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
.
5
,
Octo
b
er
20
25
,
p
p
.
4
8
3
7
~
4
8
4
7
I
SS
N:
2088
-
8
7
0
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijece.
v
15
i
5
.
pp
4
8
3
7
-
4
8
4
7
4837
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ec
e.
ia
esco
r
e.
co
m
Sy
stema
tic
revi
e
w:
t
he appli
ca
t
io
n
o
f
Cha
t
G
PT
on
Ara
bic
la
ng
ua
g
e t
ex
t
pro
cess
ing
Ali Mo
us
a
Al
Sb
o
u
1,
2
,
F
a
dzli Sy
ed
Abdu
lla
h
1
,
Ash
a
n
ira
M
a
t
Der
is
1
1
F
a
c
u
l
t
y
o
f
C
o
mp
u
t
e
r
S
c
i
e
n
c
e
a
n
d
M
a
t
h
e
ma
t
i
c
s,
U
n
i
v
e
r
s
i
t
i
M
a
l
a
y
si
a
Te
r
e
n
g
g
a
n
u
(
U
M
T)
,
T
e
r
e
n
g
g
a
n
u
,
M
a
l
a
y
si
a
2
D
e
p
a
r
t
me
n
t
o
f
C
o
m
p
u
t
e
r
I
n
f
o
r
m
a
t
i
o
n
S
y
st
e
ms,
C
o
l
l
e
g
e
o
f
I
n
f
o
r
ma
t
i
o
n
T
e
c
h
n
o
l
o
g
y
,
A
l
H
u
sse
i
n
B
i
n
Ta
l
a
l
U
n
i
v
e
r
si
t
y
(
A
H
U
)
,
M
a
a
n
,
J
o
r
d
a
n
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Sep
2
9
,
2
0
2
4
R
ev
is
ed
Ap
r
2
8
,
2
0
2
5
Acc
ep
ted
J
u
l 3
,
2
0
2
5
Ov
e
r
4
2
0
m
il
li
o
n
p
e
o
p
le
sp
e
a
k
Ara
b
ic,
a
n
d
it
is
t
h
e
o
fficia
l
lan
g
u
a
g
e
o
f
2
2
c
o
u
n
tri
e
s.
Its
c
o
m
p
lex
m
o
r
p
h
o
lo
g
y
a
n
d
d
iale
c
tal
d
iv
e
rsit
y
p
re
se
n
t
u
n
i
q
u
e
c
h
a
ll
e
n
g
e
s
f
o
r
n
a
tu
ra
l
lan
g
u
a
g
e
p
r
o
c
e
ss
in
g
(NLP
)
m
o
d
e
ls
li
k
e
Ch
a
tG
P
T.
Th
is
sy
ste
m
a
ti
c
re
v
iew
i
n
v
e
sti
g
a
tes
th
e
a
p
p
li
c
a
ti
o
n
o
f
Ch
a
tG
P
T
in
Ara
b
ic
lan
g
u
a
g
e
tex
t
p
ro
c
e
ss
in
g
,
e
x
a
m
in
in
g
it
s
p
o
ten
t
ial
u
se
s,
a
c
c
u
ra
c
y
,
a
n
d
li
m
it
a
ti
o
n
s.
Co
v
e
rin
g
li
tera
tu
re
p
u
b
li
sh
e
d
b
e
twe
e
n
2
0
2
1
a
n
d
2
0
2
4
,
t
h
is
re
v
iew
sy
n
t
h
e
siz
e
s
fin
d
in
g
s
fr
o
m
2
1
a
rti
c
les
,
a
d
d
re
ss
in
g
fo
u
r
k
e
y
re
se
a
rc
h
q
u
e
stio
n
s:
C
h
a
tG
P
T’s
a
p
p
l
ica
ti
o
n
s
in
Ara
b
ic
tex
t
p
r
o
c
e
ss
in
g
,
it
s
p
e
rfo
rm
a
n
c
e
in
term
s
o
f
a
c
c
u
ra
c
y
a
n
d
re
li
a
b
il
it
y
,
th
e
c
h
a
ll
e
n
g
e
s
a
n
d
li
m
it
a
ti
o
n
s
e
n
c
o
u
n
tere
d
,
a
n
d
fu
t
u
re
d
irec
ti
o
n
s
t
o
e
n
h
a
n
c
e
it
s
u
ti
li
z
a
ti
o
n
.
Re
su
lt
s
in
d
ica
te
th
a
t
C
h
a
tG
P
T
h
a
s
p
o
ten
t
ial
in
se
v
e
ra
l
a
p
p
li
c
a
ti
o
n
s,
in
c
lu
d
in
g
e
d
u
c
a
ti
o
n
a
l
t
o
o
ls,
m
a
c
h
in
e
tran
sla
ti
o
n
,
tex
t
g
e
n
e
ra
ti
o
n
,
a
n
d
se
n
ti
m
e
n
t
a
n
a
ly
sis.
De
sp
it
e
c
u
r
re
n
t
li
m
it
a
ti
o
n
s,
Ch
a
tG
P
T'
s
p
o
t
e
n
ti
a
l
in
Ara
b
ic
tex
t
p
ro
c
e
ss
in
g
is
p
ro
m
isin
g
.
Wh
il
e
it
sh
o
ws
h
i
g
h
a
c
c
u
ra
c
y
in
stru
c
tu
re
d
tas
k
s,
it
stru
g
g
les
wit
h
d
iale
c
tal
v
a
riati
o
n
s
a
n
d
c
u
lt
u
ra
l
n
u
a
n
c
e
s,
e
sp
e
c
ially
in
c
o
m
p
le
x
tex
t
ty
p
e
s.
P
rima
ry
li
m
it
a
ti
o
n
s
i
n
c
lu
d
e
a
lac
k
o
f
h
i
g
h
-
q
u
a
li
t
y
Ara
b
ic
d
a
tas
e
ts,
d
iffi
c
u
l
t
y
h
a
n
d
l
in
g
d
iale
c
ts,
a
n
d
a
n
e
e
d
fo
r
m
o
re
n
u
a
n
c
e
d
c
o
n
tex
t
u
a
l
u
n
d
e
rsta
n
d
in
g
.
F
u
t
u
re
re
se
a
rc
h
sh
o
u
ld
fo
c
u
s
o
n
imp
ro
v
i
n
g
d
a
ta
q
u
a
li
ty
,
e
x
p
a
n
d
i
n
g
d
iale
c
tal
c
o
v
e
ra
g
e
,
f
in
e
-
tu
n
i
n
g
m
o
d
e
ls
fo
r
sp
e
c
ifi
c
li
n
g
u
isti
c
tas
k
s,
a
n
d
in
te
g
ra
ti
n
g
AI
wit
h
h
u
m
a
n
tea
c
h
in
g
m
e
th
o
d
s.
Ad
d
re
ss
in
g
th
e
se
a
re
a
s
will
e
n
h
a
n
c
e
Ch
a
tG
P
T'
s
a
c
c
u
ra
c
y
a
n
d
re
li
a
b
il
it
y
f
o
r
Ara
b
ic NLP
.
K
ey
w
o
r
d
s
:
Ar
ab
ic
tex
t p
r
o
ce
s
s
in
g
C
h
atGPT
Ma
ch
in
e
lear
n
in
g
Natu
r
al
lan
g
u
ag
e
p
r
o
ce
s
s
in
g
Sy
s
tem
atic
r
ev
iew
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
:
Fad
zli
Sy
ed
Ab
d
u
llah
Facu
lty
o
f
C
o
m
p
u
ter
Scien
ce
an
d
Ma
th
em
atics
,
Un
iv
er
s
iti
Ma
lay
s
ia
T
er
en
g
g
an
u
(
UM
T
)
2
1
0
3
0
Ku
ala
Ner
u
s
,
T
e
r
en
g
g
a
n
u
Dar
u
l I
m
an
,
Ma
lay
s
ia
E
m
ail: e
f
ad
zli@
u
m
t.e
d
u
.
m
y
1.
I
NT
RO
D
UCT
I
O
N
Ar
ab
ic
lan
g
u
ag
e
is
an
o
f
f
icial
lan
g
u
a
g
e
f
o
r
2
2
Mid
d
le
E
a
s
ter
n
an
d
No
r
t
h
Af
r
ica
co
u
n
t
r
ies.
Ov
er
4
2
0
m
illi
o
n
p
eo
p
le
s
p
ea
k
Ar
a
b
ic
wo
r
ld
wid
e.
Du
e
t
o
its
h
is
to
r
ical,
cu
ltu
r
al,
a
n
d
g
eo
p
o
liti
ca
l
f
u
n
ctio
n
s
,
Ar
a
b
ic
is
s
t
ill
e
s
s
en
tial
to
d
ay
.
I
t
is
t
h
e
litu
r
g
ical
lan
g
u
ag
e
o
f
I
s
lam
an
d
h
as
a
r
ich
liter
ar
y
h
is
to
r
y
.
Ar
ab
ic
p
lay
s
a
s
ig
n
if
ican
t
r
o
le
in
g
lo
b
al
b
u
s
in
ess
,
r
eg
io
n
al
p
o
liti
cs,
an
d
in
ter
n
atio
n
al
d
ip
lo
m
ac
y
,
d
u
e
to
th
e
ec
o
n
o
m
ic
s
ig
n
if
ican
ce
o
f
th
e
r
eg
i
o
n
.
I
t
is
cr
u
cial
f
o
r
co
m
m
u
n
icatio
n
an
d
n
eg
o
tiatio
n
in
th
ese
f
i
eld
s
.
Ar
ab
ic
h
as
a
d
is
tin
ct
alp
h
ab
et,
co
m
p
le
x
m
o
r
p
h
o
lo
g
y
with
a
r
o
o
t
-
a
n
d
-
p
atter
n
s
y
s
tem
,
a
s
o
p
h
is
ticated
p
h
o
n
o
lo
g
ical
s
y
s
tem
,
an
d
ad
a
p
tab
le
s
y
n
tax
.
Mo
d
e
r
n
s
tan
d
ar
d
Ar
a
b
ic
(
MSA)
,
class
ical
Ar
ab
ic
(
C
A)
,
an
d
o
th
er
r
e
g
io
n
al
d
ialec
ts
ar
e
all
in
clu
d
ed
in
it,
m
ak
i
n
g
it
a
cr
u
cial
a
n
d
s
o
p
h
is
ticated
la
n
g
u
ag
e
in
m
an
y
f
ield
s
to
d
ay
.
Natu
r
al
lan
g
u
ag
e
p
r
o
ce
s
s
in
g
(
NL
P)
an
d
ar
tific
ia
l
in
tellig
en
ce
(
AI
)
h
av
e
p
ar
tic
u
lar
h
u
r
d
les
an
d
o
p
p
o
r
tu
n
ities
wh
en
d
ea
lin
g
with
Ar
ab
ic'
s
in
tr
icate
m
o
r
p
h
o
lo
g
y
,
s
y
n
tax
,
an
d
v
o
ca
b
u
lar
y
[
1
]
.
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
.
5
,
Octo
b
e
r
20
25
:
4
8
3
7
-
4
8
4
7
4838
AI
tech
n
o
lo
g
ies
an
d
ap
p
licati
o
n
s
ar
e
in
cr
ed
i
b
ly
v
er
s
atile,
c
o
v
er
in
g
v
ar
io
u
s
f
ield
s
,
in
clu
d
in
g
NL
P,
r
o
b
o
tics
,
co
m
p
u
ter
v
is
io
n
,
M
L
,
an
d
o
th
er
s
.
T
h
is
v
er
s
atility
is
wh
at
m
ak
es
AI
s
o
f
ascin
a
tin
g
,
as
it
s
ee
k
s
to
r
ep
licate
h
u
m
an
i
n
tellig
en
ce
an
d
d
ec
is
io
n
-
m
ak
in
g
i
n
a
wid
e
r
an
g
e
o
f
c
o
n
tex
ts
.
NL
P
is
a
p
r
im
e
ex
am
p
le
o
f
th
is
,
s
tu
d
y
in
g
n
atu
r
al
lan
g
u
a
g
e
g
en
er
atio
n
,
co
m
p
r
eh
e
n
s
io
n
,
an
d
an
aly
s
is
.
NL
P
'
s
v
er
s
atili
ty
is
ev
id
en
t
in
it
s
v
ar
io
u
s
ap
p
licatio
n
s
,
s
u
ch
as
in
f
o
r
m
atio
n
ex
t
r
ac
tio
n
,
s
en
tim
en
t
an
aly
s
is
,
m
ac
h
in
e
tr
an
s
latio
n
,
tex
t
s
u
m
m
ar
izatio
n
,
a
n
d
s
p
ee
c
h
r
ec
o
g
n
itio
n
.
An
e
x
am
p
le
o
f
th
is
v
er
s
atility
is
C
h
atGPT
f
r
o
m
Op
en
AI
,
a
co
n
v
er
s
atio
n
al
AI
b
u
ilt
o
n
th
e
GPT
ar
ch
itectu
r
e.
T
e
x
t
g
en
er
atio
n
m
o
d
els
f
r
o
m
Op
en
AI
ar
e
tau
g
h
t
to
co
m
p
r
eh
e
n
d
n
atu
r
al
lan
g
u
ag
e
,
co
d
e,
a
n
d
p
ictu
r
es,
an
d
th
e
y
ar
e
o
f
ten
ca
lled
s
u
b
s
tan
tial
l
an
g
u
ag
e
m
o
d
els
o
r
g
en
er
ativ
e
p
r
e
-
tr
ain
ed
tr
a
n
s
f
o
r
m
er
s
(
GPTs)
.
T
h
ese
m
o
d
els
g
en
er
ate
tex
t
o
u
tp
u
ts
(
in
m
u
lt
ip
le
lan
g
u
ag
es)
in
r
esp
o
n
s
e
to
in
p
u
ts
r
ef
er
r
e
d
to
as
“
p
r
o
m
p
ts
.
”
[
2
]
.
Ar
ab
ic
n
atu
r
al
lan
g
u
ag
e
p
r
o
c
ess
in
g
(
ANL
P)
h
as
s
ee
n
r
em
ar
k
ab
le
g
r
o
wth
as
a
r
esear
ch
d
o
m
ai
n
,
d
r
iv
en
b
y
th
e
i
n
tr
icate
ch
ar
ac
ter
is
tics
o
f
Ar
ab
ic
s
u
ch
as
its
co
m
p
lex
m
o
r
p
h
o
lo
g
y
,
r
ic
h
s
y
n
tax
,
a
n
d
d
iv
er
s
e
d
ialec
ts
.
Mo
d
er
n
ANL
P
s
y
s
t
em
s
h
ea
v
ily
lev
er
ag
e
m
ac
h
in
e
lear
n
in
g
(
ML
)
tec
h
n
iq
u
es,
wh
ich
h
av
e
p
r
o
v
e
n
ef
f
ec
tiv
e
d
esp
ite
th
e
lan
g
u
a
g
e'
s
in
h
er
en
t
am
b
ig
u
ities
,
in
clu
d
in
g
d
ig
lo
s
s
ia
an
d
u
n
iq
u
e
s
cr
ip
t
f
ea
tu
r
es.
Sig
n
if
ican
t
ad
v
an
ce
m
e
n
ts
in
clu
d
e
th
e
d
ev
elo
p
m
en
t
o
f
s
p
ec
i
alize
d
to
o
ls
lik
e
co
r
p
o
r
a
an
d
l
ex
ico
n
s
tailo
r
ed
f
o
r
Ar
ab
ic,
s
u
p
p
o
r
tin
g
task
s
s
u
ch
as
p
ar
s
in
g
an
d
p
ar
t
-
of
-
s
p
ee
ch
tag
g
in
g
.
Ho
wev
e
r
,
ch
allen
g
es p
er
s
is
t,
s
u
ch
as
th
e
ab
s
en
ce
o
f
s
tan
d
ar
d
ized
f
o
r
m
al
g
r
am
m
ar
f
o
r
MSA,
wh
i
ch
h
in
d
e
r
s
th
e
ev
o
lu
tio
n
o
f
m
o
r
e
s
o
p
h
is
ticated
s
y
s
tem
s
.
Ad
d
itio
n
ally
,
ad
d
r
e
s
s
in
g
Ar
ab
ic's
s
o
cio
lin
g
u
is
tic
co
m
p
lex
ities
,
p
ar
ticu
lar
ly
d
i
g
lo
s
s
ia,
r
em
ain
s
a
n
ascen
t
ar
ea
o
f
r
esear
ch
.
