I
nte
rna
t
io
na
l J
o
urna
l o
f
E
lect
rica
l a
nd
Co
m
pu
t
er
E
ng
ineering
(
I
J
E
CE
)
Vo
l.
15
,
No
.
2
,
A
p
r
il
20
25
,
p
p
.
2
3
5
6
~
2
3
6
3
I
SS
N:
2088
-
8
7
0
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijece.
v
15
i
2
.
pp
2
3
5
6
-
2
3
6
3
2356
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ec
e.
ia
esco
r
e.
co
m
An inno
v
a
tive Ar
a
bic light st
emme
r develo
ped usi
ng
a hy
brid
a
ppro
a
ch
Driss
Na
m
ly
1
,
K
a
rim
B
o
uzo
ub
a
a
2
,3
1
D
e
p
a
r
t
me
n
t
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
M
o
h
a
mm
e
d
V
U
n
i
v
e
r
si
t
y
i
n
R
a
b
a
t
,
R
a
b
a
t
,
M
o
r
o
c
c
o
2
M
o
h
a
mm
a
d
i
a
S
c
h
o
o
l
o
f
E
n
g
i
n
e
e
r
s,
M
o
h
a
mm
e
d
V
U
n
i
v
e
r
s
i
t
y
i
n
R
a
b
a
t
,
R
a
b
a
t
,
M
o
r
o
c
c
o
3
D
e
p
a
r
t
me
n
t
o
f
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
,
U
n
i
v
e
r
s
i
t
y
o
f
R
o
e
h
a
mp
t
o
n
,
L
o
n
d
o
n
,
U
n
i
t
e
d
K
i
n
g
d
o
m
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
J
u
n
2
7
,
2
0
2
4
R
ev
is
ed
No
v
2
5
,
2
0
2
4
Acc
ep
ted
Dec
2
,
2
0
2
4
Ou
r
stu
d
y
in
tr
o
d
u
c
e
s
a
n
in
n
o
v
a
ti
v
e
li
g
h
t
ste
m
m
in
g
to
o
l
tail
o
re
d
f
o
r
Ara
b
ic
m
o
r
p
h
o
l
o
g
y
c
h
a
l
le
n
g
e
s
.
I
n
c
o
n
f
o
r
m
a
n
c
e
wi
t
h
t
h
e
tem
p
la
t
ic
a
n
d
c
o
n
c
a
ten
a
ti
v
e
stru
c
tu
re
s,
o
u
r
ste
m
m
e
r
u
ti
li
z
e
s
a
c
o
m
b
in
a
ti
o
n
o
f
c
li
ti
c
stri
p
p
i
n
g
,
lex
ico
n
-
b
a
se
d
,
a
n
d
sta
ti
stica
l
d
isa
m
b
i
g
u
a
ti
o
n
tec
h
n
iq
u
e
s
to
e
n
su
re
a
c
c
u
ra
te
ste
m
m
in
g
.
T
o
a
c
c
o
m
p
li
s
h
t
h
is,
we
re
ly
o
n
o
u
r
c
li
t
ic
ru
les
lex
ico
n
t
o
d
e
tec
t
a
ll
p
o
ten
t
ial
c
o
m
b
in
a
ti
o
n
s
o
f
c
li
t
ics
fo
r
e
a
c
h
in
p
u
t
e
n
tr
y
.
S
u
b
se
q
u
e
n
tl
y
,
we
d
e
p
e
n
d
o
n
a
n
e
x
ten
si
v
e
lex
ico
n
o
f
o
v
e
r
7
m
il
li
o
n
ste
m
s
to
v
e
rify
t
h
e
p
o
ten
ti
a
l
ste
m
s.
Las
tl
y
,
we
e
m
p
l
o
y
a
sta
ti
stica
l
m
o
d
e
l
t
o
a
sc
e
rtain
t
h
e
m
o
st
li
k
e
ly
ste
m
b
a
se
d
o
n
th
e
s
e
n
ten
c
e
'
s
c
o
n
tex
t.
E
x
p
e
rime
n
t
a
l
re
su
lt
s
d
e
m
o
n
stra
te
t
h
e
e
ffe
c
ti
v
e
n
e
ss
o
f
th
e
p
r
o
p
o
se
d
ste
m
m
e
r
in
c
o
m
p
a
r
iso
n
with
e
x
isti
n
g
o
n
e
s.
Us
in
g
d
iffere
n
t
d
a
tas
e
ts,
o
u
r
ste
m
m
e
r
a
c
h
iev
e
s
h
ig
h
e
r
a
c
c
u
ra
c
y
a
n
d
F
1
sc
o
re
s,
h
ig
h
li
g
h
t
in
g
it
s e
fficie
n
c
y
i
n
Ara
b
ic ste
m
m
in
g
tas
k
s.
K
ey
w
o
r
d
s
:
Ar
ab
ic
lan
g
u
a
g
e
L
ar
g
e
lex
ico
n
Natu
r
al
lan
g
u
ag
e
p
r
o
ce
s
s
in
g
Stem
m
in
g
Su
p
er
v
is
ed
lear
n
in
g
T
h
is i
s
a
n
o
p
e
n
a
c
c
e
ss
a
rticle
u
n
d
e
r th
e
CC B
Y
-
SA
li
c
e
n
se
.
C
o
r
r
e
s
p
o
nd
ing
A
uth
o
r
:
Dr
is
s
Nam
ly
Dep
ar
tm
en
t o
f
C
o
m
p
u
ter
Scie
n
ce
,
Mo
h
am
m
ed
V
Un
iv
e
r
s
ity
in
R
ab
at,
Av
en
u
e
d
es Na
tio
n
s
Un
ies
,
B
.
P: 8
0
0
7
.
N.
U,
Ag
d
al,
R
ab
at,
M
o
r
o
cc
o
E
m
ail: d
.
n
am
ly
@
u
m
5
r
.
ac
.
m
a
1.
I
NT
RO
D
UCT
I
O
N
Stem
m
in
g
is
th
e
p
r
o
ce
s
s
o
f
r
e
m
o
v
in
g
p
r
ef
ix
es,
in
f
ix
es,
an
d
s
u
f
f
ix
es
f
r
o
m
a
w
o
r
d
th
at
h
as
u
n
d
er
g
o
n
e
d
er
iv
atio
n
o
r
in
f
lectio
n
,
r
esu
ltin
g
in
its
s
tem
f
o
r
m
[
1
]
.
Stem
m
in
g
to
o
ls
ca
n
b
e
class
if
ied
as
eith
er
r
o
o
t
-
b
ased
o
r
s
tem
-
b
ased
,
d
ep
e
n
d
in
g
o
n
th
e
ty
p
e
o
f
th
e
r
esu
ltin
g
f
o
r
m
[
2
]
.
Fo
r
ex
am
p
le,
wh
e
n
t
h
e
wo
r
d
“
ةب
ت
ك
م
لا
”
is
s
tem
m
ed
u
s
in
g
a
r
o
o
t
-
b
ased
s
tem
m
er
,
it r
esu
lts
in
th
e
r
o
o
t
“
بت
ك
”
,
wh
er
ea
s
a
s
tem
-
b
ased
s
te
m
m
er
p
r
o
d
u
ce
s
th
e
s
tem
“
ةب
ت
ك
م
”
.
T
h
ese
to
o
ls
ty
p
ic
ally
r
ely
o
n
o
n
e
o
r
m
o
r
e
o
f
th
e
f
iv
e
m
ain
s
tem
m
in
g
ap
p
r
o
a
ch
es.
Firstl
y
,
clitic
s
tr
ip
p
in
g
in
v
o
lv
es
r
em
o
v
i
n
g
s
o
m
e
clitics
f
r
o
m
wo
r
d
s
with
o
u
t
an
y
ad
d
itio
n
al
p
r
o
c
ess
in
g
[
3
]
.
Patter
n
d
etec
tio
n
r
elies
o
n
lin
g
u
is
tic
r
u
les
to
ex
p
lain
th
e
d
er
iv
atio
n
o
r
in
f
lectio
n
o
f
Ar
a
b
ic
wo
r
d
s
[
4
]
.
L
ex
ic
o
n
-
b
ased
m
eth
o
d
s
u
s
e
m
an
u
ally
co
n
s
tr
u
cted
lex
i
co
n
s
as
lo
o
k
u
p
tab
les
to
s
to
r
e
s
tem
s
o
r
r
o
o
ts
[
2
]
.
Statis
tical
ap
p
r
o
ac
h
es
id
en
tif
y
wo
r
d
f
ea
t
u
r
es
th
r
o
u
g
h
a
tr
ain
in
g
p
h
ase,
u
s
in
g
th
e
tr
ai
n
ed
m
o
d
el
to
d
eter
m
i
n
e
th
e
s
tem
s
o
f
n
ew
wo
r
d
s
[
3
]
.
L
astl
y
,
h
ea
v
y
s
tem
m
in
g
u
tili
ze
s
m
o
r
p
h
o
l
o
g
ical
an
aly
s
is
to
ex
tr
ac
t
s
tem
s
o
r
r
o
o
ts
f
r
o
m
in
p
u
t
wo
r
d
s
,
o
f
f
er
in
g
a
m
o
r
e
th
o
r
o
u
g
h
a
n
aly
s
is
[
5
]
–
[
7
]
.
A
s
u
r
v
ey
o
f
Ar
a
b
ic
lig
h
t
s
tem
m
in
g
ex
h
ib
its
v
ar
io
u
s
to
o
ls
,
ea
ch
with
ad
v
a
n
tag
es
an
d
d
r
awb
ac
k
s
.
L
ar
k
ey
et
a
l.'
s
L
ig
h
t1
0
s
tem
m
er
[
8
]
,
[
9
]
,
wh
ich
u
tili
ze
s
af
f
ix
s
tr
ip
p
in
g
,
is
wid
ely
u
s
ed
d
esp
ite
is
s
u
es
with
er
r
o
n
e
o
u
s
,
s
in
g
le,
an
d
am
b
i
g
u
o
u
s
o
u
tco
m
es.
Saad
an
d
Ash
o
u
r
[
1
0
]
in
tr
o
d
u
ce
d
a
n
o
v
el
af
f
ix
-
r
em
o
v
al
alg
o
r
ith
m
in
co
r
p
o
r
ated
in
to
W
E
KA
an
d
R
ap
id
Min
er
,
th
o
u
g
h
it
also
f
ac
ed
p
r
o
b
lem
s
with
am
b
ig
u
o
u
s
s
in
g
le
o
u
tp
u
t
an
d
er
r
o
n
e
o
u
s
s
tem
m
in
g
.
AR
L
Stem
[
1
1
]
f
o
cu
s
es
o
n
elim
in
atin
g
p
r
ef
ix
es,
s
u
f
f
ix
es,
an
d
in
f
ix
es.
FAR
A
SA
[
1
2
]
em
p
lo
y
s
a
s
u
p
p
o
r
t
v
ec
to
r
m
ac
h
in
e
to
r
a
n
k
p
o
ten
tial
s
tem
s
b
u
t
lack
s
d
iacr
itic
m
ar
k
s
,
r
esu
ltin
g
in
am
b
ig
u
o
u
s
o
u
tp
u
t.
C
o
n
d
L
i
g
h
t
[
1
3
]
en
h
a
n
ce
s
L
ig
h
t
1
0
with
r
u
les
f
o
r
d
ef
in
ite
ar
ticles
a
n
d
p
lu
r
al
s
u
f
f
ix
es,
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
A
n
in
n
o
va
tive
A
r
a
b
ic
lig
h
t stemme
r
d
ev
elo
p
ed
u
s
in
g
a
h
yb
r
id
a
p
p
r
o
a
ch
(
Dri
s
s
N
a
mly
)
2357
s
h
o
win
g
a
5
%
r
etr
iev
al
im
p
r
o
v
em
en
t
b
u
t
s
till
s
tr
u
g
g
lin
g
with
er
r
o
n
e
o
u
s
s
tem
m
in
g
.
T
ash
a
p
h
y
n
e
0
.
4
[
1
4
]
u
s
es
a
Fin
ite
-
State
Au
to
m
ato
n
,
p
r
o
d
u
cin
g
s
in
g
le,
a
m
b
ig
u
o
u
s
s
tem
s
.
