
u
n
s
(
Sato
s
h
i
et
al.
,
2
0
0
1
)
[
1
]
(
Mu
r
d
o
ck
,
2006)
[
2
]
.
T
h
is
alg
o
r
ith
m
p
er
f
o
r
m
s
a
co
m
p
ar
is
o
n
b
et
w
ee
n
t
h
e
ter
m
f
r
eq
u
en
c
ies (
T
F
)
in
a
d
o
cu
m
e
n
t
T
F(W)=
b.
Co
s
ine Si
m
ila
rit
y
:
C
o
s
i
n
e
s
i
m
ilar
it
y
i
s
a
p
o
p
u
lar
s
en
te
n
ce
-
to
-
s
en
te
n
ce
s
i
m
ilar
it
y
m
etr
ic
u
s
ed
i
n
m
an
y
cl
u
s
t
er
in
g
a
n
d
s
u
m
m
ar
izatio
n
tas
k
s
[
1
0
]
,
[
1
1
]
.
Sen
ten
ce
s
ar
e
r
ep
r
esen
t
ed
b
y
a
v
ec
to
r
o
f
w
ei
g
h
t
s
w
h
ile
co
m
p
u
ti
n
g
co
s
in
e
s
i
m
ilar
it
y
.
B
u
t,
th
e
f
ea
t
u
r
e
v
ec
to
r
co
r
r
esp
o
n
d
in
g
to
a
s
en
ten
ce
b
ec
o
m
es
to
o
s
p
ar
s
e
b
ec
au
s
e
s
en
te
n
ce
s
ar
e
to
o
s
h
o
r
t
i
n
s
ize
co
m
p
ar
ed
to
th
e
in
p
u
t
co
llectio
n
o
f
s
en
te
n
ce
s
.
So
m
eti
m
es
it
m
a
y
h
ap
p
en
th
at
t
w
o
s
e
n
te
n
ce
s
s
h
ar
in
g
o
n
l
y
o
n
e
h
i
g
h
er
f
r
eq
u
en
t
w
o
r
d
s
h
o
w
h
ig
h
co
s
i
n
e
s
i
m
ilar
it
y
v
al
u
e.
Sim
(
S
i
, S
j
)
=(
2*|
S
i
ᴖS
j
|
)
/
(
|
S
i
|
+
|
S
j
|)
W
h
er
e
S i
an
d
S j
ar
e
an
y
t
w
o
s
e
n
ten
ce
s
b
elo
n
g
i
n
g
to
th
e
in
p
u
t c
o
llectio
n
o
f
s
e
n
te
n
ce
s
.
T
h
e
n
u
m
er
ato
r
|
Siᴖ
S j
|
r
ep
r
ese
n
ts
n
u
m
b
er
o
f
m
atch
in
g
w
o
r
d
s
b
et
w
ee
n
t
w
o
s
en
te
n
c
es a
n
d
|
Si
|
is
th
e
le
n
g
th
o
f
th
e
i
-
t
h
s
e
n
te
n
ce
,
w
h
er
e
len
g
th
o
f
a
s
en
ten
ce
=n
u
m
b
er
o
f
w
o
r
d
s
i
n
t
h
e
s
en
t
en
ce
.
2
.
3
.
Sente
nce
Clus
t
er
ing
Sen
te
n
ce
cl
u
s
ter
i
n
g
i
s
t
h
e
i
m
p
o
r
ta
n
t
co
m
p
o
n
e
n
t
o
f
th
e
clu
s
ter
i
n
g
b
ased
s
u
m
m
ar
iza
tio
n
s
y
s
te
m
b
ec
au
s
e
s
u
b
-
to
p
ics
o
r
m
u
ltip
le
th
e
m
es
i
n
th
e
in
p
u
t
d
o
c
u
m
e
n
t
s
et
s
h
o
u
ld
p
r
o
p
er
ly
b
e
id
en
tif
ied
to
f
i
n
d
th
e
s
i
m
ilar
ities
a
n
d
d
is
s
i
m
ilar
itie
s
ac
r
o
s
s
t
h
e
d
o
cu
m
en
ts
.
C
lu
s
ter
i
n
g
o
f
s
e
n
te
n
ce
s
p
r
o
v
id
e
g
r
o
u
p
in
g
t
h
e
s
e
n
te
n
ce
w
h
i
ch
p
r
o
v
id
e
s
i
m
ilar
i
n
f
o
r
m
atio
n
.