Gi
v
en
Ar
ab
ic'
s
g
lo
b
al
s
ig
n
if
ica
n
ce
with
o
v
er
4
0
0
m
illi
o
n
s
p
ea
k
er
s
,
en
h
an
cin
g
ANL
P
n
o
t
o
n
ly
s
u
p
p
o
r
ts
lin
g
u
is
tic
s
tu
d
ies
b
u
t
also
f
ac
ili
tates
p
r
ac
tical
ap
p
licatio
n
s
in
v
a
r
ian
t
d
o
m
ain
s
.
C
o
n
tin
u
ed
in
n
o
v
atio
n
in
ML
m
eth
o
d
o
l
o
g
ies
an
d
a
d
ap
tin
g
e
x
is
tin
g
NL
P
f
r
am
ewo
r
k
s
f
o
r
Ar
ab
ic
ar
e
cr
u
cial
to
s
u
r
m
o
u
n
tin
g
th
ese
o
b
s
tacle
s
an
d
ad
v
an
cin
g
th
e
f
ield
[
3
]
,
[
4
]
.
T
h
is
s
y
s
tem
atic
r
ev
iew
aim
s
t
o
ev
alu
ate
th
e
c
u
r
r
e
n
t
s
tate
o
f
C
h
atGPT
's
ap
p
licatio
n
with
Ar
ab
ic
tex
t
p
r
o
ce
s
s
in
g
,
ad
d
r
ess
in
g
cr
itical
q
u
esti
o
n
s
ab
o
u
t
its
p
o
te
n
tial
u
s
es,
ac
cu
r
ac
y
,
an
d
m
a
in
ch
allen
g
es
an
d
lim
itatio
n
s
.
W
h
ile
s
ev
er
al
g
e
n
er
ativ
e
AI
(
Gen
AI
)
m
o
d
els
a
n
d
lar
g
e
la
n
g
u
a
g
e
m
o
d
els
(
L
L
Ms)
h
av
e
r
ec
en
tly
em
er
g
ed
,
th
is
r
ev
iew
f
o
cu
s
es
o
n
C
h
atGPT
d
u
e
to
it
s
wid
esp
r
ea
d
ad
o
p
tio
n
an
d
th
e
u
n
i
q
u
e
lin
g
u
is
tic
an
d
cu
ltu
r
al
ch
allen
g
es
it
p
r
esen
ts
wh
en
ap
p
lied
to
Ar
a
b
ic
lan
g
u
ag
e
p
r
o
ce
s
s
in
g
.
T
h
e
r
ev
iew
wi
ll
ex
p
lo
r
e
p
r
ac
tical
ap
p
licatio
n
s
,
in
clu
d
in
g
ed
u
c
a
tio
n
al
to
o
ls
a
n
d
lan
g
u
a
g
e
lea
r
n
in
g
,
m
ac
h
i
n
e
tr
a
n
s
latio
n
,
g
en
er
atin
g
tex
t,
a
n
d
s
en
tim
en
t
an
aly
s
is
,
to
d
em
o
n
s
tr
ate
th
e
r
elev
an
ce
an
d
u
s
ef
u
l
n
ess
o
f
th
e
r
esear
ch
.
T
h
e
p
ap
er
is
g
u
id
ed
b
y
f
o
u
r
r
esear
ch
q
u
esti
o
n
s
th
at
ex
p
lo
r
e
th
e
ap
p
licatio
n
s
,
p
e
r
f
o
r
m
an
ce
,
ch
allen
g
es,
an
d
f
u
tu
r
e
d
ir
ec
tio
n
s
o
f
C
h
atGPT
in
Ar
ab
ic
tex
t
p
r
o
ce
s
s
in
g
.
T
h
e
Me
th
o
d
s
ec
tio
n
th
en
d
eta
ils
th
e
s
y
s
tem
atic
r
ev
iew
p
r
o
ce
s
s
,
in
clu
d
in
g
th
e
s
ea
r
ch
s
tr
ateg
y
,
in
clu
s
io
n
a
n
d
ex
clu
s
io
n
cr
iter
ia,
a
n
d
th
e
d
ata
ex
tr
ac
tio
n
a
n
d
s
y
n
th
esi
s
ap
p
r
o
ac
h
.
I
n
th
e
R
esu
lts
s
ec
tio
n
,
f
in
d
in
g
s
r
el
ated
to
th
e
r
esear
ch
q
u
esti
o
n
s
ar
e
p
r
esen
te
d
,
co
v
er
in
g
t
h
e
ap
p
licatio
n
s
o
f
C
h
atGPT
f
o
r
Ar
ab
ic
lan
g
u
ag
e
tex
t,
ev
alu
atin
g
its
ac
cu
r
ac
y
an
d
r
eliab
ilit
y
,
an
d
d
is
cu
s
s
in
g
th
e
ch
allen
g
es
an
d
lim
itatio
n
s
id
en
tifie
d
in
liter
atu
r
e.
T
h
e
Dis
cu
s
s
io
n
s
ec
tio
n
f
o
llo
ws,
ex
p
lo
r
in
g
t
h
e
b
r
o
ad
er
im
p
licatio
n
s
o
f
th
e
f
in
d
in
g
s
f
o
r
lin
g
u
is
tic
r
esear
ch
,
p
r
ac
tical
ap
p
licatio
n
s
,
an
d
f
u
tu
r
e
d
ir
ec
tio
n
s
to
en
h
an
ce
t
h
e
u
s
e
o
f
C
h
atGPT
in
Ar
ab
ic
tex
t
p
r
o
ce
s
s
in
g
.
T
h
e
p
ap
e
r
co
n
clu
d
es
with
a
C
o
n
clu
s
io
n
th
at
s
u
m
m
a
r
izes
th
e
k
ey
f
in
d
in
g
s
,
em
p
h
asizin
g
th
e
p
o
ten
tial a
n
d
lim
itatio
n
s
o
f
C
h
atGPT
in
Ar
ab
ic
lan
g
u
ag
e
p
r
o
ce
s
s
in
g
an
d
s
u
g
g
esti
n
g
ar
ea
s
f
o
r
f
u
tu
r
e
r
esear
c
h
.
2.
RE
L
AT
E
D
WO
RK
W
h
ile
r
esear
ch
o
n
Ar
ab
ic
n
atu
r
al
lan
g
u
ag
e
p
r
o
ce
s
s
in
g
(
ANL
P)
h
as
g
r
o
wn
s
ig
n
if
ican
tly
,
m
o
s
t
p
r
ev
io
u
s
s
u
r
v
ey
s
h
av
e
f
o
cu
s
ed
o
n
g
e
n
er
al
lan
g
u
ag
e
m
o
d
els o
r
b
r
o
a
d
er
Ar
ab
ic
NL
P a
p
p
licatio
n
s
.
Fo
r
in
s
tan
ce
,
Sey
id
o
v
[
5
]
p
r
o
v
i
d
ed
a
n
o
v
er
v
iew
o
f
a
r
tific
ial
in
tellig
en
ce
ap
p
licatio
n
s
in
Ar
ab
ic
NL
P,
em
p
h
asizin
g
p
r
o
s
p
ec
ts
b
u
t
with
o
u
t
d
etailed
p
er
f
o
r
m
an
ce
a
n
aly
s
is
o
f
in
d
iv
id
u
al
m
o
d
els
lik
e
C
h
atGPT
.
Similar
ly
,
Al
-
Sar
ay
r
eh
et
a
l.
[
3
]
d
is
cu
s
s
ed
th
e
ch
allen
g
es
o
f
Ar
ab
ic
NL
P
in
s
o
cial
m
ed
ia
co
n
tex
ts
b
u
t
d
id
n
o
t
ad
d
r
ess
g
en
er
ativ
e
m
o
d
els.
A
r
ec
en
t
s
y
s
tem
atic
r
ev
iew
b
y
Mu
s
taf
a
et
a
l.
[
4
]
f
o
cu
s
ed
o
n
s
p
ee
ch
e
m
o
tio
n
r
ec
o
g
n
itio
n
b
u
t
r
em
ain
ed
lim
ited
to
p
r
o
s
o
d
y
an
d
v
o
ca
l
f
ea
tu
r
es,
ex
clu
d
in
g
lar
g
e
lan
g
u
ag
e
m
o
d
els.
I
n
p
ar
allel,
Fer
d
u
s
h
et
a
l.
[
2
]
r
e
v
iewe
d
C
h
atGPT
's
ap
p
licatio
n
in
c
lin
ical
d
ec
is
io
n
s
u
p
p
o
r
t,
d
e
m
o
n
s
tr
atin
g
g
r
o
win
g
in
ter
est in
s
p
ec
if
ic
d
o
m
ain
-
b
ased
ass
ess
m
en
ts
b
u
t n
o
t A
r
ab
ic
tex
t p
r
o
ce
s
s
in
g
.
T
o
d
ate,
n
o
s
y
s
tem
atic
r
ev
ie
w
h
as
co
m
p
r
eh
e
n
s
iv
ely
ex
a
m
in
ed
C
h
atGPT
'
s
s
p
ec
if
ic
ap
p
licatio
n
s
,
p
er
f
o
r
m
an
ce
,
a
n
d
c
h
allen
g
es
in
Ar
ab
ic
lan
g
u
ag
e
tex
t
p
r
o
c
ess
in
g
.
T
h
is
p
ap
er
f
ills
th
at
g
ap
b
y
s
y
n
th
esizin
g
f
in
d
in
g
s
f
r
o
m
2
1
s
tu
d
ies
p
u
b
lis
h
ed
b
etwe
en
2
0
2
1
an
d
2
0
2
4
,
ad
d
r
ess
in
g
f
o
u
r
f
o
cu
s
ed
r
esear
ch
q
u
esti
o
n
s
r
elate
d
to
C
h
atGPT
's
u
s
e
in
ed
u
ca
tio
n
al
to
o
ls
,
tr
an
s
latio
n
,
tex
t
g
en
e
r
atio
n
,
a
n
d
s
en
ti
m
en
t
an
aly
s
is
.
Ou
r
ap
p
r
o
ac
h
f
o
llo
ws
a
PR
I
SMA
-
g
u
id
ed
r
ev
iew
p
r
o
to
co
l
a
n
d
in
clu
d
es
p
ee
r
-
r
e
v
iewe
d
a
n
d
p
r
e
p
r
in
t
s
o
u
r
ce
s
,
d
is
tin
g
u
is
h
in
g
it f
r
o
m
p
r
i
o
r
n
a
r
r
ativ
e
o
v
e
r
v
iews.
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
S
ystema
tic
r
ev
iew
:
th
e
a
p
p
lica
tio
n
o
f Ch
a
tGP
T o
n
A
r
a
b
ic
l
a
n
g
u
a
g
e
text
p
r
o
ce
s
s
in
g
(
A
li
Mo
u
s
a
A
lS
b
o
u
)
4839
3.
M
E
T
H
O
D
T
h
is
p
ap
er
em
p
lo
y
ed
a
s
y
s
tem
atic
r
ev
iew
m
eth
o
d
f
o
r
id
e
n
tify
in
g
,
ag
g
r
eg
atin
g
,
an
d
s
y
n
th
esizin
g
ex
is
tin
g
r
esear
ch
r
ele
v
an
t
to
a
r
esear
ch
t
o
p
ic
with
th
e
ai
m
o
f
s
y
n
th
esizin
g
ev
i
d
en
ce
.
I
n
s
o
r
tin
g
o
u
t
th
e
r
elev
an
t
ar
ticles
(
r
ec
o
r
d
s
)
to
b
e
an
aly
ze
d
,
r
esear
ch
er
s
u
s
ed
a
PR
I
SMA
m
o
d
el
,
s
ee
Fi
g
u
r
e
1
.
Fo
r
r
elate
d
ar
ticles,
a
co
m
p
r
eh
en
s
iv
e
li
ter
atu
r
e
s
ea
r
ch
u
n
til
1
4
/
8
/2
0
2
4
was
co
n
d
u
cted
u
s
in
g
d
atab
ases
s
u
ch
as
Scien
ce
Dir
ec
t,
Sp
r
in
g
er
L
in
k
,
W
eb
o
f
S
cien
ce
(
W
o
S),
S
co
p
u
s
,
I
E
E
E
Xp
lo
r
e,
R
esear
ch
Gate
,
an
d
AC
L
An
th
o
lo
g
y
,
as
well
as
p
r
e
-
p
r
in
t
r
ep
o
s
ito
r
ies
s
u
ch
as
m
ed
R
x
iv
,
an
d
Ar
Xiv
.
I
t
u
tili
ze
d
s
ea
r
ch
en
g
in
es
lik
e
Go
o
g
le
Sch
o
lar
a
n
d
Sem
an
tic
Sch
o
lar
.
Fig
u
r
e
1
.
PR
I
SMA
f
lo
w
d
iag
r
am
f
o
r
s
y
s
tem
atic
r
ev
iews
3
.
1
.
Def
ini
t
io
n o
f
re
s
ea
rc
h ques
t
io
ns
T
h
e
o
b
jectiv
e
o
f
th
is
s
tu
d
y
is
to
in
v
esti
g
ate
th
e
C
h
atGPT
m
o
d
els
th
at
h
av
e
b
ee
n
u
s
ed
f
o
r
Ar
ab
ic
tex
t
p
r
o
ce
s
s
in
g
.
Fo
u
r
q
u
esti
o
n
s
we
r
e
d
ef
in
e
d
B
ased
o
n
th
is
o
b
jec
tiv
e:
a.
R
esear
ch
q
u
esti
o
n
1
(
R
Q1
)
:
wh
at
ar
e
t
h
e
p
r
im
ar
y
ap
p
licatio
n
s
(
p
o
te
n
tial
u
s
es
)
o
f
C
h
at
GPT
f
o
r
Ar
ab
ic
lan
g
u
ag
e
te
x
t p
r
o
ce
s
s
in
g
?
b.
R
esear
ch
q
u
esti
o
n
2
(
R
Q2
)
:
h
o
w
d
o
es
C
h
atGPT
p
er
f
o
r
m
in
ter
m
s
o
f
ac
cu
r
ac
y
an
d
r
eliab
ilit
y
wh
en
p
r
o
ce
s
s
in
g
Ar
ab
ic
tex
t
p
r
o
ce
s
s
in
g
?
c.
R
esear
ch
q
u
esti
o
n
3
(
R
Q3
)
:
w
h
at
ar
e
t
h
e
m
ai
n
ch
allen
g
es
a
n
d
lim
itatio
n
s
ass
o
ciate
d
with
u
s
in
g
C
h
atGPT
f
o
r
Ar
ab
ic
la
n
g
u
a
g
e
tex
t p
r
o
ce
s
s
in
g
?
d.
R
esear
ch
q
u
esti
o
n
4
(
R
Q4
)
:
W
h
at
f
u
tu
r
e
d
i
r
ec
tio
n
s
ca
n
en
h
a
n
ce
th
e
u
tili
za
tio
n
o
f
C
h
atGPT
f
o
r
Ar
ab
ic
tex
t
p
r
o
ce
s
s
in
g
?
3
.
2
.
Sea
rc
h pha
s
e
T
h
e
s
ea
r
ch
q
u
e
r
y
was
f
o
r
m
u
lated
u
s
in
g
B
o
o
lean
o
p
er
ato
r
s
,
with
k
ey
wo
r
d
s
s
u
ch
as
“
C
h
atGPT
”
“
Ar
ab
ic
”
an
d
“
o
p
en
AI
”
.
I
n
ad
d
itio
n
,
s
o
m
e
ter
m
s
ar
e
lis
ted
in
th
e
tab
le
b
elo
w.
T
h
is
an
aly
s
is
f
o
cu
s
ed
o
n
r
ec
e
n
t
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
.
5
,
Octo
b
e
r
20
25
:
4
8
3
7
-
4
8
4
7
4840
ar
ticles
th
at
co
n
tain
ed
r
elev
an
t
k
ey
wo
r
d
s
in
th
eir
titl
es
o
r
ab
s
tr
ac
ts
to
ad
d
r
ess
th
e
r
esear
ch
q
u
esti
o
n
s
.
Desp
ite
th
e
tar
g
eted
n
at
u
r
e
o
f
o
u
r
k
e
y
wo
r
d
s
s
p
ec
if
ic
to
th
e
A
r
ab
ic
lan
g
u
ag
e,
we
o
b
s
er
v
ed
a
n
o
t
ab
le
n
ee
d
f
o
r
m
o
r
e
r
eso
u
r
ce
s
d
ir
ec
tly
r
elate
d
t
o
A
r
ab
ic
tex
t,
as
m
u
ch
o
f
th
e
e
x
is
tin
g
r
esear
ch
ten
d
s
to
ad
d
r
ess
b
r
o
ad
e
r
asp
ec
ts
o
f
tex
t
p
r
ep
r
o
ce
s
s
in
g
an
d
ca
teg
o
r
izatio
n
.