Ass
em
Ar
ab
ic
lig
h
t
s
tem
m
in
g
alg
o
r
ith
m
[
1
5
]
,
p
ar
t o
f
th
e
Sn
o
wb
all
s
tem
m
er
,
p
er
f
o
r
m
s
clitic
s
tr
ip
p
in
g
f
o
llo
wed
b
y
p
atter
n
m
atch
in
g
b
u
t is p
r
o
n
e
to
in
co
r
r
ec
t
s
tem
m
in
g
.
Mo
r
p
h
o
l
o
g
ical
an
a
ly
ze
r
s
[
5
]
–
[
7
]
,
[
1
6
]
–
[
1
9
]
p
r
o
v
id
e
co
m
p
r
eh
en
s
iv
e
d
iacr
itized
f
o
r
m
s
a
n
d
v
ar
io
u
s
f
ea
tu
r
es,
lead
in
g
t
o
in
cr
ea
s
ed
am
b
ig
u
ity
b
y
p
r
esen
tin
g
all
p
o
s
s
ib
le
s
o
lu
tio
n
s
f
o
r
ea
ch
wo
r
d
.
Desp
ite
ad
v
an
ce
m
en
ts
in
Ar
ab
ic
s
tem
m
in
g
,
ex
is
tin
g
s
tem
m
er
s
en
co
u
n
ter
th
e
ch
allen
g
es o
f
er
r
o
n
e
o
u
s
s
tem
m
in
g
,
am
b
i
g
u
o
u
s
o
u
tp
u
t,
s
in
g
le
o
u
tco
m
e,
a
n
d
th
e
li
n
g
u
is
tic
s
p
ec
if
icities
o
f
Ar
ab
ic
th
at
h
in
d
er
th
eir
ef
f
ec
tiv
en
ess
.
T
h
e
f
ir
s
t
is
s
u
e
i
s
er
r
o
n
eo
u
s
s
tem
m
in
g
,
wh
er
e
s
u
b
s
tr
in
g
s
with
in
wo
r
d
s
ar
e
in
co
r
r
ec
tly
id
en
tifie
d
as
af
f
ix
es
o
r
p
ar
ts
o
f
s
tem
s
.
Fo
r
in
s
tan
ce
,
t
h
e
wo
r
d
“
ط
اسوأ
”
(
OwsAT)
ca
n
b
e
in
ac
c
u
r
ately
s
tem
m
ed
as
“
ط
ا
َ
س
ْ
و
َ
أ
”
(
Mid
s
ts
)
,
“
ط
ا
َ
س
َ
و
+
َ
أ
”
(
I
s
W
A
S
AT
)
,
o
r
“
ط
ا
َ
س
+
َ
و
َ
أ
”
(
Did
h
e
f
l
ag
ellate?
)
.
An
o
th
er
s
ig
n
if
ica
n
t
ch
allen
g
e
is
th
e
am
b
ig
u
ity
in
o
u
t
p
u
t
d
u
e
to
n
o
n
-
d
iacr
itized
s
tem
s
.
T
h
is
lead
s
to
m
u
ltip
le
in
ter
p
r
etatio
n
s
o
f
a
s
in
g
le
s
tem
.
Fo
r
ex
am
p
le,
th
e
s
tem
o
f
th
e
wo
r
d
“
اه
لمجو
”
(
wjm
lh
A)
is
“
لم
ج
”
(
jm
l)
with
th
e
p
r
ef
ix
“
و
”
(
w)
an
d
th
e
s
u
f
f
ix
“
اه
”
(
h
A)
.
Ho
we
v
er
,
t
h
e
n
o
n
-
d
iacr
itized
s
tem
“
لم
ج
”
ca
n
r
ef
er
to
v
ar
io
u
s
m
ea
n
in
g
s
,
in
clu
d
in
g
“
ل
َ
م
َ
ج
”
(
C
am
el)
,
“
ل
ُ
م
َ
ج
”
(
B
e
co
m
ely
)
,
“
ل
م
َ
ج
”
(
Ma
k
e
it
p
r
etty
)
,
o
r
“
ل
َ
م
ُ
ج
”
(
Sen
te
n
ce
s
)
.
Fu
r
th
er
m
o
r
e,
m
an
y
s
te
m
m
er
s
p
r
o
d
u
ce
o
n
ly
a
s
in
g
le
o
u
tco
m
e,
d
is
r
eg
ar
d
in
g
th
e
lin
g
u
is
tic
r
ea
lity
t
h
at
wo
r
d
s
ca
n
p
o
s
s
ess
m
u
ltip
le
s
tem
s
.
Fo
r
in
s
tan
ce
,
th
e
wo
r
d
“
دوأ
”
(
OwlAd
)
ca
n
b
e
s
tem
m
ed
as
th
e
p
lu
r
al
“
د
َ
ْ
و
َ
أ
”
(
C
h
ild
r
en
)
,
th
e
n
o
u
n
“
د
َ
ِ
و
+
َ
أ
”
(
W
as
h
e
b
o
r
n
f
r
o
m
?)
,
o
r
th
e
v
er
b
“
ّ
د
َ
+
َ
و
َ
أ
”
(
An
d
d
id
h
e
q
u
ar
r
el
with
h
im
?
)
.
L
astl
y
,
t
h
e
u
n
i
q
u
e
c
h
ar
ac
ter
is
tics
o
f
th
e
Ar
ab
ic
lan
g
u
ag
e,
in
clu
d
in
g
th
e
lack
o
f
ca
p
italiz
atio
n
f
o
r
p
r
o
p
e
r
n
o
u
n
s
an
d
th
e
ab
s
en
ce
o
f
clea
r
r
u
les
f
o
r
b
r
o
k
en
p
lu
r
als,
f
u
r
th
er
d
im
in
is
h
th
e
ef
f
ec
tiv
e
n
ess
o
f
c
u
r
r
en
t stem
m
in
g
alg
o
r
ith
m
s
.
Ou
r
r
esear
ch
aim
s
to
cr
ea
te
a
n
o
v
el,
p
r
ec
is
e,
a
n
d
er
r
o
r
-
f
r
ee
Ar
ab
ic
lig
h
t
s
tem
m
er
th
at
ad
d
r
ess
es
th
e
lim
itatio
n
s
o
f
e
x
is
tin
g
s
tem
m
i
n
g
alg
o
r
ith
m
s
.
Pre
v
io
u
s
ap
p
r
o
ac
h
es
o
f
ten
s
tr
u
g
g
le
with
am
b
ig
u
o
u
s
o
u
tp
u
ts
an
d
ten
d
to
p
r
o
v
id
e
a
s
in
g
le
-
s
tem
o
u
tco
m
e,
wh
ich
d
o
es
n
o
t
r
ef
le
ct
th
e
lin
g
u
is
tic
r
ich
n
ess
o
f
th
e
Ar
ab
ic
lan
g
u
a
g
e.
Ou
r
p
r
o
p
o
s
ed
s
tem
m
in
g
ap
p
r
o
ac
h
lev
er
ag
es
a
d
ee
p
m
o
r
p
h
o
lo
g
ical
u
n
d
er
s
tan
d
i
n
g
o
f
Ar
ab
ic
w
o
r
d
s
to
o
v
er
co
m
e
th
ese
ch
allen
g
es.
T
h
is
m
eth
o
d
g
en
er
ates
all
p
o
ten
tial
s
tem
s
f
o
r
a
g
iv
en
wo
r
d
,
allo
win
g
f
o
r
a
m
o
r
e
co
m
p
r
eh
e
n
s
iv
e
an
aly
s
is
.
Fo
ll
o
win
g
th
is
,
a
co
m
p
r
eh
en
s
iv
e
s
tem
s
lex
ico
n
v
er
if
ies
th
e
s
u
g
g
ested
s
tem
s
,
an
d
a
s
tatis
t
ical
alg
o
r
ith
m
ev
alu
ates
th
e
co
n
tex
t
to
d
eter
m
in
e
th
e
m
o
s
t
lik
ely
s
tem
,
en
s
u
r
in
g
th
at
th
e
o
u
tp
u
t
is
ac
cu
r
ate
an
d
c
o
n
tex
t
u
ally
r
ele
v
an
t.
T
h
e
im
p
lem
en
tatio
n
o
f
o
u
r
p
r
o
p
o
s
ed
s
tem
m
in
g
ap
p
r
o
ac
h
h
as
d
em
o
n
s
tr
ated
s
ig
n
if
ican
t
im
p
r
o
v
em
e
n
ts
.
Ou
r
d
e
v
elo
p
ed
s
tem
m
er
ef
f
ec
tiv
ely
id
en
tifie
s
all
p
o
s
s
ib
le
d
iacr
itized
s
tem
s
,
with
th
e
f
ir
s
t
s
tem
b
ein
g
th
e
m
o
s
t
p
r
o
b
a
b
le
b
as
ed
o
n
th
e
c
o
n
tex
t.
T
h
is
ad
v
a
n
ce
m
en
t
d
i
r
ec
tly
ad
d
r
ess
es
th
e
s
h
o
r
tco
m
in
g
s
o
f
ex
is
tin
g
s
tem
m
er
s
b
y
m
in
im
iz
in
g
am
b
ig
u
o
u
s
o
u
tp
u
ts
an
d
p
r
o
v
id
in
g
m
u
ltip
le
s
tem
o
p
tio
n
s
,
th
er
eb
y
en
h
a
n
cin
g
th
e
o
v
er
all
ac
cu
r
ac
y
a
n
d
r
eliab
ilit
y
o
f
Ar
ab
ic
s
tem
m
in
g
.
2.
P
RO
P
O
SE
D
AP
P
RO
ACH
Ou
r
Ar
ab
ic
lig
h
t
s
tem
m
er
(
AL
Stem
m
er
)
is
s
tr
u
ctu
r
ed
in
to
th
r
ee
d
is
tin
ct
s
tag
es,
as
illu
s
tr
ated
in
Fig
u
r
e
1
.
T
h
e
s
tem
m
in
g
p
r
o
ce
s
s
b
eg
in
s
with
a
p
r
ep
r
o
ce
s
s
in
g
in
clu
d
in
g
to
k
en
izatio
n
,
n
o
r
m
aliza
tio
n
,
a
n
d
v
o
ca
b
u
lar
y
g
e
n
er
atio
n
.
I
n
th
e
in
itial
s
tag
e,
p
o
ten
tial
clitics
ar
e
elim
in
ated
f
r
o
m
w
o
r
d
s
b
as
ed
o
n
a
p
r
ed
ef
in
e
d
clitic
r
u
les
lex
ico
n
,
g
iv
in
g
r
is
e
to
th
e
ca
n
d
i
d
ate
s
tem
s
.
T
h
e
lis
t
o
f
ca
n
d
id
ate
s
tem
s
is
th
en
v
alid
ated
in
t
h
e
s
ec
o
n
d
s
tag
e
u
s
in
g
a
lar
g
e
s
tem
s
lex
ico
n
.
T
h
e
f
in
al
s
tag
e
f
o
cu
s
es
o
n
r
eso
lv
in
g
t
h
e
am
b
ig
u
ity
o
f
th
e
v
alid
s
tem
s
b
y
em
p
lo
y
in
g
a
s
tatis
tic
al
alg
o
r
ith
m
to
d
eter
m
in
e
t
h
e
m
o
s
t p
r
o
b
a
b
le
o
n
e
with
in
th
e
g
iv
en
co
n
tex
t.
2
.
1
.
P
ha
s
e
1
:
rules
-
ba
s
ed
ph
a
s
e
I
n
th
is
p
h
ase,
o
u
r
p
r
im
ar
y
g
o
a
l
is
to
lev
er
ag
e
g
r
am
m
atica
l
r
u
les
to
ex
tr
ac
t
all
p
o
s
s
ib
le
s
tem
s
f
o
r
ea
ch
wo
r
d
.
B
y
co
n
s
id
er
in
g
m
u
ltip
l
e
p
o
ten
tial
s
tem
s
,
we
ef
f
ec
tiv
ely
ad
d
r
ess
th
e
lim
itatio
n
o
f
s
in
g
u
lar
o
u
tco
m
es
o
b
s
er
v
ed
in
o
th
er
s
tem
m
in
g
m
eth
o
d
s
.
T
h
is
ap
p
r
o
ac
h
alig
n
s
with
th
e
lin
g
u
is
tic
r
ea
lity
t
h
at
Ar
ab
ic
wo
r
d
s
ca
n
h
av
e
m
u
ltip
le
v
alid
s
tem
s
.
Fu
r
th
er
m
o
r
e
,
we
em
p
lo
y
a
clitic
s
tr
ip
p
in
g
tec
h
n
iq
u
e
to
en
h
a
n
ce
th
e
ef
f
icien
cy
o
f
th
e
s
tem
m
in
g
p
r
o
ce
s
s
.