Se
n
te
n
ce
clu
s
ter
i
n
g
is
t
h
e
i
m
p
o
r
tan
t
co
m
p
o
n
e
n
t
o
f
t
h
e
cl
u
s
ter
i
n
g
b
ased
s
u
m
m
ar
izatio
n
s
y
s
te
m
b
ec
au
s
e
s
u
b
-
to
p
ics
o
r
m
u
ltip
le
th
e
m
es
in
th
e
in
p
u
t
d
o
cu
m
e
n
t
s
et
s
h
o
u
ld
p
r
o
p
er
ly
b
e
id
en
ti
f
ied
to
f
i
n
d
th
e
s
i
m
i
lar
ities
a
n
d
d
is
s
i
m
ilar
itie
s
ac
r
o
s
s
t
h
e
d
o
cu
m
en
ts
.
C
lu
s
ter
in
g
s
h
o
u
ld
b
e
tig
h
t
a
n
d
n
o
t
g
e
n
er
ate
r
ed
u
n
d
a
n
c
y
o
f
s
e
n
te
n
ce
s
i
n
in
ter
-
c
lu
s
ter
an
d
in
tr
a
-
cl
u
s
ter
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8938
IJ
-
AI
Vo
l.
3
,
No
.
2
,
J
u
n
e
201
4
:
73
–
78
76
Her
e
K
-
Me
a
n
is
s
u
itab
le
f
o
r
th
is
t
y
p
e
o
f
clu
s
ter
i
n
g
.
I
t
m
ak
es
cla
s
s
i
f
icatio
n
o
f
v
ec
to
r
o
n
d
is
tan
t
m
ea
s
u
r
e.
W
e
ar
e
ca
lcu
latin
g
d
is
tan
ce
m
atr
i
x
f
r
o
m
th
e
co
s
i
n
e
s
i
m
i
lar
it
y
m
atr
i
x
.
Dis
t(
s
1
,
s
2
)
=1
-
C
o
s
in
e(
s
1
,
s
2
)
2
.
4
.
Clus
t
er
O
rder
ing
Sin
ce
o
u
r
s
en
te
n
ce
-
c
l
u
s
ter
i
n
g
alg
o
r
ith
m
i
s
f
u
ll
y
s
u
p
er
v
i
s
e
d
an
d
it
ass
u
m
e
p
r
io
r
k
n
o
w
le
d
g
e
ab
o
u
t
th
e
n
u
m
b
er
o
f
cl
u
s
ter
s
to
b
e
f
o
r
m
ed
,
it
i
s
cr
u
cial
to
d
ec
id
e
w
h
ich
cl
u
s
ter
w
o
u
l
d
co
n
tr
ib
u
te
th
e
r
ep
r
esen
tativ
e
f
ir
s
t
to
t
h
e
s
u
m
m
ar
y
.
I
n
s
tead
o
f
co
n
s
id
er
i
n
g
th
e
co
u
n
t
o
f
s
e
n
ten
ce
s
i
n
a
cl
u
s
ter
a
s
t
h
e
clu
s
ter
i
m
p
o
r
tan
ce
,
w
e
m
ea
s
u
r
e
th
e
i
m
p
o
r
ta
n
ce
o
f
a
clu
s
ter
b
ased
o
n
th
e
n
u
m
b
er
o
f
i
m
p
o
r
tan
t
w
o
r
d
s
it
co
n
tain
s
.
2
.
5
.
Repre
s
ent
a
t
iv
e
Sente
nce
Select
io
n
Selectin
g
m
o
s
t
i
n
f
o
r
m
ati
v
e
s
en
ten
ce
s
f
r
o
m
c
lu
s
ter
n
ee
d
r
an
k
i
n
g
al
g
o
r
ith
m
to
g
i
v
e
t
h
e
s
en
ten
ce
s
.
Af
ter
r
an
k
i
n
g
s
en
te
n
ce
s
in
t
h
e
clu
s
ter
b
ased
o
n
its
s
co
r
e
s
,
t
h
e
s
e
n
te
n
ce
w
it
h
h
ig
h
es
t
s
co
r
e
is
s
elec
ted
as
th
e
r
ep
r
esen
tati
v
e
s
e
n
te
n
ce
2
.