T
h
u
s
,
th
is
h
ig
h
lig
h
ts
th
e
cr
itical
n
ee
d
f
o
r
m
o
r
e
r
esear
ch
tailo
r
ed
to
Ar
ab
ic
NL
P.
T
ab
le
1
s
u
m
m
ar
izes
th
e
n
u
m
b
er
o
f
r
ec
o
r
d
s
r
etr
iev
ed
f
r
o
m
Sco
p
u
s
an
d
all
o
th
er
co
m
b
i
n
ed
s
o
u
r
ce
s
(
e.
g
.
,
Sp
r
in
g
er
L
in
k
,
I
E
E
E
Xp
lo
r
e,
AC
L
An
th
o
l
o
g
y
,
R
esear
ch
Gate
,
an
d
Go
o
g
le
Sc
h
o
lar
)
.
T
ab
le
1
.
B
o
o
lean
q
u
er
y
s
y
n
tax
B
o
o
l
e
a
n
q
u
e
r
y
sy
n
t
a
x
S
c
o
p
u
s
O
t
h
e
r
s
/
D
a
t
a
b
a
se
TI
TLE
-
A
B
S
-
K
EY
(
O
p
e
n
A
I
O
R
C
h
a
t
G
P
T
)
A
N
D
A
r
a
b
i
c
57
27
A
p
p
l
i
c
a
t
i
o
n
A
N
D
(
O
p
e
n
A
I
O
R
C
h
a
t
G
P
T
)
A
N
D
A
r
a
b
i
c
11
6
3
.
3
.
I
nclus
io
n a
nd
ex
clus
io
n
cr
it
er
ia
(
E
lig
ibi
lity
cr
it
er
ia
)
I
n
lin
e
with
s
tan
d
a
r
d
s
y
s
tem
atic
r
ev
iew
m
eth
o
d
o
lo
g
y
,
cle
ar
in
clu
s
io
n
a
n
d
ex
clu
s
io
n
cr
iter
ia
wer
e
estab
lis
h
ed
to
g
u
i
d
e
th
e
s
elec
tio
n
o
f
s
tu
d
ies.
T
h
ese
c
r
iter
ia
s
et
th
e
b
o
u
n
d
ar
ies
o
f
th
e
r
ev
iew
an
d
h
elp
m
in
im
ize
s
elec
tio
n
b
ias
b
y
f
ilt
er
in
g
th
e
liter
atu
r
e
in
a
co
n
s
is
ten
t,
tr
an
s
p
ar
e
n
t
m
an
n
er
.
T
h
e
p
u
r
p
o
s
e
o
f
d
e
f
in
in
g
s
tr
ict
cr
iter
ia
is
to
en
s
u
r
e
th
at
th
e
r
ev
iew
r
em
ai
n
s
f
o
cu
s
ed
o
n
p
er
tin
en
t,
h
i
g
h
-
q
u
ality
ev
id
e
n
ce
wh
ile
ex
clu
d
in
g
out
-
of
-
s
co
p
e
o
r
l
o
w
-
r
elev
an
c
e
s
tu
d
ies.
B
elo
w
ar
e
th
e
s
p
ec
if
ic
in
clu
s
io
n
an
d
ex
cl
u
s
io
n
c
r
iter
ia
u
s
ed
in
th
is
r
ev
iew.
3
.
3
.
1
.
I
nclus
io
n
cr
it
er
ia
Fo
u
r
(
4
)
in
clu
s
io
n
c
r
iter
ia
wer
e
estab
lis
h
ed
:
a.
Ar
ticles f
o
cu
s
ed
o
n
th
e
ap
p
lic
atio
n
o
f
C
h
atGPT
to
Ar
ab
ic
la
n
g
u
ag
e
tex
t.
b.
Ar
ticles ev
alu
atin
g
th
e
p
er
f
o
r
m
an
ce
an
d
ac
cu
r
ac
y
o
f
C
h
atG
PT
o
n
Ar
ab
ic
tex
t.
c.
Pu
b
licatio
n
s
d
is
cu
s
s
in
g
th
e
ch
allen
g
es a
n
d
lim
itatio
n
s
o
f
C
h
atGPT
with
Ar
ab
ic
lan
g
u
ag
e
t
ex
t.
d.
Peer
-
r
ev
iewe
d
ar
ticles,
co
n
f
er
en
ce
p
ap
er
s
,
a
n
d
tech
n
ical
r
ep
o
r
ts
.
3
.
3
.
2
.
E
x
clus
io
n
cr
it
er
ia
Fo
u
r
(
4
)
ex
clu
s
io
n
c
r
iter
ia
wer
e
estab
lis
h
ed
:
a.
Ar
ticles n
o
t r
elate
d
to
C
h
atGPT
o
r
Ar
ab
ic
la
n
g
u
a
g
e.
b.
Ar
ticles d
o
n
o
t e
v
alu
ate
t
h
e
p
e
r
f
o
r
m
a
n
ce
an
d
ac
cu
r
ac
y
o
f
C
h
atGPT
o
n
Ar
ab
ic
tex
t.
c.
Ar
ticles n
o
t a
v
ailab
le
in
f
u
ll te
x
t.
d.
Pu
b
licatio
n
s
b
ef
o
r
e
2
0
2
1
wer
e
ex
clu
d
ed
.
T
h
e
r
e
v
iew
f
o
cu
s
es
o
n
liter
atu
r
e
p
u
b
lis
h
ed
b
et
wee
n
2
0
2
1
an
d
2
0
2
4
,
alig
n
in
g
with
th
e
m
o
s
t
r
ec
en
t
d
ev
elo
p
m
en
ts
in
AI
an
d
NL
P
tech
n
o
lo
g
ies
to
en
s
u
r
e
t
h
e
r
elev
an
ce
o
f
th
e
f
in
d
in
g
s
.
3.
4
.
Da
t
a
e
x
t
ra
ct
i
o
n a
nd
s
y
nthesis
I
n
itially
,
a
to
tal
o
f
1
0
1
ar
ticles
wer
e
s
elec
ted
f
r
o
m
all
d
atab
a
s
es,
in
clu
d
in
g
6
8
f
r
o
m
SC
OP
US,
an
d
3
3
f
r
o
m
o
t
h
er
d
ata
b
ases
.
T
h
e
ar
ti
cle
s
elec
tio
n
p
r
o
ce
s
s
in
v
o
lv
e
d
th
e
f
o
llo
win
g
s
tag
es:
a.
R
em
o
v
in
g
d
u
p
licatio
n
s
:
Ar
tic
les
wer
e
im
p
o
r
te
d
in
t
o
a
R
ef
er
en
ce
Ma
n
ag
er
Sy
s
tem
(
E
n
d
No
te)
an
d
4
9
d
u
p
licate
r
ec
o
r
d
s
wer
e
r
em
o
v
ed
,
r
ed
u
cin
g
th
e
n
u
m
b
er
o
f
ar
t
icles to
5
2
.
b.
T
itle
an
d
Ab
s
tr
ac
t
Scr
ee
n
in
g
:
T
h
is
p
r
o
ce
s
s
in
v
o
lv
es
r
ev
i
ewin
g
th
e
titl
es
an
d
ab
s
tr
ac
t
s
to
d
eter
m
i
n
e
wh
eth
er
th
e
y
a
r
e
r
ele
v
an
t
t
o
th
e
to
p
ic
b
ased
o
n
th
e
in
clu
s
io
n
an
d
e
x
clu
s
io
n
cr
iter
ia
.
A
s
th
e
r
esu
lt,
2
7
r
ec
o
r
d
s
wer
e
in
cl
u
d
ed
f
o
r
f
u
r
t
h
er
an
aly
s
is
,
with
2
5
b
ein
g
e
x
clu
d
ed
.
c.
I
n
f
o
r
m
atio
n
g
ath
er
in
g
:
Fu
ll
tex
t
is
r
ev
iewe
d
in
d
etail
f
o
r
elig
ib
ilit
y
ass
ess
m
en
t
to
en
s
u
r
e
t
h
at
th
e
ar
ticles
m
ee
t
all
th
e
s
tu
d
y
q
u
esti
o
n
s
.
Data
wer
e
ex
tr
ac
ted
f
r
o
m
s
elec
ted
ar
ticles
u
s
in
g
a
s
tan
d
ar
d
ized
f
o
r
m
,
ca
p
tu
r
in
g
in
f
o
r
m
atio
n
o
n
s
tu
d
y
d
esig
n
,
m
eth
o
d
s
,
k
ey
f
in
d
i
n
g
s
,
an
d
co
n
clu
s
io
n
s
.
As
th
e
r
esu
lt,
1
ar
ticle
was c
o
n
s
id
er
ed
ir
r
elev
a
n
t to
th
e
s
tu
d
y
an
d
ex
clu
d
e
d
,
leav
in
g
2
6
ar
ticles.
d.
Qu
ality
ch
ec
k
: Fin
ally
,
af
ter
ass
es
s
in
g
th
e
elig
ib
ilit
y
o
f
th
e
ar
ticles,
an
o
th
er
5
ar
ticles we
r
e
b
ein
g
ex
clu
d
e
d
f
o
r
h
a
v
in
g
p
o
o
r
p
ap
e
r
q
u
ality
,
leav
in
g
o
n
ly
2
1
ar
ticles to
b
e
i
n
clu
d
ed
i
n
th
is
r
ev
iew
s
tu
d
y
.
4.
RE
SU
L
T
S
AND
D
I
SCU
SS
I
O
N
Af
ter
d
ata
ex
tr
ac
tio
n
f
r
o
m
s
el
ec
ted
ar
ticles,
th
e
n
ar
r
ativ
e
f
o
r
m
at
will
s
y
n
th
esize
d
ata.
W
e
p
r
esen
t
th
e
r
esu
lts
o
f
th
e
r
ev
iewe
d
ar
ticle
s
,
f
o
cu
s
in
g
o
n
o
u
r
4
r
esear
c
h
q
u
esti
o
n
s
,
p
ar
ticu
lar
ly
with
r
eg
ar
d
to
C
h
atGPT
.
T
o
ex
tr
ac
t
d
ata
f
r
o
m
th
e
in
clu
d
ed
ar
ticles,
a
p
r
e
-
d
ef
in
e
d
d
ata
ex
tr
ac
tio
n
m
o
d
el
was
u
s
ed
.
T
h
e
m
o
d
el
co
n
tain
s
th
e
f
o
llo
win
g
v
a
r
iab
les:
ar
ticle
titl
e,
au
th
o
r
s
,
y
ea
r
,
ty
p
e,
an
d
o
th
er
in
f
o
r
m
atio
n
.
T
h
e
d
is
tr
ib
u
tio
n
o
f
ar
ticles
b
y
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
S
ystema
tic
r
ev
iew
:
th
e
a
p
p
lica
tio
n
o
f Ch
a
tGP
T o
n
A
r
a
b
ic
l
a
n
g
u
a
g
e
text
p
r
o
ce
s
s
in
g
(
A
li
Mo
u
s
a
A
lS
b
o
u
)
4841
p
u
b
licatio
n
y
ea
r
an
d
p
u
b
licati
o
n
ty
p
e
is
s
h
o
wn
in
Fig
u
r
e
2
.
As
ca
n
b
e
s
ee
n
,
th
er
e
h
as
b
ee
n
a
s
h
ar
p
in
cr
ea
s
e
in
ar
ticles
u
s
in
g
C
h
atGPT
f
o
r
Ar
ab
ic
tex
t
i
n
th
e
p
ast
t
h
r
ee
y
ea
r
s
.
W
h
ile
th
er
e
was
o
n
ly
o
n
e
ar
ticle
in
2
0
2
2
,
t
h
e
n
u
m
b
er
i
n
cr
ea
s
ed
to
8
i
n
2
0
2
3
an
d
1
2
in
2
0
2
4
.
T
h
e
d
is
tr
ib
u
tio
n
o
f
a
r
ticles
b
y
p
u
b
licatio
n
ty
p
e
s
h
o
ws
th
at
m
o
s
t
o
f
th
e
ar
ticles
in
clu
d
ed
in
th
is
s
tu
d
y
(
6
ar
ticles,
2
9
%)
ar
e
co
n
f
er
e
n
ce
ar
ticles.
Fo
u
r
teen
ar
ticles
(
6
7
%)
ar
e
wo
r
k
s
h
o
p
ar
ticles.
T
h
er
e
i
s
also
o
n
e
jo
u
r
n
al
letter
(
5
%).
Fig
u
r
e
2
.
Dis
tr
ib
u
tio
n
o
f
p
u
b
li
ca
tio
n
s
b
y
y
ea
r
an
d
ty
p
e
4
.
1
.
RQ
1
:
Wha
t
a
re
s
o
m
e
p
o
t
ent
ia
l a
pp
lica
t
io
ns
o
f
G
P
T
f
o
r
Ara
bic
la
ng
ua
g
e
t
e
x
t
pro
ce
s
s
ing
?
Fiv
e
p
r
ed
eter
m
in
ed
th
em
es
e
m
er
g
ed
f
r
o
m
R
Q1
an
d
wer
e
u
s
ed
in
th
e
s
y
n
th
esis
.
T
h
o
s
e
th
em
es
ar
e
:
i
)
ed
u
ca
tio
n
al
to
o
ls
an
d
lan
g
u
ag
e
lear
n
in
g
,
ii
)
m
ac
h
i
n
e
tr
an
s
latio
n
,
iii
)
tex
t
g
en
er
atio
n
,
an
d
iv
)
s
en
tim
en
t
an
aly
s
is
.
As
illu
s
tr
ated
in
T
ab
le
2
,
5
a
r
ticles
(
2
3
%)
in
d
icate
th
at
C
h
atGPT
is
b
o
th
an
ed
u
ca
tio
n
al
to
o
l
an
d
a
lan
g
u
ag
e
lear
n
in
g
m
o
d
el.
I
n
c
o
m
p
ar
is
o
n
,
te
n
ar
ticles
(
4
7
%
o
f
th
e
ar
ticles)
h
ig
h
lig
h
t
th
e
p
o
ten
tial
ap
p
licatio
n
s
o
f
C
h
atGPT
in
m
ac
h
in
e
tr
an
s
latio
n
.
Sp
ec
if
ically
,
f
o
u
r
ar
ti
cles
(
1
9
%)
s
u
g
g
est
th
at
C
h
at
GPT
is
a
m
ac
h
in
e
tr
an
s
latio
n
to
o
l
f
o
r
co
n
v
er
tin
g
E
n
g
lis
h
tex
t
to
Ar
ab
ic
an
d
v
ice
v
er
s
a.
Ad
d
itio
n
ally
,
two
ar
ticles
(
0
.
9
%)
r
ep
o
r
t
its
u
s
e
in
s
en
tim
en
t
a
n
aly
s
is
.
T
h
e
Dis
tr
ib
u
tio
n
o
f
ar
ticles
b
a
s
ed
o
n
p
o
ten
tial
a
p
p
licatio
n
s
i
s
s
h
o
wn
in
Fig
u
r
e
3
.
As
ca
n
b
e
s
ee
n
,
ap
p
licatio
n
s
in
clu
d
e
ed
u
ca
tio
n
al
to
o
ls
(
5
s
tu
d
ies),
m
ac
h
in
e
tr
an
s
latio
n
(
1
0
s
tu
d
ies),
te
x
t
g
en
er
atio
n
(
4
s
tu
d
ies),
a
n
d
s
en
tim
en
t a
n
aly
s
is
(
2
s
tu
d
ies).
T
ab
le
2
.
Dis
tr
ib
u
tio
n
o
f
ar
ticle
s
b
ased
o
n
p
o
ten
tial a
p
p
licatio
n
s
A
p
p
l
i
c
a
t
i
o
n
Li
st
o
f
a
r
t
i
c
l
e
s
To
t
a
l
Ed
u
c
a
t
i
o
n
a
l
t
o
o
l
s
a
n
d
l
a
n
g
u
a
g
e
l
e
a
r
n
i
n
g
[
5
]
–
[
9
]
5
M
a
c
h
i
n
e
t
r
a
n
s
l
a
t
i
o
n
[
1
0
]
–
[
1
9
]
10
Te
x
t
g
e
n
e
r
a
t
i
o
n
[
2
0
]
–
[
2
3
]
4
S
e
n
t
i
me
n
t
a
n
a
l
y
si
s
[
2
4
]
,
[
2
5
]
2
Fig
u
r
e
3
.
Dis
tr
ib
u
tio
n
o
f
a
r
ticles b
ased
o
n
C
h
atGPT
p
o
ten
tia
l a
p
p
licatio
n
s
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
.