Un
lik
e
o
th
er
s
tem
m
in
g
alg
o
r
ith
m
s
,
th
is
ap
p
r
o
ac
h
s
ig
n
i
f
ican
tly
r
ed
u
ce
s
p
r
o
ce
s
s
in
g
tim
e,
m
ak
in
g
t
h
e
p
r
o
ce
s
s
m
o
r
e
ef
f
ec
tiv
e
an
d
p
r
ac
tical
f
o
r
r
e
al
-
wo
r
ld
ap
p
licatio
n
s
.
Ar
ab
ic
co
n
ca
ten
ativ
e
m
o
r
p
h
o
l
o
g
y
is
d
ef
in
e
d
b
y
th
e
f
o
r
m
atio
n
o
f
wo
r
d
s
th
r
o
u
g
h
th
e
a
g
g
lu
t
in
atio
n
o
f
a
s
eq
u
en
ce
th
at
in
clu
d
es
a
p
r
o
clitic,
a
s
tem
,
an
d
an
en
clitic.
I
n
th
is
s
tr
u
ctu
r
e,
th
e
p
r
o
clitic
attac
h
es
b
ef
o
r
e
th
e
s
tem
,
wh
ile
th
e
en
clitic
i
s
p
o
s
i
tio
n
ed
af
ter
th
e
s
tem
.
B
o
th
p
r
o
clitics
an
d
en
clitics
ca
n
ex
is
t
in
ato
m
ic
f
o
r
m
s
o
r
as
co
m
b
in
atio
n
s
.
W
h
en
two
o
r
m
o
r
e
ato
m
ic
p
r
o
clitics
(
o
r
en
clitics
)
ar
e
co
m
b
in
ed
,
th
ey
cr
ea
te
a
s
in
g
le
co
m
b
in
ed
p
r
o
clitic
(
o
r
en
cliti
c)
.
Fo
r
in
s
tan
ce
,
th
e
co
m
b
in
e
d
p
r
o
clitic
“
ّ
َ
س
َ
أ
”
(
d
o
-
will)
is
f
o
r
m
ed
f
r
o
m
th
e
ato
m
ic
p
r
o
clitics
“
َ
أ
”
(
d
o
)
an
d
“
ّ
َ
س
”
(
will).
I
n
th
is
p
h
ase,
th
e
s
tem
m
er
f
ir
s
t
to
k
en
izes
an
d
n
o
r
m
alize
s
th
e
in
p
u
t
tex
t.
Fo
r
ea
ch
v
o
ca
b
u
lar
y
en
tr
y
,
th
e
s
tem
m
er
ex
p
lo
its
th
e
“
clitics
lex
ico
n
”
to
id
en
tify
all
p
o
ten
tial c
o
m
b
in
atio
n
s
o
f
clitics
attac
h
ed
to
th
e
wo
r
d
.
T
h
is
lex
ico
n
p
r
o
v
id
es
a
s
et
o
f
ca
n
d
id
ate
s
tem
s
b
ased
o
n
th
e
id
e
n
tifie
d
clitics
.
T
h
e
le
x
ico
n
o
f
clitic
r
u
les
in
clu
d
es
1
2
ato
m
ic
p
r
o
clitics
m
o
d
eled
u
s
in
g
9
g
r
am
m
atica
l
r
u
les,
alo
n
g
with
1
4
ato
m
ic
e
n
clitics
d
ef
in
ed
b
y
6
co
r
r
esp
o
n
d
in
g
r
u
les.
T
h
e
a
p
p
l
icatio
n
o
f
th
ese
clitic
r
u
les
r
e
s
u
lts
in
a
to
tal
o
f
9
4
p
r
o
clitics
an
d
7
3
en
clitics
,
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
2
,
Ap
r
il
20
25
:
2
3
5
6
-
2
3
6
3
2358
en
co
m
p
ass
in
g
b
o
th
ato
m
ic
a
n
d
co
m
b
in
ed
f
o
r
m
s
.
T
ab
le
1
p
r
o
v
id
es
ex
a
m
p
les
o
f
th
e
g
e
n
er
ated
ato
m
ic
an
d
co
m
b
in
ed
p
r
o
clitics
an
d
e
n
clitics
an
d
th
eir
u
s
ag
e,
c
o
m
p
o
s
itio
n
,
an
d
f
ea
tu
r
es.
T
o
illu
s
tr
ate
th
is
p
r
o
ce
s
s
,
l
et's
co
n
s
id
er
th
e
in
p
u
t
wo
r
d
“
هل
جأ
”
(
Ojlh
)
.
B
y
ap
p
ly
in
g
th
e
clitic
id
en
tific
atio
n
r
u
les,
th
e
s
tem
m
er
g
e
n
er
ates
f
o
u
r
p
o
ten
tial
s
eg
m
en
tatio
n
s
(
ه
+لج+
أ
ّ
،
ه
+ل
جأ
ّ
،
هل
ج+أ
ّ
،
هل
جأ
)
.
Fro
m
th
ese
s
eg
m
en
tatio
n
s
,
th
e
s
tem
m
er
id
en
tifie
s
th
e
p
o
ten
tial
clitics
“
أ
-
”
an
d
“
-
ه
”
an
d
ex
tr
ac
ts
th
e
p
r
o
b
a
b
le
s
tem
“
لج
”
(
jl)
b
ased
o
n
t
h
e
s
eg
m
en
t
atio
n
“
ه
+لج+
أّ=
ّ
هل
جأ
”
.
Fig
u
r
e
1
.
Pro
p
o
s
ed
ar
c
h
itectu
r
e
f
o
r
AL
Stem
m
er
T
ab
le
1
.
Sam
p
les o
f
ato
m
ic
an
d
co
m
b
i
n
ed
clitics
C
l
i
t
i
c
ّ
Ty
p
e
Ex
a
m
p
l
e
ّ
C
o
m
p
o
si
t
i
o
n
ّ
F
e
a
t
u
r
e
s
ّ
ّ
ِ
ب
W
i
t
h
P
r
o
c
l
i
t
i
c
ّ
ُ
ت
ْ
ع
َ
ط
َ
ق
ّ
ِ
ب
ّ
ِ
ن
ي
ِ
ك
ِ
س
ل
ا
ّ
I
c
u
t
w
i
t
h
t
h
e
k
n
i
f
e
ّ
ِ
ب
W
i
t
h
ّ
ّ
ر
ج
لا
ّ
فر
ح
P
r
e
p
o
si
t
i
o
n
ي
ةم
لك
لا
ّ
ر
ج
P
u
t
s
t
h
e
w
o
r
d
i
n
t
h
e
g
e
n
i
t
i
v
e
c
a
s
e
ّ
ا
َ
م
ُ
ك
Y
o
u
r
En
c
l
i
t
i
c
ّ
ْ
ي
َ
ت
َ
ب
ي
ِ
ق
َ
ح
ّ
َ
ِ
م
ْ
ح
ِ
ا
ّ
ا
َ
م
ُ
ك
C
a
r
r
y
y
o
u
r
t
w
o
b
a
g
s
ّ
ا
َ
م
ُ
ك
Y
o
u
r
ّ
ن
ي
ب
طا
خ
م
لا
ّ
ر
ي
م
ض
A
d
d
r
e
ss
e
e
s
p
r
o
n
o
u
n
ى
ن
ث
م
لا
ّ
،
ث
ن
ؤم
ل
اوّ
ر
ك
ذ
م
لل
،
ب
طا
خ
م
لا
ّ
f
e
mi
n
i
n
e
,
mas
c
u
l
i
n
e
,
d
u
a
l
,
2
n
d
p
e
r
s
o
n
ّ
ا
َ
ه
ي
ِ
ن
i
t
t
o
me
En
c
l
i
t
i
c
و
ُ
م
ُ
ت
ْ
ي
َ
ق
ْ
س
َ
أ
ّ
ي
ِ
ت
ل
ا
ّ
َ
س
و
ُ
ؤ
ُ
ك
ل
ا
ّ
ا
َ
ه
ي
ِ
ن
Th
e
c
u
p
s
y
o
u
g
a
v
e
i
t
t
o
me
ّ
ي
ِ
ن
t
o
me
ّ
ّ
م
لك
ت
م
لا
ّ
ء
ا
ي
+
ةي
ا
قول
اّ
ن
ون
P
r
e
v
e
n
t
i
o
n
n
w
n
a
n
d
s
p
e
a
k
e
r
y
A
’
ّ
م
لك
ت
م
لا
ّ
،
د
ر
ف
م
لا
ّ
،
ث
ن
ؤم
ل
اوّ
ر
ك
ذ
م
لا
f
e
mi
n
i
n
e
,
mas
c
u
l
i
n
e
,
s
i
n
g
u
l
a
r
,
1
st
p
e
r
s
o
n
ا
َ
ه
it
ةب
ئ
ا
غ
لا
ّ
ر
ي
م
ض
A
b
se
n
t
p
r
o
n
o
u
n
ب
ئ
ا
غ
ل
اّ
،
د
ر
ف
م
لا
ّ
،
ث
ن
ؤم
لا
f
e
mi
n
i
n
e
,
si
n
g
u
l
a
r
,
3
r
d
p
e
r
s
o
n
2
.
2
.
P
ha
s
e
2
:
L
ex
ico
n
-
ba
s
ed
ph
a
s
e
T
h
e
s
ec
o
n
d
p
h
ase
o
f
o
u
r
s
tem
m
er
is
cr
u
cial
in
en
s
u
r
in
g
t
h
e
v
alid
ity
o
f
th
e
ca
n
d
id
ate
s
tem
s
id
en
tifie
d
in
th
e
p
r
ev
io
u
s
p
h
ase.
W
e
ef
f
ec
tiv
ely
ad
d
r
ess
er
r
o
n
eo
u
s
an
d
am
b
ig
u
o
u
s
s
tem
m
in
g
co
n
ce
r
n
s
u
s
in
g
a
co
m
p
r
eh
e
n
s
iv
e
lex
ico
n
o
f
v
al
id
an
d
d
iacr
itized
s
tem
s
.
T
o
ac
h
iev
e
th
is
,
we
r
ely
o
n
co
m
p
r
eh
en
s
iv
e
Ar
ab
ic
L
E
Mm
as
(
C
AL
E
M
)
[
2
0
]
,
o
u
r
lar
g
e
lex
ico
n
o
f
Ar
ab
ic
s
tem
s
an
d
th
eir
co
r
r
esp
o
n
d
i
n
g
lem
m
as.
T
h
e
in
itial
s
et
o
f
ca
n
d
id
ate
s
tem
s
p
r
o
d
u
ce
d
in
th
e
p
r
ec
e
d
in
g
p
h
ase
is
u
s
ed
to
au
t
h
en
ticate
th
e
s
tem
s
b
y
ch
ec
k
i
n
g
t
h
eir
p
r
esen
ce
in
th
e
“
C
AL
E
M
l
ex
ico
n
”
.
I
f
a
ca
n
d
id
ate
s
tem
is
f
o
u
n
d
in
C
AL
E
M,
it
is
co
n
s
id
er
ed
v
alid
.
C
o
n
v
er
s
ely
,
if
a
ca
n
d
id
ate
s
tem
is
ab
s
en
t
in
C
AL
E
M,
it
in
d
icate
s
th
at
th
e
s
eg
m
en
tatio
n
r
e
s
u
ltin
g
in
th
is
s
tem
is
in
v
alid
.
Fo
r
in
s
tan
ce
,
b
y
ch
ec
k
in
g
th
e
p
r
o
b
ab
le
s
tem
“
لج
”
(
jl)
in
C
AL
E
M,
we
o
b
tain
two
v
alid
a
n
d
d
iacr
itized
s
tem
s
:
“
ّ
ل
ُ
ج
ّ
،
ل
َ
ج
”
(
B
e
m
ajestic,
m
o
s
t o
f
)
.
C
AL
E
M
was
co
n
s
tr
u
cted
u
s
i
n
g
a
d
atab
ase
co
m
p
r
is
in
g
th
e
m
o
s
t
co
m
m
o
n
ly
u
s
ed
Ar
a
b
ic
v
er
b
s
,
co
n
s
is
tin
g
o
f
2
4
,
1
7
1
v
er
b
s
g
e
n
er
ated
f
r
o
m
Ar
ab
ic
r
o
o
ts
.