6
.
Su
m
m
a
ry
G
e
nera
t
io
n
W
e
s
elec
t
o
n
e
s
e
n
te
n
ce
f
r
o
m
t
h
e
to
p
m
o
s
t
cl
u
s
ter
f
ir
s
t
an
d
t
h
en
co
n
ti
n
u
e
s
elec
t
in
g
t
h
e
s
e
n
te
n
ce
s
f
r
o
m
th
e
s
u
b
s
eq
u
e
n
t c
l
u
s
ter
s
i
n
o
r
d
er
ed
lis
t u
n
t
il a
g
i
v
e
n
s
u
m
m
ar
y
len
g
th
i
s
r
ea
ch
ed
.
3.
RE
SU
L
T
S
T
h
e
E
x
p
er
im
e
n
tal
r
es
u
lt i
s
ap
p
lied
o
n
r
eu
ter
2
1
5
7
8
n
e
w
s
p
ap
er
co
r
p
u
s
.
T
ab
le
1
.
Deta
il o
f
R
eu
ter
2
1
5
7
8
d
ataset
N
u
mb
e
r
o
f
F
i
l
e
s
21
D
o
c
u
me
n
t
i
n
e
a
c
h
f
i
l
e
N
e
a
r
l
y
1
0
0
0
T
o
t
a
l
D
o
c
u
me
n
t
2
1
5
7
8
Fig
u
r
e
3
.
Ma
in
GUI
o
f
o
u
r
ap
p
licatio
n
p
r
o
v
id
e
in
p
u
t te
x
t b
o
x
,
in
ter
m
ed
iate
r
es
u
lt a
n
d
o
u
tp
u
t te
x
t b
o
x
Evaluation Warning : The document was created with Spire.PDF for Python.
IJ
-
AI
I
SS
N:
2252
-
8938
E
xtra
ctive
B
a
s
ed
S
in
g
le
Do
c
u
men
t Tex
t S
u
mma
r
iz
a
tio
n
Usi
n
g
C
lu
s
teri
n
g
A
p
p
r
o
a
ch
(
P
a
n
ka
j B
h
o
le
)
77
Fig
u
r
e
4
.
T
h
e
T
er
m
Fre
q
u
e
n
c
y
tab
le
o
f
in
p
u
t te
x
t
Fig
u
r
e
5.
T
h
e
Dis
tan
ce
m
a
tr
ix
o
f
in
p
u
t te
x
t p
r
o
v
id
e
d
is
s
i
m
i
la
r
it
y
v
al
u
e
o
f
s
en
te
n
ce
s
Fig
u
r
e
6.
C
lu
s
ter
in
g
o
f
s
en
te
n
ce
s
u
s
in
g
K
m
ea
n
al
g
o
r
ith
m
4
CO
NCLUS
I
O
N
AN
D
F
UT
UR
E
WO
RK
I
n
th
i
s
p
ap
er
w
e
h
a
v
e
s
ee
n
t
h
e
h
o
w
t
h
e
K
m
ea
n
clu
s
ter
in
g
i
s
ap
p
licab
le
in
s
u
m
m
ar
izatio
n
an
d
h
o
w
th
e
clu
s
ter
n
u
m
b
er
is
ef
f
ec
ti
v
e
o
n
q
u
alitativ
e
s
u
m
m
ar
y
Ou
r
w
o
r
k
f
o
cu
s
es
o
n
th
e
d
esig
n
o
f
a
s
u
cc
ess
f
u
l
clu
s
ter
i
n
g
b
ased
s
u
m
m
ar
izati
o
n
a
n
d
th
e
r
elate
d
i
s
s
u
es
s
u
ch
as
h
o
w
to
c
lu
s
ter
s
e
n
ten
ce
s
,
h
o
w
to
o
r
d
er
clu
s
ter
s
an
d
h
o
w
to
s
elec
t
r
ep
r
esen
tati
v
e
s
en
te
n
ce
s
f
r
o
m
th
e
clu
s
ter
s
.