5
,
Octo
b
e
r
20
25
:
4
8
3
7
-
4
8
4
7
4842
4
.
1
.
1
.
E
du
ca
t
io
na
l
t
o
o
ls
a
nd
la
ng
ua
g
e
lea
rning
I
n
r
ec
e
n
t
s
tu
d
ies,
C
h
atGPT
is
h
ig
h
lig
h
ted
as
a
v
e
r
s
atile
ed
u
c
atio
n
al
to
o
l
with
s
ig
n
if
ican
t
ap
p
licatio
n
s
f
o
r
Ar
ab
ic
lan
g
u
ag
e
teac
h
in
g
.
Mo
h
am
ed
et
a
l.
[
6
]
n
o
te
th
a
t
C
h
atGPT
en
h
an
ce
s
Ar
ab
ic
lan
g
u
ag
e
teac
h
in
g
,
s
tu
d
en
t
p
er
f
o
r
m
a
n
ce
an
al
y
s
is
,
an
d
c
o
n
ten
t
-
lea
r
n
er
i
n
ter
ac
tio
n
b
y
f
ac
ilit
atin
g
r
esear
ch
,
ta
s
k
co
m
p
letio
n
,
an
d
en
g
ag
in
g
ac
tiv
ities
.
Sey
id
o
v
[
5
]
p
o
i
n
ts
o
u
t
its
p
o
ten
tial
in
d
ev
elo
p
in
g
in
tellig
en
t
tu
to
r
i
n
g
s
y
s
tem
s
,
lan
g
u
ag
e
lear
n
in
g
p
latf
o
r
m
s
,
an
d
ed
u
ca
tio
n
al
g
am
es
tailo
r
ed
f
o
r
Ar
ab
ic
lear
n
er
s
th
r
o
u
g
h
p
er
s
o
n
alize
d
lear
n
in
g
.
Nasar
u
d
d
in
[
7
]
em
p
h
asizes
C
h
atGPT
'
s
r
o
le
in
s
u
p
p
o
r
tin
g
Ar
ab
ic
lan
g
u
ag
e
teac
h
er
s
with
cu
s
to
m
ized
ed
u
ca
tio
n
al
m
ate
r
ials
.
Ad
d
itio
n
ally
,
B
u
tg
er
eit
et
a
l.
[
8
]
d
em
o
n
s
tr
ate
C
h
atGPT
’
s
ef
f
ec
tiv
en
ess
in
th
e
Pro
f
Pi
m
ath
em
atics
tu
to
r
in
g
s
y
s
tem
f
o
r
Ar
a
b
ic
-
s
p
ea
k
in
g
s
tu
d
en
t
s
,
s
h
o
win
g
h
ig
h
u
s
er
s
atis
f
ac
tio
n
an
d
im
p
r
o
v
ed
m
ath
s
k
ills
.
L
elep
ar
y
et
a
l.
[
9
]
f
in
d
th
at
C
h
atGPT
s
ig
n
if
ic
an
tly
en
h
a
n
ce
s
u
n
iv
e
r
s
ity
-
lev
el
Ar
ab
ic
lan
g
u
a
g
e
lear
n
in
g
b
y
im
p
r
o
v
in
g
r
ea
d
in
g
s
k
ills
,
b
o
o
s
tin
g
m
o
tiv
at
io
n
,
an
d
ea
s
in
g
ass
ig
n
m
e
n
t
co
m
p
letio
n
.
T
h
is
in
f
o
r
m
atio
n
u
n
d
er
s
co
r
es
C
h
atGPT
's
g
r
o
win
g
im
p
o
r
ta
n
ce
in
en
h
an
cin
g
ed
u
ca
tio
n
al
p
r
ac
tic
es
an
d
r
eso
u
r
ce
s
f
o
r
Ar
ab
ic
lan
g
u
a
g
e
lear
n
er
s
.
4
.
1
.
2
.
M
a
chine
t
ra
ns
la
t
io
n
C
h
atGPT
i
s
a
m
ac
h
in
e
tr
an
s
la
tio
n
to
o
l
th
at
co
n
v
er
ts
E
n
g
lis
h
tex
t
to
Ar
ab
ic
an
d
v
ice
v
er
s
a.
B
ec
au
s
e
it
h
as
ad
v
an
ce
d
NL
P
ca
p
ab
ili
ties
,
it
p
r
o
v
id
es
in
s
tan
t
an
d
c
o
n
tex
tu
ally
r
ele
v
an
t
tr
an
s
latio
n
s
.
Sev
er
al
s
tu
d
ies
h
av
e
e
x
p
lo
r
e
d
th
e
u
s
e
o
f
C
h
at
GPT
f
o
r
t
r
an
s
latin
g
Ar
a
b
ic
te
x
ts
.
Desp
ite
its
s
tr
o
n
g
p
er
f
o
r
m
an
ce
in
E
n
g
lis
h
a
n
d
o
th
er
h
ig
h
-
r
eso
u
r
ce
lan
g
u
ag
e
s
,
C
h
atGPT
’
s
ef
f
ec
tiv
en
ess
i
n
Ar
ab
ic
tr
an
s
latio
n
f
ac
es
u
n
iq
u
e
ch
allen
g
es
an
d
h
as m
ix
ed
r
esu
lts
.
R
esear
ch
o
n
C
h
atGPT
'
s
r
o
le
in
m
ac
h
in
e
tr
an
s
latio
n
,
p
ar
t
icu
lar
ly
b
etwe
en
Ar
ab
ic
an
d
E
n
g
lis
h
,
h
ig
h
lig
h
ts
its
v
er
s
atility
an
d
e
f
f
ec
tiv
en
ess
ac
r
o
s
s
v
ar
io
u
s
d
o
m
ain
s
.
B
an
im
elh
em
an
d
Am
a
y
r
eh
[
1
1
]
ev
alu
ate
C
h
atGPT
as
a
to
o
l
f
o
r
tr
an
s
latin
g
E
n
g
lis
h
to
Ar
ab
ic,
n
o
tin
g
its
ab
ilit
y
to
h
an
d
le
d
iv
er
s
e
tex
t
f
o
r
m
ats,
wh
ile
Alk
h
awa
ja
[
1
3
]
em
p
h
asizes
its
p
o
ten
tial
to
en
h
an
ce
tr
an
s
latio
n
ef
f
icien
c
y
an
d
ac
ce
s
s
ib
ilit
y
.
Kh
o
s
h
af
a
h
[
1
9
]
f
in
d
s
th
at
C
h
atGPT
g
e
n
er
ally
d
eliv
er
s
ac
c
u
r
ate
tr
a
n
s
latio
n
s
,
ef
f
ec
tiv
ely
co
n
v
ey
in
g
t
h
e
in
ten
d
ed
m
ea
n
in
g
.
I
n
s
p
ec
ialized
ap
p
licatio
n
s
,
Alg
h
am
d
i
et
a
l.
[
1
0
]
f
o
c
u
s
o
n
f
in
e
-
tu
n
in
g
C
h
atGPT
-
3
.
5
T
u
r
b
o
f
o
r
tr
an
s
latin
g
f
in
an
cial
n
ews
f
r
o
m
Ar
ab
ic
to
E
n
g
lis
h
,
o
u
tp
e
r
f
o
r
m
in
g
o
th
er
n
eu
r
al
m
ac
h
in
e
tr
a
n
s
latio
n
m
o
d
els,
wh
ile
Alk
h
awa
ja
[
1
3
]
e
x
p
lo
r
e
its
u
s
e
in
f
ilm
tr
a
n
s
latio
n
,
d
e
m
o
n
s
tr
atin
g
its
ab
ilit
y
t
o
m
ai
n
tain
q
u
ality
ac
r
o
s
s
v
ar
i
o
u
s
d
im
en
s
io
n
s
.
Ob
eid
at
a
n
d
J
ar
a
d
at
[
1
5
]
ass
ess
th
eir
ef
f
ec
tiv
en
ess
in
tr
an
s
latin
g
r
esis
tan
ce
liter
atu
r
e,
p
ar
ticu
lar
ly
its
ab
ilit
y
to
ca
p
tu
r
e
liter
ar
y
es
s
en
ce
.
Alaf
n
an
[
1
2
]
in
v
esti
g
ates
its
p
er
f
o
r
m
an
ce
in
tr
an
s
latin
g
h
i
g
h
-
s
tak
es
s
p
ee
ch
es,
an
d
Kad
ao
u
i
et
a
l.
[
2
6
]
ex
a
m
in
e
C
h
atGPT
'
s
ap
p
l
icatio
n
ac
r
o
s
s
d
if
f
er
en
t
Ar
ab
i
c
d
ialec
ts
,
in
clu
d
in
g
C
A
an
d
MSA.
Mo
h
s
en
[
1
6
]
d
em
o
n
s
tr
ates
C
h
atGPT
'
s
p
r
ec
is
io
n
in
tr
an
s
latin
g
ac
ad
em
ic
ab
s
tr
ac
ts
,
p
ar
ticu
lar
ly
in
s
p
ec
ialized
co
n
tex
ts
,
wh
ile
Sh
ah
in
an
d
I
s
m
ail
[
1
7
]
ex
p
lo
r
e
th
eir
p
o
ten
tial
f
o
r
tr
an
s
latin
g
Ar
ab
ic
s
ig
n
lan
g
u
ag
e
(
Ar
SL)
an
d
o
th
e
r
s
ig
n
lan
g
u
a
g
es.
Fin
ally
,
AlKaa
b
i
et
a
l.
[
1
8
]
ev
alu
ate
its
ab
il
ity
to
tr
an
s
late
cu
ltu
r
e
-
b
o
u
n
d
ter
m
s
an
d
id
i
o
m
atic
ex
p
r
ess
io
n
s
in
liter
ar
y
tex
ts
,
s
p
ec
if
ically
in
Nag
u
ib
Ma
h
f
o
u
z’
s
n
o
v
el
Z
u
q
āq
al
-
Mid
aq
q
.
T
h
ese
s
tu
d
ies
co
llectiv
ely
d
em
o
n
s
tr
ate
C
h
atGPT
's
ca
p
ab
ilit
y
in
v
ar
i
o
u
s
m
ac
h
in
e
tr
a
n
s
latio
n
task
s
,
r
an
g
in
g
f
r
o
m
tech
n
ical
d
o
cu
m
e
n
ts
an
d
f
in
a
n
cial
n
ews to
liter
ar
y
wo
r
k
s
an
d
s
ig
n
lan
g
u
ag
es.
4
.
1
.
3
.
T
ex
t
g
ener
a
t
i
o
n
R
esear
ch
d
em
o
n
s
tr
ates
C
h
atGPT
's
p
o
wer
f
u
l
p
o
te
n
tial
in
v
ar
io
u
s
lin
g
u
is
tic
tex
t
g
en
er
a
tio
n
task
s
,
p
ar
ticu
lar
ly
i
n
Ar
ab
ic.
El
-
Sh
an
g
iti
et
a
l.
[
2
0
]
h
ig
h
lig
h
t
it
s
ab
ilit
y
to
g
en
er
ate
c
o
h
er
e
n
t
an
d
f
lu
en
t
Ar
ab
ic
s
to
r
ies,
em
p
h
asizin
g
t
h
e
to
o
l'
s
u
s
ef
u
ln
ess
in
cr
ea
tiv
e
w
r
itin
g
an
d
cu
ltu
r
al
s
to
r
y
tellin
g
tailo
r
ed
to
Ar
ab
r
eg
io
n
s
.
Similar
ly
,
B
eh
eitt
an
d
Hm
id
a
[
2
1
]
s
h
o
w
th
at
GPT
-
2
ca
n
b
e
ef
f
ec
tiv
ely
u
tili
ze
d
to
g
en
er
ate
h
ig
h
-
q
u
alit
y
Ar
ab
ic
p
o
em
s
,
r
ein
f
o
r
ci
n
g
its
ca
p
ab
ilit
y
in
p
r
o
d
u
cin
g
ac
cu
r
ate
cu
ltu
r
al
an
d
lin
g
u
is
tic
co
n
ten
t.
An
tar
[
2
2
]
d
is
cu
s
s
es
th
e
ap
p
licatio
n
o
f
C
h
atGPT
an
d
o
th
er
lar
g
e
lan
g
u
ag
e
m
o
d
els
(
L
L
Ms)
in
cr
ea
tiv
e
wr
itin
g
,
co
n
ten
t
g
en
er
atio
n
,
a
n
d
ed
u
ca
tio
n
al
to
o
ls
s
p
ec
if
ically
f
o
r
Ar
ab
ic
-
s
p
ea
k
in
g
au
d
ie
n
ce
s
,
with
a
f
o
cu
s
o
n
s
to
r
y
g
en
er
atio
n
.
Ad
d
itio
n
ally
,
Am
i
n
[
2
3
]
e
x
p
lo
r
es
th
e
u
s
e
o
f
C
h
atGPT
f
o
r
au
to
m
ated
Ar
ab
ic
t
ex
t
s
u
m
m
ar
izatio
n
,
wh
ich
is
p
ar
ticu
lar
ly
v
al
u
ab
le
in
ac
ad
em
ic
r
esear
ch
,
co
n
te
n
t
m
an
ag
em
en
t,
an
d
i
n
f
o
r
m
atio
n
r
etr
iev
al,
o
f
f
er
in
g
f
ast
an
d
a
cc
u
r
ate
s
u
m
m
ar
izati
o
n
s
o
lu
tio
n
s
.
T
h
ese
s
tu
d
ies
u
n
d
er
s
co
r
e
C
h
atGPT
'
s
v
er
s
atilit
y
an
d
ef
f
ec
tiv
en
ess
in
g
en
er
atin
g
an
d
p
r
o
ce
s
s
in
g
Ar
ab
ic
co
n
ten
t a
c
r
o
s
s
v
ar
io
u
s
cr
ea
tiv
e
an
d
ac
a
d
em
ic
co
n
tex
t
s
.
4
.
1
.
4
.
Sentim
ent
a
na
ly
s
is
C
h
atGPT
h
as
d
em
o
n
s
tr
ated
ef
f
ec
tiv
en
ess
in
s
en
tim
en
t
an
a
ly
s
is
an
d
o
p
in
io
n
e
x
tr
ac
tio
n
f
o
r
Ar
ab
ic
tex
ts
,
y
ield
in
g
p
r
o
m
is
in
g
r
esu
lts
ac
r
o
s
s
v
ar
io
u
s
ap
p
licatio
n
s
.
I
t
h
as
b
ee
n
u
tili
ze
d
to
an
aly
ze
s
o
cial
m
ed
ia
d
ata,
cu
s
to
m
er
ch
a
r
ac
ter
is
tics
,
p
o
lit
ical
o
p
in
io
n
s
,
an
d
s
er
v
ices.
T
h
ese
ca
p
ab
ilit
ies
s
u
g
g
est
th
at
C
h
atGPT
ca
n
b
e
a
v
alu
ab
le
to
o
l
f
o
r
u
n
d
er
s
tan
d
in
g
p
u
b
lic
s
en
tim
en
t
in
Ar
ab
ic
-
s
p
ea
k
in
g
r
eg
io
n
s
,
esp
ec
ially
wh
en
lar
g
e
v
o
lu
m
e
s
o
f
u
n
s
tr
u
ct
u
r
ed
te
x
t d
ata
ar
e
in
v
o
lv
ed
.
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
S
ystema
tic
r
ev
iew
:
th
e
a
p
p
lica
tio
n
o
f Ch
a
tGP
T o
n
A
r
a
b
ic
l
a
n
g
u
a
g
e
text
p
r
o
ce
s
s
in
g
(
A
li
Mo
u
s
a
A
lS
b
o
u
)
4843
Al
-
T
h
u
b
aity
et
a
l.
[
2
4
]
s
u
g
g
est
th
at
ad
v
an
ce
d
g
en
e
r
ativ
e
m
o
d
els,
p
ar
ticu
lar
ly
GPT
-
4
,
p
e
r
f
o
r
m
r
elativ
ely
well
o
n
Ar
ab
ic
s
en
tim
en
t
an
aly
s
is
task
s
,
ev
en
in
lo
w
-
s
h
o
t
s
ettin
g
s
,
o
u
tp
er
f
o
r
m
in
g
s
o
m
e
f
u
lly
s
u
p
er
v
is
ed
m
o
d
els.
Similar
ly
,
Ald
er
az
i
et
a
l.
[
2
5
]
in
d
icate
th
at
C
h
atGPT
ca
n
class
if
y
s
en
tim
en
t
an
d
to
p
ics
in
Ar
ab
ic
s
o
cial
m
ed
ia,
f
u
n
ctio
n
in
g
alo
n
g
s
id
e
tr
a
d
itio
n
al
m
a
ch
in
e
lear
n
i
n
g
a
n
d
d
ee
p
lear
n
in
g
m
o
d
els.