Af
ter
co
n
ju
g
atin
g
th
ese
v
er
b
s
,
d
er
iv
ed
n
o
u
n
s
wer
e
o
b
tain
ed
b
y
a
p
p
ly
in
g
th
e
d
er
i
v
atio
n
p
r
o
ce
s
s
to
all
v
er
b
al
c
ateg
o
r
ies.
T
h
e
lex
ico
n
was
f
u
r
th
er
en
r
ich
ed
with
Ar
ab
ic
p
ar
ticles
an
d
n
o
n
-
d
er
i
v
ed
n
o
u
n
s
,
s
u
ch
as
p
r
o
p
er
n
o
u
n
s
an
d
b
r
o
k
en
p
lu
r
als,
to
e
n
co
m
p
ass
all
Ar
ab
ic
lan
g
u
ag
e
s
p
ec
if
icities
.
As
a
r
esu
lt,
C
AL
E
M
in
co
r
p
o
r
ates
1
6
6
,
9
6
3
lem
m
as
d
ep
icted
b
y
7
,
1
3
3
,
1
0
6
s
tem
s
in
th
eir
d
iacr
itized
f
o
r
m
.
T
h
is
co
m
p
r
eh
e
n
s
iv
e
ap
p
r
o
ac
h
h
el
p
s
p
r
ev
e
n
t
lan
g
u
ag
e
s
p
ec
if
icity
an
d
am
b
ig
u
o
u
s
o
u
tp
u
t sh
o
r
tco
m
in
g
s
d
u
r
in
g
th
e
s
tem
m
in
g
p
r
o
ce
s
s
.
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
A
n
in
n
o
va
tive
A
r
a
b
ic
lig
h
t stemme
r
d
ev
elo
p
ed
u
s
in
g
a
h
yb
r
id
a
p
p
r
o
a
ch
(
Dri
s
s
N
a
mly
)
2359
2
.
3
.
P
ha
s
e
3
:
s
t
a
t
is
t
ica
l pha
s
e
I
n
th
e
s
tatis
tical
s
tem
m
in
g
p
h
ase,
we
r
eso
lv
e
am
b
ig
u
ities
b
y
s
elec
tin
g
th
e
m
o
s
t
ap
p
r
o
p
r
iate
s
tem
f
r
o
m
a
lis
t
o
f
v
alid
s
tem
s
b
ase
d
o
n
th
e
s
en
ten
ce
'
s
co
n
tex
t.
T
h
is
p
r
o
ce
s
s
em
p
lo
y
s
a
s
u
p
e
r
v
i
s
ed
lear
n
in
g
m
et
h
o
d
to
id
en
tify
th
e
b
est
s
tem
f
o
r
e
ac
h
in
p
u
t
wo
r
d
,
co
n
s
id
er
i
n
g
it
s
s
u
r
r
o
u
n
d
in
g
wo
r
d
s
.
T
o
ac
co
m
p
lis
h
th
is
task
,
we
ca
n
u
s
e
a
g
e
n
er
ativ
e
m
o
d
el,
s
u
ch
as
th
e
“
h
id
d
en
Ma
r
k
o
v
m
o
d
el
(
HM
M)
”
o
r
“
lo
n
g
s
h
o
r
t
-
ter
m
m
em
o
r
y
(
L
STM
)
”
n
etwo
r
k
s
.
R
ec
en
t
r
esear
ch
[
2
1
]
h
as
in
d
icate
d
th
at
HM
Ms
ar
e
s
im
p
ler
an
d
m
o
r
e
tr
an
s
p
a
r
en
t
co
m
p
ar
ed
t
o
L
STM
s
,
m
ak
in
g
th
em
ef
f
ec
tiv
e
f
o
r
a
p
p
r
o
x
im
a
tin
g
th
e
p
er
f
o
r
m
an
ce
o
f
L
STM
s
.
T
h
is
s
im
p
licity
allo
ws
f
o
r
m
o
r
e
e
f
f
icien
t
tr
ain
in
g
an
d
ca
n
im
p
r
o
v
e
o
v
er
all
p
er
f
o
r
m
a
n
ce
.
T
h
e
r
ef
o
r
e
,
we
im
p
lem
en
t
an
HM
M
f
o
r
o
u
r
s
tatis
tical
s
tem
m
in
g
p
r
o
ce
s
s
.
I
n
o
u
r
HM
M
m
o
d
el,
“
o
b
s
er
v
e
d
s
tates
”
co
r
r
esp
o
n
d
to
th
e
wo
r
d
s
in
th
e
in
p
u
t
s
en
ten
ce
,
wh
il
e
“h
id
d
e
n
s
tates”
r
ep
r
esen
t
th
e
p
o
ten
tial
s
tem
s
id
en
tifie
d
d
u
r
in
g
t
h
e
s
ec
o
n
d
p
h
ase
o
f
th
e
s
tem
m
in
g
p
r
o
ce
s
s
.
Fo
r
ex
am
p
le,
as sh
o
wn
in
Fig
u
r
e
2
,
if
th
e
o
b
s
er
v
ed
s
tate
is
“
رس
”
(
s
r
)
,
th
e
h
id
d
en
s
tates c
o
u
ld
in
clu
d
e
“
َ
ر
ِ
س
”
(
walk
)
,
“
ر
ُ
س
”
(
u
m
b
ilical
co
r
d
)
,
“
َ
ر
ُ
س
”
(
b
e
h
ap
p
y
)
,
“
َ
ر
س
”
(
d
elig
h
t)
,
an
d
“
َ
ر
ِ
س
”
(
s
ec
r
et)
.
I
n
a
m
o
r
e
f
o
r
m
al
way
,
to
f
in
d
f
o
r
th
e
s
en
ten
ce
Ph
=
(
w
1
,
w
2
,
.
.
.
,
w
n
)
th
e
m
o
s
t
p
r
o
b
ab
le
s
eq
u
en
ce
o
f
s
tem
s
(
s
1
*
,s
2
*
,
…,
s
n
*
)
,
th
e
HM
M
m
o
d
el
λ
=
(
S,
A,
B
,
π)
ad
m
its
th
e
f
o
llo
win
g
p
ar
am
eter
s
:
S
=
{s
1
,
s
2
,
…,
s
m
}
th
e
s
et
o
f
s
tem
s
in
th
e
Ar
ab
ic
lan
g
u
ag
e
,
a
(
i,j)
th
e
p
r
o
b
ab
ilit
y
f
o
r
a
s
tem
s
i
to
b
e
f
o
llo
wed
b
y
th
e
s
tem
s
j
,
b
i
(
t)
th
e
p
r
o
b
a
b
ilit
y
f
o
r
t
h
e
wo
r
d
w
t
to
g
iv
e
th
e
s
tem
s
i
,
an
d
π
i
th
e
p
r
o
b
a
b
ilit
y
f
o
r
Ph
to
s
tar
t
with
th
e
s
tem
s
i
.
T
h
e
elem
en
ts
o
f
m
at
r
ices
A,
B
,
an
d
π
ar
e
d
ef
in
ed
b
y
eq
u
atio
n
s
(
1
)
,
(
2
)
,
an
d
(
3
)
as f
o
llo
ws:
(
i
,
j
)
=
ℎ
1
≤
≤
,
1
≤
≤
(
1
)
(
)
=
ℎ
1
≤
≤
,
1
≤
≤
(
2
)
=
(
3
)
wh
er
e
th
e
m
o
d
el
p
ar
am
eter
s
a
r
e
esti
m
ated
u
s
in
g
a
tr
ain
in
g
c
o
r
p
u
s
C
co
m
p
o
s
ed
o
f
N
wo
r
d
s
an
d
M
s
en
ten
ce
s
,
n
ij
is
th
e
o
cc
u
r
r
en
ce
n
u
m
b
er
in
C
o
f
th
e
s
tem
s
i
f
o
llo
wed
b
y
th
e
s
tem
s
j
,
n
i
is
th
e
o
cc
u
r
r
e
n
ce
n
u
m
b
er
in
C
o
f
th
e
s
tem
s
i
,
m
it
is
th
e
o
cc
u
r
r
en
ce
n
u
m
b
e
r
in
C
o
f
th
e
wo
r
d
w
t
ass
o
ciate
d
w
ith
th
e
s
te
m
s
i
,
an
d
n
io
is
th
e
o
cc
u
r
r
e
n
ce
n
u
m
b
er
in
C
o
f
s
e
n
ten
ce
s
s
tar
tin
g
with
th
e
s
tem
s
i
.
T
o
r
ef
in
e
o
u
r
m
o
d
el,
we
ap
p
l
y
th
e
“
ab
s
o
lu
te
d
is
co
u
n
tin
g
s
m
o
o
th
in
g
tech
n
iq
u
e
”
,
wh
ich
h
elp
s
ad
ju
s
t
th
e
elem
en
ts
o
f
th
e
m
atr
ices
th
at
m
ay
h
av
e
b
ee
n
esti
m
ated
as
ze
r
o
.
Fin
ally
,
we
u
tili
ze
th
e
“
Viter
b
i
alg
o
r
ith
m
”
to
f
in
d
th
e
b
est
s
eq
u
en
ce
o
f
h
id
d
en
s
tates
(
s
tem
s
)
th
at
co
r
r
esp
o
n
d
to
th
e
o
b
s
er
v
ed
s
tates
(
wo
r
d
s
)
in
th
e
in
p
u
t
s
en
ten
ce
.
T
h
is
alg
o
r
ith
m
ef
f
icien
tly
d
eter
m
in
es
th
e
m
o
s
t
l
ik
ely
s
eq
u
en
ce
o
f
s
tem
s
,
en
s
u
r
in
g
a
co
n
te
x
tu
ally
ap
p
r
o
p
r
iate
an
d
ac
cu
r
ate
o
u
tp
u
t.
Fig
u
r
e
2
.
T
h
e
d
is
am
b
ig
u
atio
n
p
h
ase
o
f
th
e
s
tem
m
er
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
2
,
Ap
r
il
20
25
:
2
3
5
6
-
2
3
6
3
2360
3.
E
XP
E
R
I
M
E
N
T
S AN
D
RE
S
UL
T
S
T
h
is
s
ec
tio
n
p
r
esen
ts
two
e
x
p
er
im
en
ts
.
T
h
e
f
i
r
s
t
ex
p
er
i
m
en
t
co
m
p
ar
es
AL
Stem
m
er
an
d
o
th
er
s
tate
-
of
-
th
e
-
ar
t
s
tem
m
er
s
to
ev
alu
ate
th
eir
ef
f
icien
cy
.
T
h
e
s
ec
o
n
d
ex
p
er
im
e
n
t
s
h
o
wca
s
es
th
at
u
tili
z
in
g
AL
Stem
m
er
is
th
e
o
p
tim
al
o
p
t
io
n
f
o
r
r
etr
iev
al
task
s
.
3
.
1
.
E
f
f
iciency
ex
peri
m
ent
T
o
v
alid
ate
th
e
ef
f
ec
tiv
e
n
ess
o
f
AL
Stem
m
er
,
we
co
n
d
u
ct
ed
a
s
er
ies
o
f
ex
p
er
im
en
ts
in
wh
ich
we
m
eticu
lo
u
s
ly
co
m
p
a
r
ed
its
p
er
f
o
r
m
a
n
ce
.
W
e
aim
to
d
em
o
n
s
tr
ate
its
ef
f
icien
cy
an
d
s
u
p
er
io
r
ity
o
v
er
e
x
is
tin
g
s
tem
m
er
s
.
T
o
en
s
u
r
e
a
co
m
p
r
eh
en
s
iv
e
an
aly
s
is
,
we
u
tili
ze
th
e
m
o
s
t
r
eliab
le
d
ata
s
et
s
a
m
o
n
g
th
e
av
ailab
le
o
n
es
.
−
T
h
e
n
o
r
m
alize
d
Ar
ab
ic
f
r
ag
m
en
ts
f
o
r
in
esti
m
ab
le
s
tem
m
in
g
(
NAFI
S
)
[
2
2
]
is
a
co
r
p
u
s
u
s
ed
to
ev
alu
ate
t
h
e
ef
f
ec
tiv
en
ess
o
f
Ar
ab
ic
s
tem
m
er
s
.
I
t
e
n
co
m
p
ass
es
a
co
m
p
r
eh
en
s
iv
e
c
o
llectio
n
o
f
Ar
a
b
i
c
clitics
co
v
er
in
g
all
p
o
s
s
ib
le
co
m
b
in
atio
n
s
.