T
h
e
b
etter
s
i
m
il
ar
it
y
m
ea
s
u
r
e
w
il
l
i
m
p
r
o
v
e
t
h
e
cl
u
s
ter
i
n
g
p
er
f
o
r
m
a
n
ce
an
d
t
h
i
s
m
a
y
i
m
p
r
o
v
e
t
h
e
s
u
m
m
ar
izat
io
n
p
er
f
o
r
m
an
ce
.
T
h
is
s
u
m
m
ar
izatio
n
ap
p
lied
o
n
n
e
w
s
ar
tic
le
o
r
d
o
cu
m
e
n
t
f
o
r
b
r
i
ef
s
u
m
m
ar
y
.
I
f
th
e
s
en
te
n
ce
i
n
in
p
u
t
te
x
t
in
cr
ea
s
es
th
en
f
o
r
b
etter
s
u
m
m
ar
y
n
u
m
b
er
o
f
clu
s
ter
s
h
o
u
ld
b
e
in
cr
ea
s
es.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
2
5
2
-
8938
IJ
-
AI
Vo
l.
3
,
No
.
2
,
J
u
n
e
201
4
:
73
–
78
78
F
ig
u
r
e
7.
T
h
e
r
elatio
n
b
et
w
ee
n
n
u
m
b
er
o
f
cl
u
s
ter
to
n
u
m
b
er
o
f
s
en
te
n
ce
s
RE
F
E
R
E
NC
E
S
[1
]
S
a
to
sh
i,
C
h
ik
a
sh
i
No
b
a
ta.,
S
a
to
s
h
i,
S
e
k
in
e
.
,
M
u
ra
ta,
M
a
sa
k
i.
,
Uc
h
im
o
to
,
Kiy
o
tak
a
.
,
Uti
y
a
m
a
,
M
a
sa
o
.
,
&
Isa
h
a
ra
,
Hito
sh
i.
Ke
ih
a
n
n
a
h
u
m
a
n
in
f
o
-
c
o
mm
u
n
ica
t
io
n
.
S
e
n
ten
c
e
e
x
tra
c
ti
o
n
sy
ste
m
a
ss
e
mb
li
n
g
mu
lt
i
p
le
e
v
id
e
n
c
e
.
In
P
r
o
c
e
e
d
in
g
s 2
n
d
NT
CIR w
o
rk
sh
o
p
,
p
p
.
3
19
–
3
2
4
,
2
0
0
1
.
[2
]
M
u
rd
o
c
k
,
V
a
n
e
ss
a
G
ra
h
a
m
.
As
p
e
c
ts
o
f
se
n
ten
c
e
re
tri
e
v
a
l.
P
h
.
D.
t
h
e
sis,
Un
iv
e
rsity
o
f
M
a
ss
a
c
h
u
se
tt
s,
Am
h
e
rst.
2
0
0
6
.
[3
]
T
se
n
g
,
Y.,
L
in
,
C.
,
&
L
in
,
Y.
Te
x
t
m
in
in
g
tec
h
n
iq
u
e
s
f
o
r
p
a
ten
t
a
n
a
ly
sis
.
In
fo
rm
a
ti
o
n
Pro
c
e
ss
in
g
&
M
a
n
a
g
e
me
n
t
,
v
o
l
4
3
(
5
),
p
p
1
2
1
6
–
1
2
4
7
,
2
0
0
7
.
[4
]
S
h
e
n
,
D.
,
Ch
e
n
,
Z.
,
Ya
n
g
,
Q.,
Ze
n
g
,
H.,
Z
h
a
n
g
,
B.
,
L
u
,
Y
.
,
e
t
a
l.
W
e
b
-
p
a
g
e
c
la
ss
ifi
c
a
ti
o
n
th
r
o
u
g
h
su
m
m
a
riza
ti
o
n
.
I
n
P
r
o
c
e
e
d
in
g
s
o
f
th
e
2
7
t
h
a
n
n
u
a
l
i
n
tern
a
ti
o
n
a
l
A
CM
S
IG
IR
c
o
n
fe
r
e
n
c
e
o
n
re
se
a
rc
h
a
n
d
d
e
v
e
lo
p
m
e
n
t
in
i
n
f
o
rm
a
ti
o
n
re
tri
e
v
a
l.
A
CM
,
p
p
.
2
4
9
,
2
0
0
4
.
[5
]
De
m
n
e
r
-
F
u
sh
m
a
n
,
D.,
&
L
in
,
J.