T
h
es
e
s
tu
d
ies h
ig
h
lig
h
t Ch
atGPT
'
s
p
o
ten
tial in
h
an
d
lin
g
Ar
ab
ic
s
en
tim
en
t a
n
aly
s
is
task
s
ef
f
icien
tly
.
4
.
2
.
RQ
3
:
H
o
w
do
es
Cha
t
G
P
T
perf
o
rm
in
t
er
m
s
o
f
a
cc
ura
cy
a
nd
re
lia
bil
it
y
whe
n
pro
ce
s
s
i
ng
Ara
bic
t
ex
t
?
Stu
d
ies
ass
e
s
s
in
g
C
h
atGPT
's
p
er
f
o
r
m
an
ce
o
n
Ar
a
b
ic
te
x
t
g
en
er
ally
r
ep
o
r
t
h
ig
h
ac
cu
r
ac
y
in
g
en
er
atin
g
g
r
am
m
atica
lly
co
r
r
ec
t
an
d
co
n
tex
t
u
ally
r
elev
an
t
r
esp
o
n
s
es.
Ho
wev
er
,
th
e
co
m
p
lex
ity
o
f
Ar
a
b
ic
m
o
r
p
h
o
lo
g
y
an
d
s
y
n
tax
p
o
s
es
ch
allen
g
es
,
s
o
m
etim
es
lea
d
in
g
to
er
r
o
r
s
in
wo
r
d
ag
r
e
em
en
t
an
d
co
n
tex
t
in
ter
p
r
etatio
n
.
T
h
ese
f
in
d
i
n
g
s
s
u
g
g
est
th
at
wh
ile
C
h
atG
PT
d
em
o
n
s
tr
ates
s
tr
o
n
g
lin
g
u
is
tic
ca
p
ab
ilit
ies,
it
s
till
r
eq
u
ir
es
en
h
an
ce
m
e
n
t
to
m
a
n
ag
e
th
e
in
tr
icac
ies
o
f
Ar
ab
i
c
g
r
am
m
a
r
,
p
ar
ticu
lar
ly
i
n
d
i
alec
tal
an
d
liter
ar
y
co
n
tex
ts
.
4
.
2
.
1
.
Acc
ura
cy
C
h
atGPT
s
h
o
ws
g
r
ea
t
p
o
ten
tial
in
p
r
o
ce
s
s
in
g
Ar
a
b
ic,
b
u
t
i
ts
ac
cu
r
ac
y
v
ar
ies
g
r
ea
tly
d
ep
en
d
in
g
o
n
th
e
task
an
d
co
n
tex
t.
Stu
d
ies
b
y
[
1
6
]
,
[
2
0
]
s
h
o
w
th
at
C
h
atGPT
,
esp
ec
ially
GPT
-
4
,
p
er
f
o
r
m
s
well
o
n
s
p
ec
if
ic
task
s
s
u
ch
as
s
to
r
y
g
en
er
atio
n
,
s
en
tim
en
t
an
aly
s
is
,
an
d
ac
a
d
e
m
ic
tr
an
s
latio
n
s
,
o
f
ten
o
u
tp
er
f
o
r
m
in
g
t
r
ad
itio
n
al
m
o
d
els
s
u
ch
as
Go
o
g
le
T
r
an
s
late
in
m
ain
tain
in
g
s
em
an
tic
i
n
teg
r
ity
an
d
co
h
er
en
ce
.
H
o
wev
er
,
it
n
ee
d
s
h
elp
with
m
o
r
e
s
u
b
tle
o
r
co
m
p
l
ex
task
s
,
s
u
ch
as
ac
cu
r
ately
tr
an
s
latin
g
liter
ar
y
wo
r
k
s
,
cu
ltu
r
al
n
u
a
n
ce
s
,
ex
p
r
ess
io
n
s
,
an
d
d
ialec
ts
.
Fo
cu
s
in
g
o
n
th
ese
s
tr
u
g
g
les,
e
s
p
ec
ially
in
s
p
ec
ialized
f
ield
s
s
u
ch
as
liter
ar
y
tr
an
s
latio
n
,
r
e
s
ea
r
ch
b
y
B
an
im
elh
em
an
d
Am
ay
r
eh
[
1
1
]
Ali a
n
d
Af
za
l
[
1
4
]
s
h
o
w
th
at
C
h
atGPT
f
ail
s
to
ca
p
tu
r
e
cu
ltu
r
al
an
d
em
o
tio
n
al
d
ep
th
f
u
lly
.
I
n
ad
d
itio
n
,
th
e
ac
cu
r
ac
y
o
f
th
e
o
u
tp
u
t
o
f
ten
d
ep
en
d
s
o
n
th
e
q
u
ality
o
f
th
e
in
p
u
t,
as h
ig
h
lig
h
ted
b
y
Nasar
u
d
d
in
[
7
]
,
wh
o
n
o
ted
t
h
at
clea
r
a
n
d
s
tr
u
ctu
r
ed
in
s
tr
u
ctio
n
s
ca
n
im
p
r
o
v
e
C
h
atGPT
’
s
p
er
f
o
r
m
an
ce
in
ed
u
ca
tio
n
al
c
o
n
tex
ts
.
Desp
ite
th
ese
lim
itatio
n
s
,
s
tu
d
ies
s
u
c
h
as
th
o
s
e
b
y
An
tar
[
2
2
]
a
n
d
Al
-
T
h
u
b
aity
et
a
l.
[
2
4
]
s
h
o
w
th
at
f
in
e
-
tu
n
in
g
m
o
d
els
s
u
ch
as
GPT
-
4
im
p
r
o
v
e
ac
cu
r
ac
y
,
esp
ec
ially
in
s
en
tim
en
t
an
aly
s
is
an
d
cr
ea
tiv
e
wr
itin
g
task
s
.
Alth
o
u
g
h
GPT
-
3
.
5
an
d
GPT
-
4
o
u
tp
e
r
f
o
r
m
co
m
m
er
cial
MT
s
y
s
tem
s
wh
en
d
ea
lin
g
with
Ar
ab
ic
d
ialec
ts
,
Kad
ao
u
i
et
a
l.
[
2
6
]
s
h
o
wed
th
at
th
e
y
p
er
f
o
r
m
ed
wo
r
s
e
in
C
A
an
d
MSA.
W
h
ile
C
h
atGPT
s
h
o
ws
p
r
o
m
is
e,
Alk
h
awa
ja
[
1
3
]
an
d
o
th
er
s
p
o
in
t
o
u
t
th
at
its
p
er
f
o
r
m
an
ce
s
till
n
ee
d
s
to
b
e
i
m
p
r
o
v
e
d
f
o
r
h
u
m
a
n
tr
an
s
latio
n
,
esp
ec
ially
in
co
m
p
lex
o
r
c
u
ltu
r
ally
r
ich
te
x
ts
.
C
h
atGPT
’
s
ac
cu
r
ac
y
is
task
-
d
e
p
en
d
en
t,
with
b
etter
r
esu
lts
in
s
tr
u
ctu
r
ed
an
d
f
in
e
-
tu
n
ed
ap
p
licatio
n
s
,
wh
ile
ch
allen
g
es
p
er
s
is
t
in
m
o
r
e
co
m
p
lex
an
d
n
u
a
n
ce
d
lan
g
u
ag
e
task
s
.
4
.
2
.
2
.
Relia
bil
it
y
T
h
e
r
esu
lts
’
s
y
n
th
esis
h
ig
h
li
g
h
ts
th
e
v
ar
y
in
g
r
eliab
ilit
y
o
f
C
h
atGPT
ac
r
o
s
s
d
if
f
er
en
t
task
s
an
d
co
n
tex
ts
,
p
a
r
ticu
lar
ly
i
n
Ar
a
b
ic
lan
g
u
ag
e
p
r
o
ce
s
s
in
g
.
C
h
atGPT
g
en
er
ally
p
er
f
o
r
m
s
w
ell
in
well
-
d
ef
i
n
ed
,
s
tr
u
ctu
r
ed
task
s
,
b
u
t
its
r
eliab
ilit
y
d
ec
r
ea
s
es
s
ig
n
if
ican
tly
in
m
o
r
e
c
o
m
p
lex
,
n
u
an
ce
d
,
an
d
cu
ltu
r
e
-
d
ep
en
d
en
t
s
ce
n
ar
io
s
.
T
h
is
u
n
d
er
s
co
r
es
th
e
n
ee
d
f
o
r
f
u
r
th
er
d
ev
elo
p
m
en
t
an
d
im
p
r
o
v
em
en
t.
C
h
a
tGPT
s
h
o
ws
h
ig
h
r
eliab
ilit
y
wh
en
s
u
p
p
o
r
ted
b
y
clea
r
in
s
tr
u
ctio
n
s
an
d
g
u
i
d
an
ce
f
r
o
m
teac
h
er
s
in
e
d
u
c
atio
n
al
s
ettin
g
s
,
as
d
em
o
n
s
tr
ated
b
y
Nasar
u
d
d
in
[
7
]
an
d
B
u
tg
e
r
eit
et
a
l.
[
8
]
,
with
p
o
s
itiv
e
s
tu
d
en
t
f
ee
d
b
ac
k
co
n
f
ir
m
in
g
its
ef
f
ec
tiv
en
ess
.
Similar
ly
,
L
elep
ar
y
et
a
l.
[
9
]
f
o
u
n
d
th
at
C
h
atGPT
r
eliab
ly
s
u
p
p
o
r
ts
in
d
ep
en
d
en
t
lan
g
u
ag
e
lear
n
in
g
.
T
h
ese
f
in
d
in
g
s
s
u
g
g
est
th
at
wh
ile
C
h
atG
PT
m
ay
n
o
t
f
u
lly
r
e
p
lace
tr
ad
itio
n
a
l
in
s
tr
u
ctio
n
,
it
ca
n
ef
f
ec
tiv
ely
co
m
p
lem
en
t
it
wh
en
th
o
u
g
h
tf
u
lly
in
teg
r
ate
d
in
to
ed
u
ca
tio
n
al
s
tr
ateg
ies.
Fo
r
tr
an
s
latio
n
task
s
,
alth
o
u
g
h
th
er
e
ar
e
m
in
o
r
s
h
o
r
tco
m
in
g
s
in
co
m
p
lex
lan
g
u
ag
e
p
air
s
.
AlAf
n
an
an
d
Alk
h
aw
aja
[
1
2
]
,
[
1
3
]
n
o
te
th
at
C
h
atGPT
p
er
f
o
r
m
s
r
eliab
ly
f
o
r
g
en
e
r
al
an
d
f
o
r
m
al
tr
an
s
latio
n
s
,
b
u
t
r
eliab
ilit
y
d
ec
lin
es
in
m
o
r
e
n
u
an
ce
d
an
d
cu
ltu
r
ally
s
en
s
itiv
e
task
s
,
s
u
ch
as
f
ilm
tr
an
s
latio
n
s
[
1
4
]
an
d
r
esis
tan
ce
liter
atu
r
e
Ob
eid
at
an
d
J
ar
ad
at
[
1
5
]
,
wh
er
e
C
h
atGPT
s
tr
u
g
g
les to
m
ain
tain
cu
ltu
r
al
a
n
d
em
o
tio
n
al
d
ep
th
.
Stu
d
ies
An
tar
[
2
2
]
an
d
Al
-
T
h
u
b
aity
et
a
l.
[
2
4
]
in
d
icate
t
h
at
C
h
atGPT
h
an
d
les
MSA
r
eliab
ly
b
u
t
b
ec
o
m
es
less
r
eliab
le
with
d
i
alec
tal
v
ar
iatio
n
s
d
u
e
to
lim
ited
tr
ain
in
g
d
ata.
Sey
id
o
v
[
5
]
also
em
p
h
asizes
th
e
im
p
ac
t
o
f
d
ialec
ts
an
d
cu
ltu
r
al
co
n
tex
ts
o
n
th
e
m
o
d
el’
s
r
eliab
ilit
y
in
r
ea
l
-
wo
r
ld
ap
p
licatio
n
s
.
I
n
s
en
tim
en
t
an
aly
s
is
an
d
ac
ad
em
ic
tr
an
s
latio
n
,
Alg
h
a
m
d
i
et
a
l.
[
1
0
]
a
n
d
Mo
h
s
en
[
1
6
]
h
ig
h
lig
h
t
th
at
C
h
atGPT
,
esp
ec
ially
GPT
-
4
,
s
h
o
ws
s
tr
o
n
g
r
eliab
il
ity
an
d
o
u
tp
er
f
o
r
m
s
o
th
e
r
m
o
d
els
in
th
ese
d
o
m
ai
n
s
.
Ho
wev
er
,
its
r
eliab
ilit
y
d
ec
lin
es
wh
en
f
ac
ed
with
co
m
p
lex
o
r
s
p
ec
ialized
tex
ts
th
at
r
eq
u
ir
e
d
ee
p
er
co
n
tex
tu
al
u
n
d
er
s
tan
d
i
n
g
,
as
in
[
1
1
]
,
[
2
5
]
.
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
.
5
,
Octo
b
e
r
20
25
:
4
8
3
7
-
4
8
4
7
4844
4
.
3
.
RQ
3
:
Wha
t
a
re
t
he
ma
in
cha
lleng
es
a
nd
lim
it
a
t
io
ns
a
s
s
o
cia
t
ed
wit
h
u
s
ing
Ch
a
t
G
P
T
f
o
r
Ara
bic
la
ng
ua
g
e
t
ex
t
?
T
h
e
s
tu
d
ies
co
llectiv
ely
h
ig
h
lig
h
t
s
ev
er
al
k
ey
ch
allen
g
es
an
d
lim
itatio
n
s
o
f
AI
m
o
d
els
lik
e
C
h
atGPT
in
p
r
o
ce
s
s
in
g
Ar
ab
ic
lan
g
u
a
g
e
an
d
r
elate
d
task
s
.
A
s
ig
n
if
ican
t
is
s
u
e
i
s
th
e
n
ee
d
f
o
r
m
o
r
e
h
ig
h
-
q
u
ality
,
an
n
o
tated
Ar
a
b
ic
d
ata
an
d
co
m
p
r
eh
en
s
iv
e
d
atasets
en
co
m
p
ass
in
g
th
e
f
u
ll
r
an
g
e
o
f
d
ialec
tal
an
d
lin
g
u
is
tic
n
u
an
ce
s
,
af
f
ec
tin
g
th
ese
m
o
d
e
ls
'
p
er
f
o
r
m
an
ce
[
5
]
,
[
6
]
.
T
h
e
v
ast
d
ialec
tal
d
iv
er
s
ity
with
in
Ar
ab
ic
also
p
o
s
es
a
ch
allen
g
e,
as
AI
m
o
d
els
s
tr
u
g
g
le
to
p
r
o
ce
s
s
an
d
g
en
er
ate
tex
t
ac
r
o
s
s
d
if
f
er
en
t
d
ialec
ts
ac
cu
r
ately
[
5
]
,
[
6
]
,
[
2
0
]
,
[
2
2
]
,
[
2
4
]
.
T
h
is
lim
itatio
n
h
ig
h
lig
h
ts
th
e
u
r
g
e
n
cy
o
f
d
ev
elo
p
in
g
s
tan
d
a
r
d
ized
d
at
asets
an
d
tr
ain
in
g
p
r
o
to
co
ls
to
en
s
u
r
e
f
air
an
d
e
f
f
ec
tiv
e
p
er
f
o
r
m
an
ce
ac
r
o
s
s
t
h
e
Ar
ab
ic
-
s
p
ea
k
in
g
wo
r
ld
.
I
n
ad
d
itio
n
,
th
e
ab
ilit
y
to
u
n
d
e
r
s
tan
d
an
d
ca
p
tu
r
e
c
u
ltu
r
al
n
u
a
n
ce
s
is
lim
ited
,
o
f
ten
r
esu
ltin
g
in
tr
an
s
latio
n
in
ac
c
u
r
ac
ies,
esp
ec
ially
in
cu
ltu
r
ally
s
en
s
itiv
e
co
n
tex
ts
[
5
]
,
[
1
3
]
,
[
1
5
]
,
[
1
8
]
,
[
1
9
]
.
An
o
th
er
p
r
o
m
i
n
en
t
is
s
u
e
is
t
h
e
d
e
p
en
d
e
n
ce
o
n
u
s
er
in
p
u
t;
th
e
q
u
ality
o
f
AI
-
g
en
e
r
ated
o
u
tp
u
ts
is
h
ig
h
ly
in
f
lu
en
ce
d
b
y
h
o
w
w
ell
u
s
er
s
cr
af
t
th
eir
p
r
o
m
p
ts
.