E
ac
h
wo
r
d
in
th
e
co
r
p
u
s
is
m
an
u
ally
an
n
o
tated
with
m
u
ltip
le
p
o
ten
tial
s
tem
s
an
d
r
o
o
ts
,
with
th
e
in
itial a
n
n
o
tatio
n
in
d
icatin
g
th
e
co
r
r
ec
t so
lu
tio
n
with
in
th
e
s
en
ten
ce
'
s
co
n
tex
t.
−
T
h
e
Al
-
Mu
s
h
af
-
c
o
r
p
u
s
(
AM
C
)
[
2
3
]
i
is
a
co
m
p
ilatio
n
o
f
th
e
Qu
r
an
ic
te
x
t
en
r
ic
h
ed
with
m
o
r
p
h
o
lo
g
ical
tag
s
.
I
t c
o
n
tain
s
7
7
,
8
8
3
wo
r
d
s
m
an
u
ally
an
n
o
tated
with
th
e
s
tem
tag
.
W
e
n
o
te
th
e
av
ailab
ilit
y
o
f
an
o
th
er
co
r
p
u
s
ca
lled
“
T
h
e
g
o
ld
en
Ar
ab
ic
co
r
p
u
s
”
[
2
4
]
f
o
r
ass
es
s
in
g
Ar
ab
ic
s
tem
m
er
s
.
Ho
wev
er
,
it
s
m
an
u
al
v
er
if
icatio
n
d
em
o
n
s
tr
ates
its
lim
itatio
n
s
s
u
ch
as
“
ّ
ّ
،
هت
ب
اوب
ب
ّ
،
ج
ارخإب
ّ
،
يتفتس
ا
مهلافطأ
و
ّ
،
مهتي
ب
ب
ّ
،
سر
دف
”
(
He
was
ask
ed
f
o
r
a
f
atwa
,
h
e
b
r
o
u
g
h
t
o
u
t,
at
h
is
g
ate,
s
o
h
e
s
tu
d
ie
d
,
with
th
eir
h
o
u
s
e,
an
d
th
eir
c
h
ild
r
en
)
wer
e
s
tem
m
ed
as
“
لافط
ّ
،
تي
ب
ب
ّ
،
س
ر
دف
ّ
،
ب
اوب
ب
ّ
،
ج
ارخ
ّ
،
ف
ت
سا
”
(
A
s
tf
,
x
r
Aj,
b
b
wAb
,
th
en
h
e
s
tu
d
ie
d
,
in
th
e
h
o
u
s
e,
T
f
Al)
wh
ich
is
in
ac
cu
r
ate.
T
h
er
ef
o
r
e,
o
u
r
s
tem
m
er
'
s
p
er
f
o
r
m
an
ce
is
ev
al
u
ated
b
y
co
m
p
ar
in
g
it
to
th
e
m
o
s
t
av
aila
b
le
Ar
ab
ic
lig
h
t
s
tem
m
er
s
lik
e
A
R
L
Ste
m
,
Ass
em
,
C
o
n
d
L
ig
h
t,
FAR
ASA
,
L
ig
h
t1
0
,
Saad
,
an
d
T
a
s
h
ap
h
y
n
e.
C
am
elir
a
an
aly
ze
r
[
7
]
a
n
d
C
h
atGPT
ar
e
ad
d
ed
to
t
h
e
ev
alu
atio
n
.
C
am
elir
a
an
aly
ze
r
is
in
co
r
p
o
r
ated
in
to
th
e
e
v
alu
atio
n
b
ec
au
s
e
it
p
r
o
v
id
es
m
u
ltip
le
d
iacr
itized
s
o
lu
tio
n
s
,
with
t
h
e
m
o
s
t
p
r
o
b
ab
le
o
n
e
d
eter
m
in
ed
b
y
th
e
s
en
ten
ce
co
n
tex
t,
u
n
lik
e
lig
h
t
s
tem
m
er
s
th
at
o
f
f
er
a
s
in
g
le
s
o
lu
tio
n
with
o
u
t
d
iacr
itics
.
Fu
r
th
er
m
o
r
e,
in
alig
n
m
en
t
with
th
e
g
r
o
win
g
tr
e
n
d
o
f
u
tili
zin
g
L
L
Ms,
a
p
r
elim
in
ar
y
ass
ess
m
en
t
was
co
n
d
u
cte
d
to
ev
al
u
ate
v
ar
io
u
s
L
L
Ms
(
s
u
ch
as
L
L
aM
A
3
an
d
Mix
tr
al
8
x
7
B
)
f
o
r
s
tem
m
in
g
p
u
r
p
o
s
es.
T
h
e
f
in
d
in
g
s
r
ev
ea
led
th
a
t
C
h
atGPT
y
ield
ed
th
e
m
o
s
t f
av
o
r
ab
le
o
u
tco
m
es.
T
o
co
n
d
u
ct
th
e
ev
alu
atio
n
,
e
ac
h
wo
r
d
in
th
e
two
d
atasets
u
n
d
e
r
wen
t
s
tem
m
in
g
u
s
in
g
all
o
f
th
ese
s
tem
m
er
s
an
d
is
th
e
n
class
if
ied
as
tr
u
e
p
o
s
itiv
e,
f
alse
p
o
s
itiv
e,
tr
u
e
n
eg
ativ
e
,
o
r
f
alse n
eg
at
iv
e.
T
h
e
ev
alu
atio
n
m
etr
ics
em
p
lo
y
ed
in
th
e
ex
p
er
im
en
ts
ar
e
Acc
u
r
ac
y
an
d
F1
s
co
r
e.
T
h
e
ev
alu
atio
n
r
esu
lts
u
s
in
g
th
e
two
co
r
p
o
r
a
ar
e
illu
s
tr
ated
in
Fig
u
r
es
3
an
d
4
.
T
h
e
AL
Stem
m
er
d
em
o
n
s
tr
ates
s
u
p
er
io
r
p
e
r
f
o
r
m
an
ce
,
ac
h
iev
in
g
F1
s
co
r
es
o
f
0
.
8
6
6
0
,
an
d
0
.
9
2
8
2
,
al
o
n
g
with
Acc
u
r
ac
y
v
alu
es
o
f
0
.
8
2
5
6
,
an
d
0
.
8
6
5
9
wh
e
n
u
tili
zin
g
NAFI
S,
an
d
AM
C
,
r
esp
ec
tiv
ely
.
Fig
u
r
e
3
.
T
h
e
F1
s
co
r
e
a
n
d
ac
cu
r
ac
y
o
f
th
e
s
tem
m
er
s
ev
alu
a
ted
u
s
in
g
th
e
NAFI
S c
o
r
p
u
s
3
.
2
.
I
nfo
r
m
a
t
io
n r
e
t
riev
a
l e
x
perim
ent
P
r
e
v
i
o
u
s
s
t
u
d
i
e
s
h
a
v
e
s
u
g
g
e
s
t
ed
t
h
a
t
l
e
m
m
a
t
i
z
at
i
o
n
[
2
5
]
,
[
2
6
]
a
n
d
r
o
o
t
-
b
a
s
e
d
s
t
e
m
m
i
n
g
[
2
7
]
–
[
2
9
]
a
r
e
b
e
t
t
e
r
s
u
it
e
d
f
o
r
r
e
t
r
i
e
v
a
l
t
a
s
k
s
d
u
e
t
o
t
h
e
i
r
a
b
i
l
it
y
t
o
s
i
g
n
i
f
i
c
an
t
l
y
r
e
d
u
c
e
v
o
c
a
b
u
l
a
r
y
s
i
z
e
i
n
c
o
m
p
a
r
i
s
o
n
t
o
l
i
g
h
t
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
A
n
in
n
o
va
tive
A
r
a
b
ic
lig
h
t stemme
r
d
ev
elo
p
ed
u
s
in
g
a
h
yb
r
id
a
p
p
r
o
a
ch
(
Dri
s
s
N
a
mly
)
2361
s
t
e
m
m
i
n
g
.
Ne
v
e
r
t
h
e
l
es
s
,
t
h
e
s
e
m
e
t
h
o
d
s
m
a
y
g
r
o
u
p
w
o
r
d
s
w
i
th
d
i
s
t
i
n
ct
s
e
m
a
n
t
i
c
m
e
a
n
i
n
g
s
to
g
e
t
h
e
r
,
r
e
s
u
l
t
i
n
g
in
d
e
c
r
e
a
s
e
d
p
r
e
c
is
i
o
n
.
C
o
n
s
e
q
u
e
n
t
l
y
,
o
u
r
e
x
p
e
r
i
m
e
n
t
a
i
m
s
t
o
d
e
m
o
n
s
t
r
a
t
e
t
h
a
t
s
t
e
m
m
i
n
g
,
e
s
p
e
c
i
al
l
y
o
u
r
l
i
g
h
t
s
t
e
m
m
e
r
,
i
s
m
o
r
e
e
f
f
e
ct
i
v
e
f
o
r
a
n
i
n
f
o
r
m
a
t
i
o
n
r
et
r
i
e
v
a
l
t
as
k
.
T
o
a
c
h
i
e
v
e
t
h
is
,
we
c
o
m
p
i
le
d
a
n
d
r
e
t
r
i
e
v
e
d
f
i
v
e
v
a
r
i
a
t
i
o
n
s
o
f
a
s
e
t
o
f
A
r
a
b
i
c
d
o
c
u
m
e
n
t
s
t
o
a
s
s
e
s
s
t
h
e
i
r
i
m
p
a
ct
o
n
p
r
e
c
i
s
i
o
n
a
n
d
r
e
c
a
l
l
m
e
a
s
u
r
e
s
.
E
a
c
h
v
a
r
i
a
t
i
o
n
e
m
p
l
o
y
s
d
i
f
f
e
r
e
n
t
i
n
d
e
x
i
n
g
t
e
r
m
s
.
T
h
e
i
n
it
i
a
l
v
a
r
i
a
ti
o
n
o
f
t
h
e
c
o
r
p
u
s
u
s
es
s
u
r
f
a
ce
f
o
r
m
s
(
w
o
r
d
s
)
,
f
o
l
l
o
w
e
d
b
y
t
w
o
s
te
m
v
a
r
i
a
ti
o
n
s
u
s
i
n
g
A
L
St
e
m
m
e
r
a
n
d
F
AR
AS
A
,
t
h
e
n
l
em
m
a
s
,
a
n
d
r
o
o
t
s
v
a
r
i
at
i
o
n
s
.
Fig
u
r
e
4
.
T
h
e
F1
s
co
r
e
a
n
d
ac
cu
r
ac
y
o
f
s
tem
m
er
s
ev
alu
ated
u
s
in
g
th
e
Qu
r
a
n
ic
C
o
r
p
u
s
T
h
u
s
,
th
e
“
Ar
a
b
ic
n
ews
ar
ticles
f
r
o
m
Aljaze
er
a.
n
et
”
d
ataset
o
b
tain
ed
f
r
o
m
Kag
g
le
i
s
u
tili
ze
d
,
co
n
s
is
tin
g
o
f
5
,
8
7
0
n
ews
ar
ticles
wr
itten
in
th
e
Ar
ab
ic
la
n
g
u
ag
e
s
o
u
r
ce
d
f
r
o
m
Aljaze
er
a.
n
et
web
s
ite.
T
o
g
en
er
ate
f
iv
e
d
is
tin
ct
v
ar
iati
o
n
s
o
f
th
e
d
ataset,
in
ad
d
itio
n
to
th
e
in
itial
co
r
p
u
s
c
o
m
p
o
s
ed
o
f
wo
r
d
s
,
th
e
d
o
cu
m
e
n
ts
ar
e
p
r
o
ce
s
s
ed
u
s
in
g
AL
Stem
m
er
,
FAR
ASA
s
te
m
m
er
,
Saf
ar
lem
m
atize
r
[
2
0
]
,
an
d
Kh
o
ja
s
tem
m
er
[
3
0
]
to
o
b
tain
v
ar
iatio
n
s
with
s
tem
s
,
lem
m
as,
an
d
r
o
o
ts
r
esp
ec
tiv
ely
.
T
h
e
f
iv
e
co
r
p
u
s
v
ar
i
atio
n
s
ar
e
i
n
d
ex
e
d
in
th
e
E
last
icsear
ch
en
g
in
e,
u
tili
zin
g
th
e
in
v
er
ted
in
d
ex
i
n
g
m
eth
o
d
.