An
swe
r
e
x
tra
c
ti
o
n
,
se
ma
n
ti
c
c
lu
ste
rin
g
,
a
n
d
e
x
tra
c
ti
v
e
su
mm
a
riza
ti
o
n
f
o
r
c
li
n
ica
l
q
u
e
stio
n
a
n
swe
rin
g
.
I
n
P
r
o
c
e
e
d
i
n
g
s
o
f
th
e
2
1
st
in
ter
n
a
ti
o
n
a
l
c
o
n
f
e
r
e
n
c
e
o
n
c
o
m
p
u
tatio
n
a
l
l
in
g
u
is
ti
c
s
a
n
d
th
e
4
4
th
a
n
n
u
a
l
m
e
e
ti
n
g
o
f
th
e
a
ss
o
c
iatio
n
f
o
r
c
o
m
p
u
tatio
n
a
l
li
n
g
u
isti
c
s.
A
s
so
c
iatio
n
f
o
r
c
o
m
p
u
tatio
n
a
l
li
n
g
u
isti
c
s,
p
p
.
8
4
8
,
2
0
0
6
.
[6
]
Yo
n
g
,
S
.
P
.
,
A
h
m
a
d
I.
Z.
A
b
id
in
a
n
d
C
h
e
n
,
Y.Y
.
A
Ne
u
r
a
l
B
a
s
e
d
T
e
x
t
S
u
mm
a
riza
ti
o
n
S
y
ste
m
,
6
th
I
n
tern
a
ti
o
n
a
l
Co
n
f
e
re
n
c
e
o
f
D
ATA
M
ININ
G
,
p
p
.
4
5
-
5
0
,
2
0
0
5
.
[7
]
M
o
h
a
m
e
d
A
b
d
e
l
F
a
tt
a
h
a
n
d
F
u
ji
Re
n
.
A
u
to
m
a
ti
c
Tex
t
S
u
m
m
a
ri
z
a
ti
o
n
,
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
C
o
mp
u
ter
S
c
ien
c
e
,
No
.
1
,
p
p
.
2
5
-
2
8
,
2
0
0
8
.
[8
]
Ha
m
id
Kh
o
sra
v
i,
Esf
a
n
d
iar
Esla
m
i,
F
a
rsh
a
d
Ky
o
o
m
a
rsi
a
n
d
P
o
o
y
a
Kh
o
sra
v
y
a
n
De
h
k
o
rd
y
.
Op
ti
m
izin
g
Tex
t
S
u
m
m
a
riz
a
ti
o
n
Ba
se
d
o
n
F
u
z
z
y
L
o
g
ic”
,
S
p
rin
g
e
r
-
Ver
la
g
Co
m
p
u
t
e
r
a
n
d
In
f
o
rm
a
ti
o
n
S
c
ien
c
e
,
S
CI
1
3
1
,
p
p
.
1
2
1
-
1
3
0
,
2
0
0
8
.
[9
]
M
o
h
a
m
m
e
d
S
a
le
m
Bin
w
a
h
lan
,
Na
o
m
ie
S
a
li
m
a
n
d
L
a
d
d
a
S
u
a
n
m
a
l
i.
‘
S
w
a
r
m
Ba
se
d
F
e
a
tu
re
s
S
e
l
e
c
ti
o
n
f
o
r
T
e
x
t
S
u
m
m
a
riz
a
ti
o
n
’
,
In
ter
n
a
ti
o
n
a
l
J
o
u
rn
a
l
o
f
Co
m
p
u
ter
S
c
ien
c
e
a
n
d
Ne
two
rk
S
e
c
u
rity
,
Vo
l.
9
,
No
.
1
,
p
p
.
1
7
5
-
1
7
9
,
2
0
0
9
.
[1
0
]
G
.
Erk
a
n
a
n
d
D.
R.
Ra
d
e
v
.
L
e
x
Ra
n
k
:
Gra
p
h
-
b
a
se
d
c
e
n
tralit
y
a
s
sa
li
e
n
c
e
in
te
x
t
su
m
m
a
riza
t
io
n
.
J
o
u
rn
a
l
o
f
Arti
fi
c
ia
l
I
n
telli
g
e
n
c
e
Res
e
a
rc
h
(
J
AIR
),
2
0
0
4
.
[1
1
]
X
.