T
h
is
d
ep
en
d
en
ce
u
n
d
er
s
co
r
e
s
th
e
n
ee
d
f
o
r
u
s
er
ed
u
ca
tio
n
an
d
s
y
s
tem
im
p
r
o
v
e
m
en
t
[
7
]
,
[
1
1
]
.
Fu
r
th
er
m
o
r
e,
AI
-
d
r
iv
en
lan
g
u
ag
e
lear
n
in
g
t
o
o
ls
r
ed
u
ce
ess
en
tial
h
u
m
an
i
n
ter
ac
tio
n
,
wh
ich
is
n
ec
ess
ar
y
f
o
r
d
ev
elo
p
i
n
g
n
u
an
ce
d
u
n
d
er
s
tan
d
in
g
an
d
cr
itical
th
in
k
in
g
s
k
ills
[
9
]
.
AI
'
s
p
er
f
o
r
m
an
ce
in
tr
an
s
latio
n
task
s
r
em
ain
s
s
u
b
o
p
tim
al,
p
ar
ticu
lar
ly
in
d
o
m
ain
-
s
p
ec
if
ic
f
ield
s
s
u
ch
as
le
g
al,
m
ed
ical,
an
d
s
cien
tific
tex
ts
,
with
tr
an
s
latio
n
q
u
ality
o
f
ten
d
ep
en
d
i
n
g
o
n
p
r
o
m
p
t
s
en
s
itiv
ity
[
1
1
]
,
[
1
3
]
–
[
1
5
]
.
AI
m
o
d
els
also
s
tr
u
g
g
le
w
ith
co
m
p
lex
lin
g
u
is
tic
s
tr
u
ctu
r
es,
id
io
m
atic
ex
p
r
ess
io
n
s
,
an
d
s
p
ec
ialized
v
o
ca
b
u
lar
y
,
esp
ec
ially
in
d
ip
lo
m
atic
an
d
ac
ad
em
ic
c
o
n
tex
ts
[
1
2
]
,
[
1
6
]
,
[
1
8
]
,
[
1
9
]
,
[
2
1
]
.
T
h
e
u
s
e
o
f
s
y
n
t
h
etic
d
ata
in
tr
o
d
u
ce
s
er
r
o
r
s
an
d
u
n
n
atu
r
a
l
s
en
ten
ce
s
tr
u
ctu
r
es,
r
eq
u
ir
i
n
g
ca
r
ef
u
l
cu
r
atio
n
t
o
m
ain
tain
p
er
f
o
r
m
a
n
ce
.
T
h
is
n
e
ed
f
o
r
ca
r
ef
u
l
cu
r
atio
n
h
ig
h
lig
h
ts
th
e
im
p
o
r
tan
c
e
o
f
d
ata
q
u
ality
i
n
AI
m
o
d
el
tr
ain
in
g
[
1
0
]
.
Dis
cr
ep
an
cies
b
etwe
en
ev
alu
atio
n
m
etr
ics
also
co
m
p
licate
th
e
ass
es
s
m
en
t
o
f
AI
m
o
d
els
[
1
0
]
.
So
m
e
s
tu
d
ies
id
e
n
tifie
d
lim
itatio
n
s
in
AI
s
y
s
te
m
s
'
ad
ap
tatio
n
to
n
o
n
-
E
n
g
lis
h
-
s
p
ea
k
in
g
co
n
te
x
ts
,
s
u
ch
as
Ar
ab
ic,
d
u
e
to
d
if
f
er
en
ce
s
in
c
u
ltu
r
al
n
o
r
m
s
an
d
lin
g
u
is
tic
f
o
r
m
s
[
8
]
.
C
o
m
p
u
t
atio
n
al
co
n
s
tr
ain
ts
f
u
r
th
er
lim
it
th
e
ex
p
lo
r
atio
n
o
f
lar
g
er
,
m
o
r
e
p
o
wer
f
u
l
m
o
d
e
ls
,
esp
ec
ially
in
d
ialec
tal
Ar
ab
ic
tex
t
g
en
er
atio
n
[
2
0
]
,
[
2
2
]
.
I
n
ter
m
s
o
f
Ar
ab
ic
Sig
n
L
an
g
u
a
g
e,
lim
ited
o
n
lin
e
r
eso
u
r
ce
s
h
in
d
er
ac
c
u
r
ate
tr
an
s
latio
n
s
b
etwe
en
Ar
ab
ic
Sig
n
L
an
g
u
ag
e
a
n
d
s
p
o
k
en
Ar
a
b
ic
[
1
7
]
.
C
h
atGPT
also
f
ac
es
ch
allen
g
es
in
g
en
er
atin
g
c
o
m
p
lex
t
ex
ts
,
s
u
ch
as
Ar
ab
ic
p
o
etr
y
,
r
eq
u
ir
in
g
ad
v
an
ce
d
la
n
g
u
a
g
e
m
o
d
elin
g
to
en
s
u
r
e
th
em
atic
an
d
s
ty
lis
tic
co
h
er
en
ce
[
2
1
]
.
Ad
d
itio
n
ally
,
o
m
itti
n
g
g
r
am
m
atica
l
an
d
lex
ical
co
h
e
s
io
n
elem
en
ts
ca
n
af
f
ec
t
th
e
c
o
h
er
en
ce
o
f
AI
-
g
en
er
ated
s
u
m
m
ar
ies
in
c
o
m
p
lex
tex
ts
[
2
3
]
.
L
im
ited
d
atasets
in
s
o
m
e
s
tu
d
ies
r
estrict
th
e
g
en
e
r
aliza
b
ilit
y
o
f
f
in
d
in
g
s
,
p
a
r
ticu
lar
ly
in
r
ea
l
-
w
o
r
ld
s
ce
n
ar
io
s
in
v
o
l
v
in
g
lo
n
g
er
,
m
o
r
e
c
o
m
p
lex
tex
ts
[
1
3
]
,
[
2
5
]
.
AI
s
tr
u
g
g
les
with
ca
p
tu
r
in
g
th
e
cu
ltu
r
al
d
ep
t
h
a
n
d
id
eo
lo
g
ical
elem
en
ts
in
r
esis
t
an
ce
liter
atu
r
e,
o
f
ten
d
is
to
r
ti
n
g
tr
an
s
latio
n
s
,
with
s
o
m
e
ex
h
ib
itin
g
d
ef
o
r
m
in
g
ten
d
en
cies
lik
e
r
atio
n
aliza
tio
n
an
d
th
e
d
estru
cti
o
n
o
f
lin
g
u
i
s
tic
p
atter
n
s
[
1
5
]
.
Fin
ally
,
AI
g
en
er
ativ
e
m
o
d
els
ar
e
s
till
u
n
d
er
d
e
v
elo
p
e
d
in
p
r
o
d
u
cin
g
h
ig
h
-
q
u
ality
s
en
tim
en
t
d
ata
in
d
ialec
tal
Ar
ab
ic,
es
p
ec
ially
f
o
r
n
eu
tr
al
s
en
tim
en
ts
[
2
4
]
.
Fig
u
r
e
4
s
u
m
m
ar
izes
th
e
m
o
s
t
f
r
eq
u
e
n
tly
r
ep
o
r
ted
ch
allen
g
e
s
en
co
u
n
ter
ed
w
h
en
ap
p
ly
in
g
C
h
atGPT
to
Ar
ab
ic
lan
g
u
a
g
e
tex
t
p
r
o
ce
s
s
in
g
.
Am
o
n
g
th
e
m
o
s
t
cit
ed
is
s
u
es
ar
e
d
ialec
tal
v
ar
iat
io
n
(
r
ep
o
r
ted
in
8
s
tu
d
ies),
th
e
lack
o
f
h
ig
h
-
q
u
ality
an
d
co
m
p
r
e
h
en
s
iv
e
Ar
ab
ic
d
atasets
(
7
s
tu
d
ies),
a
n
d
cu
ltu
r
al
n
u
a
n
ce
m
is
in
ter
p
r
etatio
n
(
6
s
tu
d
ies).
Oth
er
ch
allen
g
es
in
clu
d
e
p
r
o
m
p
t
s
en
s
itiv
ity
,
d
if
f
icu
lty
tr
an
s
latin
g
co
m
p
lex
tex
ts
—
s
u
ch
as
liter
ar
y
o
r
d
o
m
ain
-
s
p
ec
if
ic
co
n
ten
t
—
an
d
r
ed
u
ce
d
ac
cu
r
ac
y
in
s
p
ec
ialized
f
ield
s
lik
e
leg
al
an
d
m
ed
ical
tr
an
s
latio
n
.
T
h
ese
lim
itatio
n
s
h
ig
h
lig
h
t th
e
n
ee
d
f
o
r
r
ich
er
d
atasets
,
b
etter
f
in
e
-
tu
n
i
n
g
tech
n
iq
u
es,
an
d
cu
ltu
r
ally
awa
r
e
m
o
d
el
tr
ain
in
g
to
im
p
r
o
v
e
C
h
atGPT
'
s
p
er
f
o
r
m
an
ce
in
Ar
a
b
ic
NL
P task
s
.
Fig
u
r
e
4
.
R
ep
o
r
ted
ch
allen
g
es in
C
h
atGPT
Ar
ab
ic
tex
t p
r
o
ce
s
s
in
g
ac
r
o
s
s
s
tu
d
ies
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
S
ystema
tic
r
ev
iew
:
th
e
a
p
p
lica
tio
n
o
f Ch
a
tGP
T o
n
A
r
a
b
ic
l
a
n
g
u
a
g
e
text
p
r
o
ce
s
s
in
g
(
A
li
Mo
u
s
a
A
lS
b
o
u
)
4845
4
.
4
.
RQ
4
:
Wha
t
f
uture
dire
ct
io
ns
ca
n e
nh
a
nce
t
he
utiliz
a
t
io
n o
f
Cha
t
G
P
T
f
o
r
Ara
bi
c
t
ex
t
?
T
h
e
s
y
n
th
esis
o
f
r
esu
lts
h
i
g
h
lig
h
ts
s
ev
er
al
f
u
tu
r
e
d
ir
e
ctio
n
s
th
at
co
u
ld
en
h
an
ce
C
h
atGPT
's
ef
f
ec
tiv
en
ess
in
Ar
ab
ic
lan
g
u
ag
e
p
r
o
ce
s
s
in
g
.
On
e
o
f
th
e
k
ey
ar
ea
s
o
f
f
o
cu
s
is
im
p
r
o
v
in
g
d
ata
q
u
ality
.
Dev
elo
p
in
g
m
o
r
e
co
m
p
r
e
h
en
s
iv
e
d
atasets
th
at
en
co
m
p
ass
th
e
f
u
ll
r
an
g
e
o
f
Ar
ab
ic
d
ia
lects
an
d
lin
g
u
is
tic
n
u
an
ce
s
is
ess
en
tial
f
o
r
en
h
a
n
cin
g
th
e
m
o
d
el'
s
p
er
f
o
r
m
a
n
ce
.
T
h
is
in
clu
d
es
ad
d
r
ess
in
g
th
e
m
o
d
el'
s
cu
r
r
e
n
t
lim
itatio
n
s
in
r
ec
o
g
n
izin
g
a
n
d
p
r
o
ce
s
s
in
g
d
if
f
er
en
t
d
ialec
ts
,
wh
ich
co
u
ld
m
a
k
e
it
m
o
r
e
v
er
s
atile
an
d
r
eliab
le
f
o
r
a
b
r
o
ad
er
au
d
ien
ce
.
A
d
d
itio
n
ally
,
f
o
s
ter
in
g
AI
d
ev
el
o
p
m
en
t
th
at
in
c
o
r
p
o
r
ates
cu
l
tu
r
al
co
n
te
x
t,
a
n
d
s
en
s
itiv
ity
will
h
elp
m
o
d
els
lik
e
C
h
atGPT
b
etter
u
n
d
er
s
tan
d
an
d
p
r
o
ce
s
s
Ar
ab
ic
lan
g
u
ag
e
with
g
r
ea
te
r
ac
cu
r
ac
y
.
Hu
m
an
-
AI
c
o
llab
o
r
atio
n
is
a
n
o
th
er
c
r
itical
d
ir
ec
tio
n
f
o
r
f
u
tu
r
e
r
esear
ch
.
R
ath
er
th
an
r
ep
lacin
g
ed
u
ca
to
r
s
,
AI
s
h
o
u
l
d
b
e
s
ee
n
as
a
to
o
l
th
at
s
u
p
p
o
r
ts
an
d
co
m
p
lem
en
ts
h
u
m
an
teac
h
in
g
m
eth
o
d
s
.
E
n
c
o
u
r
a
g
in
g
th
is
co
llab
o
r
atio
n
r
eq
u
ir
es
b
o
t
h
tech
n
o
lo
g
ical
im
p
r
o
v
em
en
ts
an
d
teac
h
er
tr
ain
in
g
to
en
s
u
r
e
AI
s
y
s
tem
s
alig
n
with
ed
u
ca
tio
n
al
g
o
als
an
d
c
u
ltu
r
al
ex
p
ec
tatio
n
s
.
T
h
is
will
r
eq
u
ir
e
tr
ain
in
g
f
o
r
Ar
ab
ic
la
n
g
u
ag
e
teac
h
er
s
to
ef
f
ec
tiv
ely
u
s
e
C
h
atGPT
,
p
a
r
ticu
lar
ly
in
f
o
r
m
u
latin
g
p
r
ec
is
e
an
d
clea
r
co
m
m
an
d
s
to
en
s
u
r
e
th
at
AI
-
g
en
e
r
ated
co
n
ten
t
alig
n
s
with
th
eir
ed
u
ca
tio
n
al
g
o
als.
AI
s
h
o
u
ld
also
b
e
b
alan
ce
d
with
tr
ad
itio
n
a
l
lear
n
in
g
m
eth
o
d
s
,
m
ain
tain
in
g
th
e
im
p
o
r
ta
n
ce
o
f
h
u
m
an
in
ter
ac
tio
n
a
n
d
cr
itical
th
in
k
in
g
in
lan
g
u
ag
e
ac
q
u
is
itio
n
.
I
n
ter
m
s
o
f
tr
an
s
latio
n
task
s
,
i
m
p
r
o
v
i
n
g
C
h
atGPT
’
s
co
n
tex
tu
al
u
n
d
er
s
tan
d
in
g
an
d
NL
P
ca
p
ab
ilit
ies
will
b
e
cr
u
cial,
p
ar
ticu
lar
ly
f
o
r
co
m
p
lex
o
r
h
ig
h
-
s
tak
es
tr
an
s
l
atio
n
s
th
at
in
v
o
lv
e
c
u
ltu
r
al
o
r
id
io
m
atic
n
u
a
n
ce
s
.
Fu
tu
r
e
wo
r
k
s
h
o
u
ld
f
o
c
u
s
o
n
f
in
e
-
tu
n
in
g
m
o
d
els
f
o
r
s
p
ec
if
ic
g
en
r
es,
s
u
ch
as
liter
ar
y
a
n
d
ec
o
n
o
m
ic
tex
ts
,
wh
ile
also
r
ef
in
in
g
AI
m
o
d
el
s
to
p
r
eser
v
e
th
e
id
eo
lo
g
ical
d
ep
th
an
d
em
o
tio
n
al
r
eso
n
an
ce
in
co
m
p
lex
tex
ts
lik
e
r
esis
tan
ce
liter
atu
r
e.
An
o
th
er
ar
ea
o
f
f
o
c
u
s
is
ex
p
an
d
in
g
d
atasets
f
o
r
Ar
ab
ic
d
ialec
ts
an
d
s
ig
n
lan
g
u
a
g
e,
en
s
u
r
in
g
th
at
AI
m
o
d
els ca
n
h
an
d
le
a
wid
er
v
ar
iety
o
f
lin
g
u
i
s
tic
co
n
tex
ts
with
g
r
ea
ter
ac
cu
r
ac
y
.
E
r
r
o
r
an
aly
s
is
an
d
m
o
d
el
r
ef
i
n
em
en
t
ar
e
also
ess
en
tial
f
o
r
im
p
r
o
v
in
g
C
h
atGPT
’
s
p
er
f
o
r
m
an
ce
in
Ar
ab
ic
d
ialec
ts
an
d
co
m
p
lex
lin
g
u
is
tic
task
s
.