T
h
is
ap
p
r
o
ac
h
ass
o
ciate
s
ea
ch
to
k
en
in
th
e
co
r
p
u
s
(
a
wo
r
d
,
s
tem
,
le
m
m
a,
o
r
r
o
o
t)
with
th
e
r
elev
an
t
d
o
cu
m
e
n
ts
co
n
tain
in
g
it.
Su
b
s
eq
u
en
tly
,
th
e
ef
f
ec
tiv
en
ess
o
f
th
e
f
iv
e
r
etr
iev
al
s
y
s
tem
s
is
m
ea
s
u
r
ed
b
y
an
aly
zin
g
th
eir
p
r
ec
is
io
n
an
d
r
ec
all
m
etr
ics.
Fig
u
r
e
5
d
em
o
n
s
tr
ates
a
n
o
ta
b
le
en
h
an
ce
m
en
t
in
r
o
o
t
-
b
ase
d
r
etr
iev
al
co
m
p
ar
e
d
to
th
e
wo
r
d
'
s
s
u
r
f
ac
e
f
o
r
m
.
C
o
n
v
er
s
ely
,
s
tem
-
b
ased
r
etr
iev
al
u
s
in
g
AL
Stem
m
er
s
u
r
p
ass
es
lem
m
a
-
b
ased
r
etr
iev
al
an
d
ex
h
i
b
its
a
s
ig
n
if
ican
t a
d
v
an
ta
g
e
o
v
e
r
r
o
o
t
-
b
ased
r
etr
iev
al.
Fig
u
r
e
5
.
Pre
cisi
o
n
a
n
d
r
ec
all
f
lu
ctu
atio
n
Evaluation Warning : The document was created with Spire.PDF for Python.
I
SS
N
:
2
0
8
8
-
8
7
0
8
I
n
t J E
lec
&
C
o
m
p
E
n
g
,
Vo
l.
15
,
No
.
2
,
Ap
r
il
20
25
:
2
3
5
6
-
2
3
6
3
2362
Ad
d
itio
n
ally
,
it
is
w
o
r
th
n
o
ti
n
g
th
at
in
th
e
r
e
g
io
n
with
h
ig
h
er
p
r
ec
is
io
n
,
th
e
lem
m
a
-
b
ased
r
etr
iev
al
s
lig
h
tly
o
u
tp
er
f
o
r
m
s
th
e
s
tem
-
b
ased
o
n
e
with
FAR
ASA.
T
h
is
in
co
n
s
is
ten
cy
ca
n
b
e
attr
ib
u
t
ed
to
th
e
d
iacr
itics
'
lack
in
th
e
o
u
t
p
u
t
p
r
o
d
u
ce
d
b
y
th
e
FAR
ASA
s
tem
m
er
.
T
h
is
r
eg
io
n
with
h
ig
h
er
p
r
ec
is
io
n
an
d
lo
wer
r
ec
all
i
n
o
u
r
f
ig
u
r
e
h
o
ld
s
g
r
ea
ter
s
ig
n
if
ican
ce
,
as
u
s
er
s
in
a
W
eb
-
lik
e
m
ed
iu
m
ar
e
u
n
lik
ely
to
r
ea
d
n
u
m
er
o
u
s
r
etr
iev
e
d
d
o
cu
m
e
n
ts
th
o
r
o
u
g
h
ly
.
Als
o
,
t
h
e
p
er
f
o
r
m
an
ce
d
eg
r
a
d
atio
n
o
b
s
er
v
ed
wh
en
u
s
in
g
th
e
Ar
a
b
ic
s
u
r
f
ac
e
f
o
r
m
ca
n
b
e
attr
ib
u
ted
to
th
e
n
u
m
er
o
u
s
in
f
lecte
d
v
a
r
ian
ts
o
f
a
wo
r
d
i
n
th
e
Ar
a
b
ic
lan
g
u
ag
e.
T
h
is
ab
u
n
d
an
ce
o
f
v
ar
ia
n
ts
r
ed
u
ce
s
th
e
lik
eli
h
o
o
d
o
f
f
in
d
in
g
a
m
atch
b
etwe
en
th
e
q
u
er
y
an
d
th
e
d
o
c
u
m
en
ts
.
Fo
r
ex
am
p
le,
th
e
ter
m
s
“
بت
ك
و
”
(
An
d
h
e
wr
ites
)
,
“
تب
ت
ك
و
”
(
An
d
s
h
e
wr
ites
)
,
“
بت
ك
ف
”
(
An
d
h
e
wr
ites
)
,
“
هب
ت
ك
و
”
(
An
d
h
e
wr
ites
it),
“
اه
ب
ت
ك
و
”
(
An
d
h
e
wr
ites
it)
r
e
p
r
esen
t v
a
r
iatio
n
s
o
f
th
e
wo
r
d
“
بتك
”
(
T
o
wr
ite)
,
y
et
class
if
ied
as d
is
tin
ct
wo
r
d
s
.
4.
CO
NCLU
SI
O
N
T
h
e
d
is
cu
s
s
io
n
o
n
Ar
ab
ic
s
te
m
m
in
g
en
co
m
p
ass
es
an
ex
p
lo
r
atio
n
o
f
Ar
ab
ic
m
o
r
p
h
o
lo
g
y
,
v
ar
io
u
s
s
tem
m
in
g
ap
p
r
o
ac
h
es,
an
d
th
e
in
tr
o
d
u
cti
o
n
o
f
a
n
o
v
el
lig
h
t
s
tem
m
in
g
alg
o
r
ith
m
.
T
h
e
b
asis
f
o
r
o
u
r
s
tem
m
in
g
tech
n
iq
u
e
is
d
ef
in
e
d
b
y
th
e
t
em
p
latic
an
d
co
n
ca
te
n
ativ
e
f
ea
tu
r
es
th
at
ch
a
r
ac
ter
ize
th
e
s
tr
u
ctu
r
ed
n
atu
r
e
o
f
Ar
ab
ic
m
o
r
p
h
o
lo
g
y
.
T
h
e
p
r
o
p
o
s
ed
lig
h
t
s
tem
m
in
g
alg
o
r
ith
m
p
r
esen
ts
a
th
r
ee
-
s
tag
e
p
r
o
ce
s
s
:
clitic
r
em
o
v
al,
s
tem
v
alid
atio
n
,
an
d
s
tatis
ti
ca
l
d
is
am
b
ig
u
atio
n
.
E
x
p
er
i
m
en
ts
co
n
d
u
cte
d
to
ev
al
u
at
e
Ar
ab
ic
s
tem
m
er
s
d
em
o
n
s
tr
ate
th
at
AL
Stem
m
er
ef
f
ec
tiv
ely
id
en
tifie
s
s
tem
s
b
ased
o
n
co
n
tex
t,
a
d
d
r
ess
in
g
li
m
itatio
n
s
o
b
s
er
v
ed
in
ex
is
tin
g
s
tem
m
er
s
.
T
h
e
s
tem
m
er
co
n
s
is
ten
tly
ac
h
iev
es
h
ig
h
er
ac
cu
r
ac
y
an
d
F1
s
co
r
es
th
r
o
u
g
h
r
ig
o
r
o
u
s
an
aly
s
is
ac
r
o
s
s
d
if
f
er
en
t d
atas
ets,
af
f
ir
m
in
g
its
ef
f
icien
c
y
an
d
ef
f
ec
tiv
en
ess
in
Ar
ab
ic
s
tem
m
in
g
task
s
.
I
n
th
e
f
u
tu
r
e
,
we
aim
to
en
h
an
ce
o
u
r
s
tem
m
er
in
two
p
r
i
m
ar
y
way
s
:
ex
p
an
d
in
g
th
e
s
tem
/lem
m
a
lex
ico
n
to
in
cl
u
d
e
m
is
s
in
g
lem
m
as
lik
e
n
am
ed
en
titi
es,
an
d
im
p
r
o
v
in
g
co
n
tex
t
d
et
ec
tio
n
to
r
ed
u
ce
d
ef
icien
cies
in
t
h
e
s
tem
m
er
.
T
h
ese
im
p
r
o
v
em
en
ts
will
n
o
t
o
n
ly
e
n
h
an
ce
th
e
ac
cu
r
ac
y
o
f
o
u
r
s
y
s
tem
b
u
t
also
co
n
tr
ib
u
te
t
o
a
d
ee
p
er
u
n
d
er
s
tan
d
in
g
o
f
la
n
g
u
a
g
e
n
u
an
ce
s
,
u
ltima
tely
lead
in
g
t
o
b
etter
o
u
tco
m
es
in
v
a
r
io
u
s
n
atu
r
al
lan
g
u
ag
e
p
r
o
ce
s
s
in
g
(
NL
P
)
ap
p
licatio
n
s
.
RE
F
E
R
E
NC
E
S
[
1
]
M
.
Y
.
D
a
h
a
b
,
A
.
I.
A
l
I
b
r
a
h
i
m
,
a
n
d
R
.
A
l
-
M
u
t
a
w
a
,
“
A
c
o
m
p
a
r
a
t
i
v
e
s
t
u
d
y
o
n
A
r
a
b
i
c
st
e
mm
e
r
s,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
C
o
m
p
u
t
e
r
A
p
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
1
2
5
,
n
o
.
8
,
p
p
.
3
8
–
4
7
,
2
0
1
5
,
d
o
i
:
1
0
.
5
1
2
0
/
i
j
c
a
2
0
1
5
9
0
6
1
2
9
.
[
2
]
M
.
M
u
s
t
a
f
a
,
A
.
S
.
El
d
e
e
n
,
S
.
B
a
n
i
-
A
h
ma
d
,
a
n
d
A
.
O
.
E
l
f
a
k
i
,
“
A
c
o
m
p
a
r
a
t
i
v
e
su
r
v
e
y
o
n
A
r
a
b
i
c
st
e
mm
i
n
g
:
a
p
p
r
o
a
c
h
e
s
a
n
d
c
h
a
l
l
e
n
g
e
s,
”
I
n
t
e
l
l
i
g
e
n
t
I
n
f
o
rm
a
t
i
o
n
Ma
n
a
g
e
m
e
n
t
,
v
o
l
.
0
9
,
n
o
.
0
2
,
p
p
.
3
9
–
6
7
,
2
0
1
7
,
d
o
i
:
1
0
.
4
2
3
6
/
i
i
m.
2
0
1
7
.
9
2
0
0
3
.
[
3
]
S
.
M
e
m
o
n
,
G
.
A
.
M
a
l
l
a
h
,
K
.
N
.
M
e
mo
n
,
A
.
S
h
a
i
k
h
,
S
.
K
.
A
a
s
o
o
r
i
,
a
n
d
F
.
U
.
H
.
D
e
h
r
a
j
,
“
C
o
m
p
a
r
a
t
i
v
e
s
t
u
d
y
o
f
t
r
u
n
c
a
t
i
n
g
a
n
d
st
a
t
i
st
i
c
a
l
st
e
mm
i
n
g
a
l
g
o
r
i
t
h
ms,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
A
d
v
a
n
c
e
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
Ap
p
l
i
c
a
t
i
o
n
s
,
n
o
.
2
,
p
p
.
5
6
3
–
5
6
8
,
2
0
2
0
,
d
o
i
:
1
0
.
1
4
5
6
9
/
i
j
a
c
s
a
.
2
0
2
0
.
0
1
1
0
2
7
2
.
[
4
]
A
.
W
u
l
a
n
d
a
r
i
,
K
.
R
a
h
ma
t
S
W
,
a
n
d
A
.
R
o
ma
d
h
o
n
y
,
“
P
a
t
t
e
r
n
-
b
a
se
d
s
t
e
mm
e
r
a
n
a
l
y
s
i
s
a
n
d
i
m
p
l
e
me
n
t
a
t
i
o
n
o
n
A
r
a
b
i
c
Te
x
t
,
”
S
e
m
i
n
a
r
N
a
s
i
o
n
a
l
T
e
k
n
o
l
o
g
i
I
n
f
o
rm
a
s
i
K
o
m
u
n
i
k
a
si
d
a
n
I
n
d
u
st
r
i
,
p
p
.
3
1
–
4
1
,
2
0
1
1
.
[
5
]
M
.
B
o
u
d
c
h
i
c
h
e
,
A
.
M
a
z
r
o
u
i
,
M
.
O
.
A
.
O
.
B
e
b
a
h
,
A
.
La
k
h
o
u
a
j
a
,
a
n
d
A
.