W
a
n
.
Us
in
g
o
n
ly
c
ro
ss
-
d
o
c
u
m
e
n
t
re
latio
n
sh
i
p
s
f
o
r
b
o
t
h
g
e
n
e
ric
a
n
d
to
p
ic
-
f
o
c
u
se
d
m
u
lt
i
-
d
o
c
u
m
e
n
t
su
m
m
a
riza
ti
o
n
s.
In
f
o
rm
a
ti
o
n
Re
tri
e
v
a
l.
V
o
l
1
1
:
2
5
–
4
9
,
2
0
0
8
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
P
a
n
k
a
j
K
Bh
o
le
:
re
c
e
iv
e
d
B
a
c
h
e
lo
r
o
f
En
g
in
e
e
rin
g
De
g
re
e
in
In
f
o
rm
a
ti
o
n
T
e
c
h
n
o
l
o
g
y
f
ro
m
Am
ra
v
a
ti
Un
iv
e
rsit
y
,
a
n
d
M
a
ste
r
o
f
T
e
c
h
n
o
lo
g
y
d
e
g
re
e
in
Co
m
p
u
ter
S
c
ien
c
e
&
En
g
in
e
e
rin
g
f
ro
m
S
h
ri
Ra
m
d
e
o
b
a
b
a
Co
l
leg
e
o
f
En
g
in
e
e
rin
g
&
M
a
n
a
g
e
m
e
n
t
Na
g
p
u
r,
I
n
d
ia
i
n
2
0
1
2
a
n
d
2
0
1
4
re
sp
e
c
ti
v
e
l
y
.
His
r
e
se
a
rc
h
a
re
a
is
Na
tu
ra
l
Lan
g
u
a
g
e
P
r
o
c
e
ss
in
g
.
He
is
h
a
v
in
g
1
1
m
o
n
th
s
o
f
tea
c
h
in
g
e
x
p
e
rien
c
e
.
Av
in
a
sh
J.
A
g
ra
wa
l:
re
c
e
iv
e
d
Ba
c
h
e
lo
r
o
f
En
g
in
e
e
rin
g
De
g
re
e
in
C
o
m
p
u
ter
T
e
c
h
n
o
l
o
g
y
f
ro
m
Na
g
p
u
r
Un
iv
e
rsit
y
,
In
d
ia
a
n
d
M
a
ste
r
o
f
Tec
h
n
o
lo
g
y
d
e
g
r
e
e
in
Co
m
p
u
ter
T
e
c
h
n
o
lo
g
y
f
ro
m
Na
ti
o
n
a
l
In
s
ti
tu
te
o
f
T
e
c
h
n
o
lo
g
y
,
Ra
ip
u
r,
In
d
ia
in
1
9
9
8
a
n
d
2
0
0
5
re
sp
e
c
ti
v
e
l
y
.
He
re
c
e
iv
e
d
P
h
.
D.
f
ro
m
V
isv
e
s
v
a
ra
y
a
Na
ti
o
n
a
l
In
stit
u
te
o
f
T
e
c
h
n
o
l
o
g
y
,
Na
g
p
u
r,
In
d
ia
i
n
2
0
1
3
.
His
re
se
a
rc
h
a
re
a
is
Na
tu
ra
l
L
a
n
g
u
a
g
e
P
ro
c
e
ss
in
g
a
n
d
Da
tab
a
se
s.
He
is
h
a
v
in
g
1
5
y
e
a
rs
o
f
tea
c
h
in
g
e
x
p
e
rien
c
e
.
P
re
se
n
tl
y
h
e
is
A
ss
istan
t
P
ro
f
e
ss
o
r
in
S
h
ri
Ra
m
d
e
o
b
a
b
a
C
o
ll
e
g
e
o
f
En
g
in
e
e
rin
g
&
M
a
n
a
g
e
m
e
n
t
Na
g
p
u
r,
In
d
ia
He
is
th
e
a
u
th
o
r
o
f
se
v
e
n
re
se
a
r
c
h
p
a
p
e
rs
in
In
tern
a
ti
o
n
a
l
a
n
d
Na
ti
o
n
a
l
J
o
u
r
n
a
l,
Co
n
f
e
re
n
c
e
s.
Evaluation Warning : The document was created with Spire.PDF for Python.