R
esear
ch
er
s
s
h
o
u
ld
co
n
d
u
ct
t
h
o
r
o
u
g
h
er
r
o
r
an
aly
s
es
to
id
en
tif
y
lim
itatio
n
s
an
d
d
ev
elo
p
m
o
r
e
ad
v
an
ce
d
f
in
e
-
tu
n
i
n
g
s
tr
ateg
ie
s
,
wh
ich
co
u
ld
en
h
a
n
ce
th
e
m
o
d
el'
s
p
er
f
o
r
m
an
ce
in
b
o
th
tex
t
g
en
er
atio
n
an
d
s
en
tim
en
t
an
aly
s
is
task
s
.
Fu
r
th
er
m
o
r
e,
c
o
n
tin
u
e
d
tech
n
i
ca
l
r
ef
in
em
en
ts
i
n
lan
g
u
ag
e
m
o
d
els,
p
ar
ticu
la
r
ly
in
h
an
d
lin
g
s
p
ec
ialized
v
o
ca
b
u
lar
y
an
d
ac
ad
e
m
ic
s
tr
u
ctu
r
es,
will
h
elp
b
r
id
g
e
th
e
g
ap
b
etwe
en
h
u
m
an
an
d
m
ac
h
in
e
tr
an
s
latio
n
q
u
ality
.
T
h
e
p
u
b
licatio
n
tr
en
d
in
d
icat
es
a
r
ap
id
ly
g
r
o
win
g
in
ter
est
in
u
s
in
g
C
h
atGPT
m
o
d
els
t
o
p
r
o
ce
s
s
Ar
ab
ic
tex
ts
,
as
we
f
o
u
n
d
a
n
in
cr
ea
s
e
in
th
e
n
u
m
b
er
o
f
ar
tic
les
o
v
er
tim
e,
with
an
in
cr
ea
s
e
in
2
0
2
4
co
m
p
a
r
ed
to
2
0
2
3
an
d
2
0
2
2
,
n
o
tin
g
th
at
th
e
s
tu
d
y
ap
p
lied
to
p
u
b
licatio
n
s
o
v
er
th
e
p
ast
f
o
u
r
y
ea
r
s
.
Ho
wev
er
,
d
u
e
to
t
h
e
r
elativ
ely
s
m
all
n
u
m
b
er
o
f
ar
ticles
in
clu
d
ed
in
th
is
r
ev
iew
,
wh
ich
ca
n
b
e
ex
p
lain
ed
b
y
th
e
n
ee
d
f
o
r
m
o
r
e
r
esear
ch
an
d
th
e
f
ac
t
th
at
th
e
s
u
b
ject
o
f
s
tu
d
y
is
r
elativ
ely
n
ew,
its
co
n
ce
p
ts
h
av
e
o
n
ly
em
er
g
ed
in
r
ec
en
t
y
ea
r
s
.
Ov
er
all,
r
e
v
iewin
g
th
e
2
1
ar
ticles h
elp
ed
a
n
s
wer
th
e
f
o
u
r
r
esear
c
h
q
u
esti
o
n
s
.
T
h
e
r
esu
lts
o
f
th
is
r
ev
iew
h
ig
h
lig
h
t
th
e
g
r
ea
t
p
o
ten
tial
o
f
C
h
atGPT
in
Ar
ab
ic
tex
t
p
r
o
ce
s
s
in
g
,
esp
ec
ially
in
e
d
u
ca
tio
n
al
to
o
l
s
,
m
ac
h
in
e
tr
an
s
latio
n
,
tex
t
g
en
er
atio
n
,
an
d
s
en
tim
en
t
an
al
y
s
is
.
T
h
e
co
m
b
in
e
d
r
esu
lts
o
f
th
ese
s
tu
d
ies
p
o
in
t
to
an
u
r
g
e
n
t
n
ee
d
f
o
r
im
p
r
o
v
em
en
ts
in
d
ata
q
u
ality
,
d
iv
er
s
ity
o
f
tr
ain
in
g
d
ata
,
an
d
co
m
p
u
tatio
n
al
r
eso
u
r
ce
s
to
en
h
a
n
ce
C
h
atGPT
'
s
p
er
f
o
r
m
an
ce
in
h
an
d
lin
g
Ar
ab
i
c
lan
g
u
a
g
e
task
s
.
Ad
d
r
ess
in
g
th
ese
is
s
u
es
co
u
ld
lead
to
m
o
r
e
ac
cu
r
ate
an
d
r
el
iab
le
AI
m
o
d
els
lik
e
C
HAT
G
PT
th
at
u
n
d
er
s
tan
d
an
d
g
en
er
ate
Ar
ab
ic
b
etter
ac
r
o
s
s
d
if
f
er
en
t
d
ialec
ts
an
d
co
n
tex
ts
.
T
h
is
co
m
p
r
eh
en
s
iv
e
a
n
aly
s
is
s
h
o
ws
th
at
d
esp
ite
AI
m
o
d
els
lik
e
C
h
atGPT
's
tr
em
en
d
o
u
s
p
o
ten
tial,
t
h
ey
f
ac
e
s
ev
er
al
lan
g
u
ag
e
p
r
o
ce
s
s
in
g
ch
allen
g
es,
in
cr
ed
ib
ly
c
o
m
p
lex
Ar
ab
ic
d
ia
lects,
cu
ltu
r
al
d
if
f
er
e
n
ce
s
,
an
d
s
p
ec
ialized
d
o
m
ain
s
.
T
h
ese
lim
itatio
n
s
h
ig
h
lig
h
t
th
e
n
ee
d
f
o
r
f
u
r
th
er
r
esear
ch
a
n
d
d
ev
elo
p
m
e
n
t to
im
p
r
o
v
e
A
I
'
s
ab
ilit
y
to
u
n
d
er
s
tan
d
an
d
p
r
o
ce
s
s
Ar
ab
ic.
Fu
tu
r
e
wo
r
k
s
h
o
u
ld
b
u
ild
o
n
t
h
e
ch
allen
g
es
id
en
tifie
d
in
th
e
r
ev
iewe
d
s
tu
d
ies
b
y
p
r
io
r
itizin
g
s
ev
er
al
k
ey
r
esear
ch
d
ir
ec
tio
n
s
.
First,
th
er
e
is
a
clea
r
n
ee
d
t
o
d
e
v
e
lo
p
an
d
p
u
b
licly
s
h
ar
e
la
r
g
e
-
s
ca
le,
h
ig
h
-
q
u
ality
Ar
ab
ic
co
r
p
o
r
a
th
at
i
n
clu
d
e
d
iv
er
s
e
d
ialec
ts
,
f
o
r
m
al
m
o
d
er
n
s
tan
d
ar
d
Ar
a
b
ic
(
MSA)
,
an
d
u
n
d
er
r
ep
r
esen
ted
lin
g
u
is
tic
v
ar
ieties
s
u
ch
as
Ar
ab
ic
Sig
n
L
a
n
g
u
a
g
e.
D
o
in
g
s
o
will
d
ir
ec
tly
ad
d
r
ess
th
e
cu
r
r
en
t
lim
itatio
n
s
i
n
tr
ain
in
g
d
ata
th
at
h
in
d
er
m
o
d
el
ac
cu
r
ac
y
an
d
r
eliab
ilit
y
.
Seco
n
d
,
f
in
e
-
t
u
n
in
g
a
n
d
cu
s
t
o
m
izin
g
g
en
e
r
ativ
e
m
o
d
els
lik
e
C
h
atGPT
f
o
r
d
o
m
ain
-
s
p
ec
if
ic
task
s
-
s
u
ch
as
m
ed
ical
tr
an
s
latio
n
,
leg
al
ter
m
in
o
lo
g
y
,
o
r
liter
ar
y
n
u
an
ce
-
s
h
o
u
ld
b
e
ex
p
lo
r
ed
th
r
o
u
g
h
tr
an
s
f
er
lear
n
in
g
a
n
d
tar
g
eted
r
ein
f
o
r
ce
m
e
n
t
tech
n
iq
u
es.
As
m
u
ltip
le
s
tu
d
ies
in
th
is
r
ev
iew
in
d
icate
,
th
is
wo
u
ld
h
elp
im
p
r
o
v
e
p
er
f
o
r
m
an
ce
in
c
o
m
p
lex
o
r
cu
ltu
r
ally
s
en
s
itiv
e
co
n
tex
ts
.
T
h
ir
d
,
f
u
t
u
r
e
r
esear
ch
s
h
o
u
ld
also
in
v
esti
g
ate
in
teg
r
atin
g
cu
ltu
r
al
awa
r
en
ess
in
to
m
o
d
el
tr
ain
in
g
,
p
ar
ticu
lar
ly
f
o
r
s
en
tim
en
t
an
a
ly
s
is
an
d
tr
an
s
latio
n
o
f
id
io
m
atic
ex
p
r
ess
io
n
s
,
wh
ich
ar
e
p
r
o
n
e
to
d
is
to
r
tio
n
i
n
Ar
ab
ic
NL
P.
Mo
r
eo
v
er
,
s
ch
o
lar
s
s
h
o
u
ld
d
e
v
elo
p
s
tan
d
ar
d
i
ze
d
ev
alu
atio
n
f
r
a
m
ewo
r
k
s
t
ailo
r
ed
f
o
r
Ar
ab
ic
g
en
er
ativ
e
task
s
to
c
o
n
s
is
ten
tly
b
en
ch
m
ar
k
m
o
d
el
o
u
tp
u
ts
,
esp
ec
ially
ac
r
o
s
s
d
ialec
ts
an
d
g
en
r
es.
Fin
ally
,
f
u
tu
r
e
s
tu
d
ies
m
ay
ex
p
lo
r
e
h
u
m
an
-
AI
co
llab
o
r
atio
n
in
ed
u
c
atio
n
al
co
n
tex
ts
,
em
p
h
asizin
g
tr
ain
in
g
ed
u
ca
t
o
r
s
to
f
o
r
m
u
late
p
r
ec
is
e
p
r
o
m
p
ts
th
at
im
p
r
o
v
e
C
h
atGPT
’
s
clas
s
r
o
o
m
u
tili
ty
with
o
u
t
co
m
p
r
o
m
is
in
g
p
ed
ag
o
g
ical
q
u
ality
.
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
.
5
,
Octo
b
e
r
20
25
:
4
8
3
7
-
4
8
4
7
4846
5.
CO
NCLU
SI
O
N
T
h
is
s
y
s
tem
atic
r
ev
iew
h
ig
h
li
g
h
ts
th
e
p
o
ten
tial
o
f
C
h
atGPT
in
Ar
ab
ic
lan
g
u
ag
e
p
r
o
ce
s
s
in
g
ac
r
o
s
s
v
ar
io
u
s
ap
p
licatio
n
s
,
i
n
clu
d
in
g
ed
u
ca
tio
n
,
tr
an
s
latio
n
,
a
n
d
s
en
tim
en
t
an
aly
s
is
.
W
h
ile
C
h
at
GPT
d
em
o
n
s
tr
ates
h
ig
h
ac
c
u
r
ac
y
an
d
r
eliab
ilit
y
in
s
tr
u
ctu
r
ed
task
s
,
ch
allen
g
e
s
r
em
ain
in
d
ea
lin
g
with
Ar
a
b
ic'
s
lin
g
u
is
tic
an
d
cu
ltu
r
al
co
m
p
lex
ities
,
esp
ec
ially
in
d
ialec
tal
v
ar
iatio
n
s
an
d
s
p
ec
ialized
t
r
an
s
latio
n
s
.
Ad
d
r
ess
in
g
th
es
e
ch
allen
g
es
will
b
e
cr
u
cial
f
o
r
en
h
an
cin
g
th
e
u
tili
ty
o
f
AI
s
y
s
tem
s
in
Ar
ab
ic
NL
P,
m
ak
in
g
th
em
m
o
r
e
r
o
b
u
s
t
an
d
cu
ltu
r
ally
ad
ap
tiv
e.
T
h
e
f
in
d
in
g
s
o
f
th
is
s
y
s
tem
atic
r
ev
iew
h
ig
h
lig
h
t
n
ew
ar
ea
s
o
f
r
esear
ch
th
at
n
ee
d
f
u
r
th
er
im
p
r
o
v
e
m
en
t
an
d
f
u
tu
r
e
wo
r
k
.
Fu
tu
r
e
r
esear
ch
s
h
o
u
ld
f
o
cu
s
o
n
im
p
r
o
v
in
g
d
ata
r
eso
u
r
ce
s
an
d
q
u
ality
,
en
h
an
cin
g
AI
m
o
d
el
p
er
f
o
r
m
a
n
ce
,
in
teg
r
atin
g
A
I
to
o
ls
with
h
u
m
an
teac
h
in
g
m
eth
o
d
s
,
e
n
h
an
cin
g
c
u
ltu
r
al
a
n
d
d
ialec
tal
s
en
s
itiv
ity
,
an
d
ex
p
lo
r
in
g
n
ew
ap
p
licatio
n
s
in
Ar
ab
ic
lan
g
u
a
g
e
ed
u
ca
tio
n
an
d
ac
ce
s
s
ib
ilit
y
.
B
y
ad
d
r
ess
in
g
th
ese
g
ap
s
,
r
esear
c
h
er
s
ca
n
u
n
leash
th
e
f
u
ll
p
o
te
n
tial
o
f
C
h
atGPT
an
d
s
im
ilar
m
o
d
els
f
o
r
Ar
ab
ic
NL
P,
u
ltima
tely
co
n
tr
ib
u
tin
g
t
o
m
o
r
e
ac
c
u
r
ate,
r
elia
b
le,
an
d
cu
ltu
r
ally
r
elev
a
n
t A
I
lan
g
u
ag
e
p
r
o
ce
s
s
in
g
to
o
ls
.
ACK
NO
WL
E
DG
E
M
E
NT
S
T
h
e
au
th
o
r
s
th
an
k
Un
iv
er
s
iti
Ma
lay
s
ia
T
er
en
g
g
an
u
(
UM
T
)
f
o
r
s
u
p
p
o
r
tin
g
th
is
r
esear
ch
.
W
e
ex
ten
d
o
u
r
th
an
k
s
to
th
e
f
ac
u
lty
m
e
m
b
er
s
an
d
co
lleag
u
es
in
th
e
Facu
lty
o
f
C
o
m
p
u
ter
Scien
ce
an
d
Ma
th
em
atics
at
UM
T
f
o
r
th
eir
in
v
alu
ab
le
g
u
i
d
an
ce
.
Sp
ec
ial
t
h
an
k
s
g
o
t
o
a
ll
th
e
r
esear
ch
er
s
w
h
o
s
e
wo
r
k
co
n
tr
ib
u
ted
t
o
th
e
s
y
s
tem
atic
r
ev
iew
an
d
to
th
o
s
e
wh
o
p
r
o
v
i
d
ed
in
s
ig
h
tf
u
l
co
m
m
en
ts
an
d
s
u
g
g
esti
o
n
s
th
r
o
u
g
h
o
u
t
th
e
r
esear
ch
p
r
o
ce
s
s
.
RE
F
E
R
E
NC
E
S
[
1
]
“
A
r
a
b
i
c
sp
e
a
k
i
n
g
c
o
u
n
t
r
i
e
s,
”
Wo
r
l
d
A
t
l
a
s
.
h
t
t
p
s:
/
/
w
w
w
.
w
o
r
l
d
a
t
l
a
s.c
o
m
/
a
r
t
i
c
l
e
s
/
a
r
a
b
i
c
-
s
p
e
a
k
i
n
g
-
c
o
u
n
t
r
i
e
s
.
h
t
ml
(
a
c
c
e
ss
e
d
A
u
g
.
1
5
,
2
0
2
4
)
.
[
2
]
J.
F
e
r
d
u
sh
,
M
.
B
e
g
u
m,
a
n
d
S
.
T
.
H
o
s
sai
n
,
“
C
h
a
t
G
P
T
a
n
d
c
l
i
n
i
c
a
l
d
e
c
i
si
o
n
su
p
p
o
r
t
:
s
c
o
p
e
,
a
p
p
l
i
c
a
t
i
o
n
,
a
n
d
l
i
mi
t
a
t
i
o
n
s,”
An
n
a
l
s o
f
Bi
o
m
e
d
i
c
a
l
E
n
g
i
n
e
e
r
i
n
g
,
v
o
l
.
5
2
,
n
o
.
5
,
p
p
.
1
1
1
9
–
1
1
2
4
,
J
u
l
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
0
7
/
s1
0
4
3
9
-
023
-
0
3
3
2
9
-
4.
[
3
]
S
.
A
L
-
S
a
r
a
y
r
e
h
,
A
.
M
o
h
a
m
e
d
,
a
n
d
K
.