B
o
u
d
l
a
l
,
“
A
l
K
h
a
l
i
l
M
o
r
p
h
o
S
y
s
2
:
A
r
o
b
u
st
A
r
a
b
i
c
mo
r
p
h
o
-
sy
n
t
a
c
t
i
c
a
n
a
l
y
z
e
r
,
”
J
o
u
r
n
a
l
o
f
K
i
n
g
S
a
u
d
U
n
i
v
e
rsi
t
y
-
C
o
m
p
u
t
e
r
a
n
d
I
n
f
o
rm
a
t
i
o
n
S
c
i
e
n
c
e
s
,
v
o
l
.
2
9
,
n
o
.
2
,
p
p
.
1
4
1
–
1
4
6
,
2
0
1
7
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
k
su
c
i
.
2
0
1
6
.
0
5
.
0
0
2
.
[
6
]
D
.
Ta
j
i
,
S
.
K
h
a
l
i
f
a
,
O
.
O
b
e
i
d
,
F
.
Er
y
a
n
i
,
a
n
d
N
.
H
a
b
a
sh
,
“
A
n
A
r
a
b
i
c
m
o
r
p
h
o
l
o
g
i
c
a
l
a
n
a
l
y
z
e
r
a
n
d
g
e
n
e
r
a
t
o
r
w
i
t
h
c
o
p
i
o
u
s
f
e
a
t
u
r
e
s,
”
i
n
Pr
o
c
e
e
d
i
n
g
s
o
f
t
h
e
f
i
f
t
e
e
n
t
h
w
o
rks
h
o
p
o
n
c
o
m
p
u
t
a
t
i
o
n
a
l
rese
a
r
c
h
i
n
p
h
o
n
e
t
i
c
s,
p
h
o
n
o
l
o
g
y
,
a
n
d
m
o
rp
h
o
l
o
g
y
,
2
0
1
9
,
p
p
.
1
4
0
–
1
5
0
,
d
o
i
:
1
0
.
1
8
6
5
3
/
v
1
/
w
1
8
-
5
8
1
6
.
[
7
]
O
.
O
b
e
i
d
,
G
.
I
n
o
u
e
,
a
n
d
N
.
H
a
b
a
s
h
,
“
C
a
m
e
l
i
r
a
:
a
n
A
r
a
b
i
c
m
u
l
t
i
-
d
i
a
l
e
c
t
m
o
r
p
h
o
l
o
g
i
c
a
l
d
i
s
a
mb
i
g
u
a
t
o
r
,
”
i
n
E
M
N
L
P
2
0
2
2
-
2
0
2
2
C
o
n
f
e
re
n
c
e
o
n
Em
p
i
ri
c
a
l
Me
t
h
o
d
s
i
n
N
a
t
u
r
a
l
L
a
n
g
u
a
g
e
P
ro
c
e
ss
i
n
g
,
Pro
c
e
e
d
i
n
g
s
o
f
t
h
e
D
e
m
o
n
s
t
ra
t
i
o
n
s
S
e
ss
i
o
n
,
2
0
2
2
,
p
p
.
3
1
9
–
3
2
6
,
d
o
i
:
1
0
.
1
8
6
5
3
/
v
1
/
2
0
2
2
.
e
mn
l
p
-
d
e
m
o
s.
3
2
.
[
8
]
L.
S
.
L
a
r
k
e
y
,
L.
B
a
l
l
e
st
e
r
o
s
,
a
n
d
M
.
E.
C
o
n
n
e
l
l
,
“
I
mp
r
o
v
i
n
g
st
e
mm
i
n
g
f
o
r
A
r
a
b
i
c
i
n
f
o
r
m
a
t
i
o
n
r
e
t
r
i
e
v
a
l
:
l
i
g
h
t
s
t
e
mm
i
n
g
a
n
d
c
o
-
o
c
c
u
r
r
e
n
c
e
a
n
a
l
y
si
s,
”
S
I
G
I
R
F
o
r
u
m
(
AC
M
S
p
e
c
i
a
l
I
n
t
e
re
st
G
r
o
u
p
o
n
I
n
f
o
r
m
a
t
i
o
n
R
e
t
r
i
e
v
a
l
)
,
p
p
.
2
7
5
–
2
8
2
,
2
0
0
2
.
[
9
]
L.
S
.
L
a
r
k
e
y
,
L.
B
a
l
l
e
st
e
r
o
s,
a
n
d
M
.
E.
C
o
n
n
e
l
l
,
“
Li
g
h
t
s
t
e
mm
i
n
g
f
o
r
A
r
a
b
i
c
i
n
f
o
r
m
a
t
i
o
n
r
e
t
r
i
e
v
a
l
,
”
Ar
a
b
i
c
C
o
m
p
u
t
a
t
i
o
n
a
l
Mo
r
p
h
o
l
o
g
y
,
p
p
.
2
2
1
–
2
4
3
,
2
0
0
7
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
1
-
4
0
2
0
-
6
0
4
6
-
5
_
1
2
.
[
1
0
]
M
.
S
a
a
d
a
n
d
W
.
A
sh
o
u
r
,
“
A
r
a
b
i
c
mo
r
p
h
o
l
o
g
i
c
a
l
t
o
o
l
s
f
o
r
t
e
x
t
m
i
n
i
n
g
,
”
i
n
6
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
El
e
c
t
ri
c
a
l
a
n
d
C
o
m
p
u
t
e
r
S
y
st
e
m
s (EE
C
S
’
1
0
)
,
N
o
v
2
5
-
2
6
,
2
0
1
0
,
L
e
f
k
e
,
C
y
p
ru
s
.
,
2
0
1
0
,
v
o
l
.
1
8
,
p
.
1
9
.
[
1
1
]
K
.
A
b
a
i
n
i
a
,
S
.
O
u
a
mo
u
r
,
a
n
d
H
.
S
a
y
o
u
d
,
“
A
n
o
v
e
l
r
o
b
u
st
A
r
a
b
i
c
l
i
g
h
t
st
e
mm
e
r
,
”
J
o
u
r
n
a
l
o
f
Ex
p
e
ri
m
e
n
t
a
l
a
n
d
T
h
e
o
re
t
i
c
a
l
Art
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
,
v
o
l
.
2
9
,
n
o
.
3
,
p
p
.
5
5
7
–
5
7
3
,
2
0
1
7
,
d
o
i
:
1
0
.
1
0
8
0
/
0
9
5
2
8
1
3
X
.
2
0
1
6
.
1
2
1
2
1
0
0
.
[
1
2
]
A
.
A
b
d
e
l
a
l
i
,
K
.
D
a
r
w
i
sh
,
N
.
D
u
r
r
a
n
i
,
a
n
d
H
.
M
u
b
a
r
a
k
,
“
F
a
r
a
sa:
A
f
a
st
a
n
d
f
u
r
i
o
u
s
se
g
me
n
t
e
r
f
o
r
a
r
a
b
i
c
,
”
i
n
N
A
AC
L
-
H
L
T
2
0
1
6
-
2
0
1
6
C
o
n
f
e
r
e
n
c
e
o
f
t
h
e
N
o
r
t
h
A
m
e
ri
c
a
n
C
h
a
p
t
e
r
o
f
t
h
e
Ass
o
c
i
a
t
i
o
n
f
o
r
C
o
m
p
u
t
a
t
i
o
n
a
l
L
i
n
g
u
i
s
t
i
c
s:
H
u
m
a
n
L
a
n
g
u
a
g
e
T
e
c
h
n
o
l
o
g
i
e
s
,
Pr
o
c
e
e
d
i
n
g
s
o
f
t
h
e
D
e
m
o
n
s
t
ra
t
i
o
n
s
S
e
ss
i
o
n
,
2
0
1
6
,
p
p
.
1
1
–
1
6
,
d
o
i
:
1
0
.
1
8
6
5
3
/
v
1
/
n
1
6
-
3
0
0
3
.
[
1
3
]
Y
.
A
l
-
La
h
h
a
m,
K
.
A
l
M
a
t
a
r
n
e
h
,
a
n
d
M
.
H
a
ss
a
n
,
“
C
o
n
d
i
t
i
o
n
a
l
A
r
a
b
i
c
l
i
g
h
t
st
e
mm
e
r
:
C
o
n
d
Li
g
h
t
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
Ara
b
J
o
u
rn
a
l
o
f
I
n
f
o
rm
a
t
i
o
n
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
1
5
,
n
o
.
3
A
S
p
e
c
i
a
l
I
ssu
e
,
p
p
.
5
5
9
–
5
6
4
,
2
0
1
8
.
[
1
4
]
R
.
M
.
A
l
-
K
h
a
t
i
b
,
T.
Z
e
r
r
o
u
k
i
,
M
.
M
.
A
b
u
S
h
q
u
i
e
r
,
a
n
d
A
.
B
a
l
l
a
,
“
Ta
s
h
a
p
h
y
n
e
0
.
4
:
a
n
e
w
a
r
a
b
i
c
l
i
g
h
t
s
t
e
m
mer
b
a
se
d
o
n
r
h
y
z
o
me
mo
d
e
l
i
n
g
a
p
p
r
o
a
c
h
,
”
I
n
f
o
rm
a
t
i
o
n
R
e
t
ri
e
v
a
l
J
o
u
rn
a
l
,
v
o
l
.
2
6
,
n
o
.
1
–
2
,
p
.
1
4
,
D
e
c
.
2
0
2
3
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
0
7
9
1
-
023
-
0
9
4
2
9
-
y.
[
1
5
]
A
.
C
h
e
l
l
i
,
“
A
ssem’
s Ar
a
b
i
c
l
i
g
h
t
s
t
e
m
mer (
B
E
TA
)
,
”
a
ra
b
i
c
s
t
e
m
m
e
r.
c
o
m
,
h
t
t
p
s
:
/
/
a
r
a
b
i
c
st
e
mm
e
r
.
c
o
m (a
c
c
e
sse
d
M
a
y
2
3
,
2
0
2
4
)
.
[
1
6
]
K
.
D
a
r
w
i
sh
,
“
B
u
i
l
d
i
n
g
a
sh
a
l
l
o
w
A
r
a
b
i
c
mo
r
p
h
o
l
o
g
i
c
a
l
a
n
a
l
y
z
e
r
i
n
o
n
e
d
a
y
,
”
Pro
c
e
e
d
i
n
g
s
o
f
t
h
e
An
n
u
a
l
Me
e
t
i
n
g
o
f
t
h
e
Asso
c
i
a
t
i
o
n
f
o
r
C
o
m
p
u
t
a
t
i
o
n
a
l
L
i
n
g
u
i
st
i
c
s
,
2
0
0
2
,
d
o
i
:
1
0
.
3
1
1
5
/
1
1
1
8
6
3
7
.
1
1
1
8
6
4
3
.
[
1
7
]
T.
B
u
c
k
w
a
l
t
e
r
,
“
B
u
c
k
w
a
l
t
e
r
A
r
a
b
i
c
m
o
r
p
h
o
l
o
g
i
c
a
l
a
n
a
l
y
z
e
r
v
e
r
si
o
n
1
.
0
,
”
L
i
n
g
u
i
s
t
i
c
D
a
t
a
C
o
n
s
o
rt
i
u
m
,
U
n
i
v
e
r
si
t
y
o
f
Pe
n
n
sy
l
v
a
n
i
a
,
L
D
C
C
a
t
a
l
o
g
N
o
.
:
L
D
C
2
0
0
2
L
4
9
.
2
0
0
2
.
[
1
8
]
D
.
G
r
a
f
f
,
M
.
M
a
a
m
o
u
r
i
,
B
.
B
o
u
z
i
r
i
,
S
.
K
r
o
u
n
a
,
S
.
K
u
l
i
c
k
,
a
n
d
T
.
B
u
c
k
w
a
l
t
e
r
,
“
S
t
a
n
d
a
r
d
A
r
a
b
i
c
mo
r
p
h
o
l
o
g
i
c
a
l
a
n
a
l
y
z
e
r
(
S
A
M
A
)
Evaluation Warning : The document was created with Spire.PDF for Python.
I
n
t J E
lec
&
C
o
m
p
E
n
g
I
SS
N:
2088
-
8
7
0
8
A
n
in
n
o
va
tive
A
r
a
b
ic
lig
h
t stemme
r
d
ev
elo
p
ed
u
s
in
g
a
h
yb
r
id
a
p
p
r
o
a
ch
(
Dri
s
s
N
a
mly
)
2363
v
e
r
si
o
n
3
.
1
,
”
L
i
n
g
u
i
st
i
c
D
a
t
a
C
o
n
s
o
rt
i
u
m
L
D
C
2
0
0
9
E7
3
,
p
p
.