S
h
a
a
l
a
n
,
“
C
h
a
l
l
e
n
g
e
s
a
n
d
s
o
l
u
t
i
o
n
s
f
o
r
A
r
a
b
i
c
n
a
t
u
r
a
l
l
a
n
g
u
a
g
e
p
r
o
c
e
ssi
n
g
i
n
s
o
c
i
a
l
med
i
a
,
”
i
n
S
m
a
rt
I
n
n
o
v
a
t
i
o
n
,
S
y
st
e
m
s
a
n
d
T
e
c
h
n
o
l
o
g
i
e
s
,
v
o
l
.
3
5
8
,
S
p
r
i
n
g
e
r
N
a
t
u
r
e
S
i
n
g
a
p
o
r
e
,
2
0
2
3
,
p
p
.
2
9
3
–
3
0
2
.
[
4
]
H
.
H
.
M
u
s
t
a
f
a
,
N
.
R
.
D
a
r
w
i
s
h
,
a
n
d
H
.
A
.
H
e
f
n
y
,
“
A
u
t
o
ma
t
i
c
s
p
e
e
c
h
e
mo
t
i
o
n
r
e
c
o
g
n
i
t
i
o
n
:
a
s
y
st
e
ma
t
i
c
l
i
t
e
r
a
t
u
r
e
r
e
v
i
e
w
,
”
I
n
t
e
r
n
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
S
p
e
e
c
h
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
2
7
,
n
o
.
1
,
p
p
.
2
6
7
–
2
8
5
,
M
a
r
.
2
0
2
4
,
d
o
i
:
1
0
.
1
0
0
7
/
s
1
0
7
7
2
-
0
2
4
-
1
0
0
9
6
-
7.
[
5
]
R
.
S
e
y
i
d
o
v
,
“
A
r
a
b
i
c
l
a
n
g
u
a
g
e
p
r
o
c
e
ssi
n
g
:
c
u
r
r
e
n
t
s
t
a
t
u
s
a
n
d
f
u
t
u
r
e
p
r
o
s
p
e
c
t
s
o
f
a
r
t
i
f
i
c
i
a
l
i
n
t
e
l
l
i
g
e
n
c
e
,
”
J
o
u
r
n
a
l
o
f
N
a
m
i
b
i
a
n
S
t
u
d
i
e
s
:
H
i
st
o
ry
Po
l
i
t
i
c
s
C
u
l
t
u
re
,
v
o
l
.
4
1
,
p
p
.
2
2
4
–
2
4
0
,
A
p
r
.
2
0
2
4
,
d
o
i
:
1
0
.
5
9
6
7
0
/
j
w
s
z
y
0
3
7
.
[
6
]
Y
.
M
o
h
a
me
d
,
Z.
A
.
R
a
z
a
k
,
S
.
I
smai
l
,
M
.
H
.
I
b
r
a
h
i
m,
a
n
d
Z.
M
.
I
sa,
“
C
h
a
t
G
P
T
-
A
I
t
e
c
h
n
o
l
o
g
y
i
n
t
e
a
c
h
i
n
g
A
r
a
b
i
c
f
o
r
s
p
e
c
i
f
i
c
p
u
r
p
o
ses
f
r
o
m t
h
e
A
r
a
b
i
c
e
x
p
e
r
t
’
s
p
e
r
sp
e
c
t
i
v
e
,
”
Al
-
Q
a
n
a
t
i
r:
I
n
t
e
rn
a
t
i
o
n
a
l
J
o
u
r
n
a
l
o
f
I
s
l
a
m
i
c
S
t
u
d
i
e
s
,
v
o
l
.
3
2
,
n
o
.
2
,
p
p
.
2
1
3
–
2
2
5
,
2
0
2
3
.
[
7
]
N
.
N
a
s
a
r
u
d
d
i
n
,
“
U
si
n
g
C
h
a
t
G
P
T
i
n
t
e
a
c
h
i
n
g
A
r
a
b
i
c
a
s
a
f
o
r
e
i
g
n
l
a
n
g
u
a
g
e
,
”
Ar
a
b
i
y
a
t
u
n
a
:
J
u
r
n
a
l
Ba
h
a
sa
Ar
a
b
,
v
o
l
.
8
,
n
o
.
1
,
p
.
1
,
M
a
y
2
0
2
4
,
d
o
i
:
1
0
.
2
9
2
4
0
/
j
b
a
.
v
8
i
1
.
9
4
1
3
.
[
8
]
L.
B
u
t
g
e
r
e
i
t
,
H
.
M
a
r
t
i
n
u
s,
a
n
d
M
.
M
.
A
b
u
g
o
sse
i
sa,
“
P
r
o
f
P
i
:
t
u
t
o
r
i
n
g
mat
h
e
m
a
t
i
c
s
i
n
A
r
a
b
i
c
l
a
n
g
u
a
g
e
u
si
n
g
G
P
T
-
4
a
n
d
W
h
a
t
sa
p
p
,
”
i
n
I
N
E
S
2
0
2
3
-
2
7
t
h
I
EE
E
I
n
t
e
r
n
a
t
i
o
n
a
l
C
o
n
f
e
re
n
c
e
o
n
I
n
t
e
l
l
i
g
e
n
t
E
n
g
i
n
e
e
ri
n
g
S
y
s
t
e
m
s
2
0
2
3
,
Pr
o
c
e
e
d
i
n
g
s
,
Ju
l
.
2
0
2
3
,
p
p
.
1
6
1
–
1
6
4
,
d
o
i
:
1
0
.
1
1
0
9
/
I
N
ES5
9
2
8
2
.
2
0
2
3
.
1
0
2
9
7
8
2
4
.
[
9
]
H
.
L.
Le
l
e
p
a
r
y
,
R
.
R
a
c
h
maw
a
t
i
,
B
.
N
.
Za
n
i
,
a
n
d
K
.
M
a
h
a
r
j
a
n
,
“
C
h
a
t
G
P
T
:
o
p
p
o
r
t
u
n
i
t
i
e
s
a
n
d
c
h
a
l
l
e
n
g
e
s
i
n
t
h
e
l
e
a
r
n
i
n
g
p
r
o
c
e
ss
o
f
A
r
a
b
i
c
l
a
n
g
u
a
g
e
i
n
h
i
g
h
e
r
e
d
u
c
a
t
i
o
n
,
”
J
o
u
rn
a
l
I
n
t
e
rn
a
t
i
o
n
a
l
o
f
L
i
n
g
u
a
a
n
d
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
2
,
n
o
.
1
,
p
p
.
1
0
–
2
2
,
Ju
l
.
2
0
2
3
,
d
o
i
:
1
0
.
5
5
8
4
9
/
j
i
l
t
e
c
h
.
v
2
i
1
.
4
3
9
.
[
1
0
]
E.
A
.
A
l
g
h
a
m
d
i
,
J
.
Za
k
r
a
o
u
i
,
a
n
d
F
.
A
.
A
b
a
n
m
y
,
“
D
o
m
a
i
n
a
d
a
p
t
a
t
i
o
n
f
o
r
A
r
a
b
i
c
m
a
c
h
i
n
e
t
r
a
n
sl
a
t
i
o
n
:
f
i
n
a
n
c
i
a
l
t
e
x
t
s
a
s
a
c
a
s
e
st
u
d
y
,
”
A
p
p
l
i
e
d
S
c
i
e
n
c
e
s (
S
w
i
t
z
e
rl
a
n
d
)
,
v
o
l
.
1
4
,
n
o
.
1
6
,
p
.
7
0
8
8
,
A
u
g
.
2
0
2
4
,
d
o
i
:
1
0
.
3
3
9
0
/
a
p
p
1
4
1
6
7
0
8
8
.
[
1
1
]
O
.
B
a
n
i
m
e
l
h
e
m
a
n
d
W
.
A
ma
y
r
e
h
,
“
I
s
C
h
a
t
G
P
T
a
g
o
o
d
E
n
g
l
i
sh
t
o
A
r
a
b
i
c
m
a
c
h
i
n
e
t
r
a
n
s
l
a
t
i
o
n
t
o
o
l
?
,
”
i
n
2
0
2
3
1
4
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
I
n
f
o
rm
a
t
i
o
n
a
n
d
C
o
m
m
u
n
i
c
a
t
i
o
n
S
y
s
t
e
m
s,
I
C
I
C
S
2
0
2
3
,
N
o
v
.
2
0
2
3
,
p
p
.
1
–
6
,
d
o
i
:
1
0
.
1
1
0
9
/
I
C
I
C
S
6
0
5
2
9
.
2
0
2
3
.
1
0
3
3
0
5
2
5
.
[
1
2
]
M
.
A
.
A
l
a
f
n
a
n
,
“
L
a
r
g
e
l
a
n
g
u
a
g
e
m
o
d
e
l
s
a
s
c
o
m
p
u
t
a
t
i
o
n
a
l
l
i
n
g
u
i
s
t
i
c
s
t
o
o
l
s
:
a
c
o
m
p
a
r
a
t
i
v
e
a
n
a
l
y
s
i
s
o
f
C
h
a
t
G
P
T
a
n
d
G
o
o
g
l
e
m
a
c
h
i
n
e
t
r
a
n
s
l
a
t
i
o
n
s
,
”
J
o
u
r
n
a
l
o
f
A
r
t
i
f
i
c
i
a
l
I
n
t
e
l
l
i
g
e
n
c
e
a
n
d
T
e
c
h
n
o
l
o
g
y
,
v
o
l
.
5
,
p
p
.
2
0
–
3
2
,
J
u
n
.
2
0
2
5
,
d
o
i
:
1
0
.
3
7
9
6
5
/
j
a
i
t
.
2
0
2
4
.
0
5
4
9
.
[
1
3
]
L.
A
l
k
h
a
w
a
j
a
,
“
U
n
v
e
i
l
i
n
g
t
h
e
n
e
w
f
r
o
n
t
i
e
r
:
C
h
a
t
G
P
T
-
3
p
o
w
e
r
e
d
t
r
a
n
s
l
a
t
i
o
n
f
o
r
A
r
a
b
i
c
-
En
g
l
i
s
h
l
a
n
g
u
a
g
e
p
a
i
r
s,”
T
h
e
o
r
y
a
n
d
Pra
c
t
i
c
e
i
n
L
a
n
g
u
a
g
e
S
t
u
d
i
e
s
,
v
o
l
.
1
4
,
n
o
.
2
,
p
p
.
3
4
7
–
3
5
7
,
F
e
b
.
2
0
2
4
,
d
o
i
:
1
0
.
1
7
5
0
7
/
t
p
l
s
.
1
4
0
2
.
0
5
.
[
1
4
]
S
.
A
l
i
a
n
d
N
.
A
f
z
a
l
,
“
A
m
u
l
t
i
d
i
m
e
n
si
o
n
a
l
a
n
a
l
y
si
s
o
f
h
u
ma
n
a
n
d
C
h
a
t
G
P
T
-
g
e
n
e
r
a
t
e
d
E
n
g
l
i
s
h
t
r
a
n
s
l
a
t
i
o
n
s
o
f
A
r
a
b
i
c
f
i
l
m,
”
W
o
rl
d
J
o
u
rn
a
l
o
f
En
g
l
i
s
h
L
a
n
g
u
a
g
e
,
v
o
l
.
1
4
,
n
o
.
4
,
p
p
.
6
3
2
–
6
4
1
,
J
u
n
.
2
0
2
4
,
d
o
i
:
1
0
.
5
4
3
0
/
w
j
e
l
.
v
1
4
n
4
p
6
3
2
.
[
1
5
]
M
.
M
.
O
b
e
i
d
a
t
a
n
d
M
.
A
.
Jara
d
a
t
,
“
A
r
t
i
f
i
c
i
a
l
i
n
t
e
l
l
i
g
e
n
c
e
a
c
c
u
r
a
c
y
i
n
t
r
a
n
sl
a
t
i
n
g
r
e
si
s
t
a
n
c
e
l
i
t
e
r
a
t
u
r
e
f
r
o
m
A
r
a
b
i
c
i
n
t
o
E
n
g
l
i
sh
:
G
o
o
g
l
e
Tr
a
n
sl
a
t
e
a
n
d
C
h
a
t
G
P
T
a
s
a
mo
d
e
l
,
”
R
e
se
a
rc
h
J
o
u
rn
a
l
i
n
A
d
v
a
n
c
e
d
H
u
m
a
n
i
t
i
e
s
,
v
o
l
.
5
,
n
o
.
2
,
p
p
.
4
5
–
6
2
,
2
0
2
4
,
d
o
i
:
1
0
.
5
8
2
5
6
/
9
y
z
4
d
x
7
9
.
[
1
6
]
M
.
A
.
M
o
h
s
e
n
,
“
A
r
t
i
f
i
c
i
a
l
i
n
t
e
l
l
i
g
e
n
c
e
i
n
a
c
a
d
e
mi
c
t
r
a
n
sl
a
t
i
o
n
:
a
c
o
m
p
a
r
a
t
i
v
e
st
u
d
y
o
f
l
a
r
g
e
l
a
n
g
u
a
g
e
m
o
d
e
l
s
a
n
d
G
o
o
g
l
e
Tr
a
n
s
l
a
t
e
,
”
Ps
y
c
h
o
l
i
n
g
u
i
st
i
c
s
,
v
o
l
.
3
5
,
n
o
.
2
,
p
p
.
1
3
4
–
1
5
6
,
A
p
r
.
2
0
2
4
,
d
o
i
:
1
0
.
3
1
4
7
0
/
2
3
0
9
-
1
7
9
7
-
2
0
2
4
-
35
-
2
-
134
-
1
5
6
.
[
1
7
]
N
.
S
h
a
h
i
n
a
n
d
L.
I
smai
l
,
“
C
h
a
t
G
P
T
,
l
e
t
u
s
c
h
a
t
si
g
n
l
a
n
g
u
a
g
e
:
e
x
p
e
r
i
m
e
n
t
s,
a
r
c
h
i
t
e
c
t
u
r
a
l
e
l
e
m
e
n
t
s,
c
h
a
l
l
e
n
g
e
s
a
n
d
r
e
sea
r
c
h
d
i
r
e
c
t
i
o
n
s,
”
i
n
2
0
2
3
I
n
t
e
rn
a
t
i
o
n
a
l
S
y
m
p
o
s
i
u
m
o
n
N
e
t
w
o
r
k
s,
C
o
m
p
u
t
e
rs
a
n
d
C
o
m
m
u
n
i
c
a
t
i
o
n
s,
I
S
N
C
C
2
0
2
3
,
O
c
t
.
2
0
2
3
,
p
p
.
1
–
7
,
d
o
i
:
1
0
.
1
1
0
9
/
I
S
N
C
C
5
8
2
6
0
.
2
0
2
3
.
1
0
3
2
3
9
7
4
.
[
1
8
]
M
.
H
.
A
l
K
a
a
b
i
,
N
.
M
.
A
l
q
b
a
i
l
a
t
,
A
.
B
a
d
a
h
,
I
.
A
.
I
smai
l
,
a
n
d
K
.
B
.
H
i
c
h
a
m,
“
Ex
a
mi
n
i
n
g
t
h
e
c
u
l
t
u
r
a
l
c
o
n
n
o
t
a
t
i
o
n
s
i
n
h
u
m
a
n
a
n
d
mac
h
i
n
e
t
r
a
n
sl
a
t
i
o
n
s:
a
c
o
r
p
u
s s
t
u
d
y
o
f
N
a
g
u
i
b
M
a
h
f
o
u
z
’
s Z
u
q
ā
q
a
l
-
M
i
d
a
,
”
J
o
u
rn
a
l
o
f
L
a
n
g
u
a
g
e
T
e
a
c
h
i
n
g
a
n
d
R
e
se
a
rc
h
,
v
o
l
.
1
5
,
n
o
.
3
,
p
p
.
7
0
7
–
7
1
8
,
M
a
y
2
0
2
4
,
d
o
i
:
1
0
.
1
7
5
0
7
/
j
l
t
r
.
1
5
0
3
.
0
3
.
[
1
9
]
F
.
K
h
o
s
h
a
f
a
h
,
“
C
h
a
t
G
P
T
f
o
r
A
r
a
b
i
c
-
En
g
l
i
sh
t
r
a
n
s
l
a
t
i
o
n
:
e
v
a
l
u
a
t
i
n
g
t
h
e
a
c
c
u
r
a
c
y
,
”
R
e
se
a
rc
h
S
q
u
a
r
e
(
Pre
p
ri
n
t
)
,
p
p
.
1
–
1
8
,
A
p
r
.
2
0
2
3
,
d
o
i
:
1
0
.
2
1
2
0
3
/
r
s
.
3
.
r
s
-
2
8
1
4
1
5
4
/
v
2
.
Evaluation Warning : The document was created with Spire.PDF for Python.