5
3
–
5
6
,
2
0
0
9
.
[
1
9
]
A
.
B
o
u
d
l
a
l
,
A
.
La
k
h
o
u
a
j
a
,
A
.
M
a
z
r
o
u
i
,
A
.
M
e
z
i
a
n
e
,
M
.
B
e
b
a
h
,
a
n
d
M
.
S
h
o
u
l
,
“
A
l
k
h
a
l
i
l
m
o
r
p
h
o
s
y
s1
:
A
mo
r
p
h
o
sy
n
t
a
c
t
i
c
a
n
a
l
y
si
s
sy
s
t
e
m
f
o
r
A
r
a
b
i
c
t
e
x
t
s
,
”
I
n
t
e
rn
a
t
i
o
n
a
l
Ar
a
b
c
o
n
f
e
re
n
c
e
o
n
i
n
f
o
rm
a
t
i
o
n
t
e
c
h
n
o
l
o
g
y
,
n
o
.
Ja
n
u
a
r
y
2
0
1
0
,
2
0
1
7
.
[
2
0
]
D
.
N
a
m
l
y
,
K
.
B
o
u
z
o
u
b
a
a
,
A
.
El
Ji
h
a
d
,
a
n
d
S
.
L.
A
o
u
r
a
g
h
,
“
I
mp
r
o
v
i
n
g
A
r
a
b
i
c
l
e
mm
a
t
i
z
a
t
i
o
n
t
h
r
o
u
g
h
a
l
e
m
ma
s
d
a
t
a
b
a
se
a
n
d
a
mac
h
i
n
e
-
l
e
a
r
n
i
n
g
t
e
c
h
n
i
q
u
e
,
”
S
t
u
d
i
e
s
i
n
C
o
m
p
u
t
a
t
i
o
n
a
l
I
n
t
e
l
l
i
g
e
n
c
e
,
v
o
l
.
8
7
4
,
p
p
.
8
1
–
1
0
0
,
2
0
2
0
,
d
o
i
:
1
0
.
1
0
0
7
/
9
7
8
-
3
-
030
-
3
4
6
1
4
-
0
_
5
.
[
2
1
]
L.
Li
u
,
Y
.
-
C
.
Li
n
,
a
n
d
J.
R
e
i
d
,
“
I
mp
r
o
v
i
n
g
t
h
e
p
e
r
f
o
r
ma
n
c
e
o
f
t
h
e
LST
M
a
n
d
H
M
M
m
o
d
e
l
v
i
a
h
y
b
r
i
d
i
z
a
t
i
o
n
,
”
a
rX
i
v
p
re
p
r
i
n
t
a
rXi
v
:
1
9
0
7
.
0
4
6
7
0
,
2
0
1
9
.
[
2
2
]
D
.
N
a
m
l
y
,
R
.
T
a
j
m
o
u
t
,
K
.
B
o
u
z
o
u
b
a
a
,
a
n
d
L
.
A
b
o
u
e
n
o
u
r
,
“
N
A
F
I
S
:
A
g
o
l
d
s
t
a
n
d
a
r
d
c
o
r
p
u
s
f
o
r
A
r
a
b
i
c
st
e
mm
e
r
s
e
v
a
l
u
a
t
i
o
n
,
”
i
n
Pro
c
e
e
d
i
n
g
s
o
f
t
h
e
2
8
t
h
I
n
t
e
rn
a
t
i
o
n
a
l
B
u
si
n
e
ss
I
n
f
o
rm
a
t
i
o
n
M
a
n
a
g
e
m
e
n
t
Ass
o
c
i
a
t
i
o
n
C
o
n
f
e
r
e
n
c
e
-
V
i
si
o
n
2
0
2
0
:
I
n
n
o
v
a
t
i
o
n
Ma
n
a
g
e
m
e
n
t
,
D
e
v
e
l
o
p
m
e
n
t
S
u
st
a
i
n
a
b
i
l
i
t
y
,
a
n
d
C
o
m
p
e
t
i
t
i
v
e
Ec
o
n
o
m
i
c
G
r
o
w
t
h
,
2
0
1
6
,
p
p
.
1
8
6
8
–
1
8
7
7
.
[
2
3
]
I
.
Ze
r
o
u
a
l
a
n
d
A
.
La
k
h
o
u
a
j
a
,
“
A
n
e
w
Q
u
r
a
n
i
c
C
o
r
p
u
s
r
i
c
h
i
n
m
o
r
p
h
o
sy
n
t
a
c
t
i
c
a
l
i
n
f
o
r
m
a
t
i
o
n
,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
S
p
e
e
c
h
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
1
9
,
n
o
.
2
,
p
p
.
3
3
9
–
3
4
6
,
2
0
1
6
,
d
o
i
:
1
0
.
1
0
0
7
/
s1
0
7
7
2
-
0
1
6
-
9
3
3
5
-
7.
[
2
4
]
l
i
n
u
x
sc
o
u
t
,
“
Th
e
g
o
l
d
e
n
A
r
a
b
i
c
c
o
r
p
u
s
,
”
G
i
t
H
u
b
,
A
c
c
e
ss
e
d
:
M
a
y
2
3
,
2
0
2
4
.
[
O
n
l
i
n
e
]
.
A
v
a
i
l
a
b
l
e
:
h
t
t
p
s
:
/
/
g
i
t
h
u
b
.
c
o
m/
i
b
n
m
a
l
i
k
/
g
o
l
d
e
n
-
c
o
r
p
u
s
-
a
r
a
b
i
c
[
2
5
]
H
.
M
u
b
a
r
a
k
,
“
B
u
i
l
d
f
a
s
t
a
n
d
a
c
c
u
r
a
t
e
l
e
mm
a
t
i
z
a
t
i
o
n
f
o
r
A
r
a
b
i
c
,
”
i
n
L
RE
C
2
0
1
8
-
1
1
t
h
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
r
e
n
c
e
o
n
L
a
n
g
u
a
g
e
Re
so
u
r
c
e
s
a
n
d
Ev
a
l
u
a
t
i
o
n
,
2
0
1
9
,
p
p
.
1
1
2
8
–
1
1
3
2
.
[
2
6
]
M
.
B
o
u
d
c
h
i
c
h
e
a
n
d
A
.
M
a
z
r
o
u
i
,
“
A
h
y
b
r
i
d
a
p
p
r
o
a
c
h
f
o
r
A
r
a
b
i
c
l
e
mm
a
t
i
z
a
t
i
o
n
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
rn
a
l
o
f
S
p
e
e
c
h
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
2
2
,
n
o
.
3
,
p
p
.
5
6
3
–
5
7
3
,
2
0
1
9
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
0
7
7
2
-
0
1
8
-
9
5
2
8
-
3.
[
2
7
]
M
.
N
.
A
l
-
K
a
b
i
,
S
.
A
.
K
a
z
a
k
z
e
h
,
B
.
M
.
A
b
u
A
t
a
,
S
.
A
.
A
l
-
R
a
b
a
b
a
h
,
a
n
d
I
.
M
.
A
l
sma
d
i
,
“
A
n
o
v
e
l
r
o
o
t
b
a
s
e
d
A
r
a
b
i
c
s
t
e
mm
e
r
,
”
J
o
u
rn
a
l
o
f
K
i
n
g
S
a
u
d
U
n
i
v
e
rsi
t
y
-
C
o
m
p
u
t
e
r
a
n
d
I
n
f
o
rm
a
t
i
o
n
S
c
i
e
n
c
e
s
,
v
o
l
.
2
7
,
n
o
.
2
,
p
p
.
9
4
–
1
0
3
,
2
0
1
5
,
d
o
i
:
1
0
.
1
0
1
6
/
j
.
j
k
su
c
i
.
2
0
1
4
.
0
4
.
0
0
1
.
[
2
8
]
N
.
Th
a
l
j
i
,
N
.
A
.
H
a
n
i
n
,
S
.
A
l
-
H
a
k
e
e
m,
W
.
B
.
H
a
n
i
,
a
n
d
Z.
T
h
a
l
j
i
,
“
A
n
o
v
e
l
r
u
l
e
-
b
a
s
e
d
r
o
o
t
e
x
t
r
a
c
t
i
o
n
a
l
g
o
r
i
t
h
m
f
o
r
A
r
a
b
i
c
l
a
n
g
u
a
g
e
,
”
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
Ad
v
a
n
c
e
d
C
o
m
p
u
t
e
r
S
c
i
e
n
c
e
a
n
d
A
p
p
l
i
c
a
t
i
o
n
s
,
v
o
l
.
9
,
n
o
.
1
0
,
p
p
.
1
2
0
–
1
2
8
,
2
0
1
8
,
d
o
i
:
1
0
.
1
4
5
6
9
/
I
JA
C
S
A
.
2
0
1
8
.
0
9
1
0
1
5
.
[
2
9
]
B
.
A
z
m
a
n
,
“
R
o
o
t
i
d
e
n
t
i
f
i
c
a
t
i
o
n
t
o
o
l
f
o
r
A
r
a
b
i
c
v
e
r
b
s
,
”
I
EE
E
Ac
c
e
s
s
,
v
o
l
.
7
,
p
p
.
4
5
8
6
6
–
4
5
8
7
1
,
2
0
1
9
,
d
o
i
:
1
0
.
1
1
0
9
/
A
C
C
ESS
.
2
0
1
9
.
2
9
0
8
1
7
7
.
[
3
0
]
K
.
S
h
e
r
e
e
n
,
“
K
h
o
j
a
st
e
mm
e
r
,
”
Pa
c
i
f
i
c
U
n
i
v
e
rs
i
t
y
O
re
g
o
n
.
h
t
t
p
:
/
/
z
e
u
s.c
s
.
p
a
c
i
f
i
c
u
.
e
d
u
/
s
h
e
r
e
e
n
/
r
e
s
e
a
r
c
h
.
h
t
m#
s
t
e
mm
i
n
g
(
a
c
c
e
ss
e
d
M
a
y
2
3
,
2
0
2
4
)
.
B
I
O
G
RAP
H
I
E
S O
F
AUTH
O
RS
Dr
iss
Na
m
ly
is
a
n
a
ss
istan
t
p
ro
fe
ss
o
r
o
f
Co
m
p
u
ter
S
c
ie
n
c
e
a
t
M
o
h
a
m
m
e
d
V
Un
iv
e
rsity
in
Ra
b
a
t,
M
o
r
o
c
c
o
.
P
ro
f
Na
m
ly
re
c
e
iv
e
d
h
is
P
h
.
D.
d
e
g
re
e
in
Co
m
p
u
ter
S
c
ien
c
e
fro
m
M
o
h
a
m
m
e
d
V
Un
iv
e
rsity
i
n
2
0
2
0
.
His
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
a
rti
ficia
l
in
telli
g
e
n
c
e
,
e
sp
e
c
ially
n
a
tu
ra
l
lan
g
u
a
g
e
p
r
o
c
e
ss
in
g
.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
d
.
n
a
m
ly
@u
m
5
r.
a
c
.
m
a
.
K
a
r
im
B
o
u
z
o
u
b
a
a
is
a
f
u
ll
p
ro
fe
ss
o
r
o
f
c
o
m
p
u
ter
sc
ien
c
e
i
n
t
h
e
De
p
a
rtme
n
t
o
f
Co
m
p
u
ter
S
c
ien
c
e
,
M
o
h
a
m
m
a
d
i
a
S
c
h
o
o
l
o
f
E
n
g
i
n
e
e
rs,
M
o
h
a
m
m
e
d
V
Un
iv
e
rsity
i
n
Ra
b
a
t.
P
ro
f/Dr.
Ka
rim
Bo
u
z
o
u
b
a
a
re
c
e
iv
e
d
h
is
P
h
.
D.
d
e
g
re
e
in
1
9
9
8
fro
m
Lav
a
l
Un
iv
e
rsit
y
.
His
re
se
a
rc
h
in
tere
sts
in
c
lu
d
e
a
rti
ficia
l
in
telli
g
e
n
c
e
,
d
a
ta
sc
ien
c
e
,
n
a
tu
r
a
l
lan
g
u
a
g
e
p
ro
c
e
ss
in
g
,
a
n
d
c
o
m
p
u
tati
o
n
a
l
li
n
g
u
isti
c
s.
He
c
a
n
b
e
c
o
n
tac
ted
a
t
e
m
a
il
:
k
a
rim.b
o
u
z
o
u
b
a
a
@e
m
i.
a
c
.
m
a
.
Evaluation Warning : The document was created with Spire.PDF for Python.