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.
16
,
No
.
5
,
Octo
b
er
20
26
,
p
p
.
2
7
8
2
~
2
7
9
4
I
SS
N:
2088
-
8
7
0
8
,
DOI
: 1
0
.
1
1
5
9
1
/ijece.
v
16
i
5
.
pp
2
7
8
2
-
2
7
9
4
2782
J
o
ur
na
l ho
m
ep
a
g
e
:
h
ttp
:
//ij
ec
e.
ia
esco
r
e.
co
m
Desig
n
science
res
ea
rch in
d
ev
elo
ping
a relig
io
us cha
tbot bas
ed
o
n Bulug
h
a
l
-
M
a
ra
m
Aris T
j
a
hy
a
nto
,
I
rm
a
s
a
ri
H
a
f
idz,
F
a
iza
l J
o
ha
n At
let
ik
o
D
e
p
a
r
t
me
n
t
o
f
I
n
f
o
r
m
a
t
i
o
n
S
y
st
e
ms,
F
a
c
u
l
t
y
o
f
I
n
t
e
l
l
i
g
e
n
t
El
e
c
t
r
o
n
i
c
s a
n
d
I
n
f
o
r
mat
i
c
s T
e
c
h
n
o
l
o
g
y
,
I
n
st
i
t
u
t
Te
k
n
o
l
o
g
i
S
e
p
u
l
u
h
N
o
p
e
m
b
e
r
,
S
u
r
a
b
a
y
a
,
I
n
d
o
n
e
s
i
a
Art
icle
I
nfo
AB
S
T
RAC
T
A
r
ticle
his
to
r
y:
R
ec
eiv
ed
Au
g
1
5
,
2
0
2
4
R
ev
is
ed
J
u
n
3
,
2
0
2
6
Acc
ep
ted
Au
g
1
9
,
2
0
2
6
Ch
a
tb
o
ts
h
a
v
e
re
c
e
n
tl
y
g
a
i
n
e
d
sig
n
ifi
c
a
n
t
p
o
p
u
larity
.
F
o
r
in
sta
n
c
e
,
Ch
a
tG
P
T
h
a
s
b
e
c
o
m
e
a
p
re
fe
rre
d
to
o
l
fo
r
m
a
n
y
in
d
iv
i
d
u
a
ls
se
e
k
in
g
in
sta
n
t
a
n
sw
e
rs
with
o
u
t
re
ly
i
n
g
o
n
h
u
m
a
n
re
sp
o
n
se
s.
Th
is
imm
e
d
iac
y
se
ts
c
h
a
tb
o
ts
a
p
a
rt
fro
m
b
o
o
k
s,
wh
ich
re
q
u
ire
u
se
rs
to
se
a
rc
h
fo
r
in
f
o
rm
a
ti
o
n
m
a
n
u
a
ll
y
.
Th
is
ti
m
e
-
c
o
n
su
m
in
g
p
ro
c
e
ss
d
o
e
s
n
o
t
a
li
g
n
with
m
il
len
n
ials'
p
re
fe
re
n
c
e
fo
r
c
o
n
v
e
n
ien
c
e
a
n
d
e
fficie
n
c
y
.
S
tu
d
y
in
g
h
a
d
it
h
in
d
e
p
e
n
d
e
n
tl
y
u
sin
g
th
e
Bu
lu
g
h
al
-
M
a
ra
m
b
o
o
k
d
e
m
a
n
d
s
c
o
n
si
d
e
ra
b
le
ti
m
e
a
n
d
e
ffo
rt
.
T
h
e
li
m
it
e
d
u
se
o
f
n
a
tu
ra
l
lan
g
u
a
g
e
p
ro
c
e
ss
in
g
tec
h
n
o
l
o
g
ies
in
re
li
g
i
o
u
s
c
h
a
tb
o
ts
re
stricts
th
e
ir
a
b
il
i
ty
to
h
a
n
d
le
c
o
m
p
lex
i
n
q
u
iri
e
s
e
ffe
c
ti
v
e
ly
.
A
c
h
a
tb
o
t
c
a
p
a
b
le
o
f
a
n
sw
e
rin
g
h
a
d
it
h
-
re
lat
e
d
q
u
e
stio
n
s
c
o
u
l
d
g
re
a
tl
y
a
ss
ist
th
e
p
u
b
li
c
in
st
u
d
y
in
g
h
a
d
it
h
tex
ts
b
y
p
ro
v
id
i
n
g
d
irec
t
re
sp
o
n
se
s
wit
h
o
u
t
e
x
ten
siv
e
se
a
rc
h
in
g
.
Th
is
c
h
a
tb
o
t
wa
s
d
e
sig
n
e
d
fo
r
we
b
b
ro
ws
e
rs,
u
ti
l
izin
g
d
e
e
p
lea
rn
in
g
a
s
it
s
c
o
re
tec
h
n
o
lo
g
y
.
Th
is
re
se
a
rc
h
led
to
th
e
d
e
v
e
lo
p
m
e
n
t
o
f
a
c
h
a
tb
o
t
p
r
o
t
o
ty
p
e
f
o
r
lea
rn
in
g
h
a
d
it
h
fr
o
m
Bu
lu
g
h
a
l
-
M
a
ra
m
.
B
u
il
t
u
si
n
g
t
h
e
d
e
sig
n
sc
ien
c
e
re
se
a
rc
h
(DSR)
m
e
th
o
d
o
l
o
g
y
,
th
e
p
ro
t
o
t
y
p
e
a
c
h
iev
e
s
a
n
in
ten
t
re
c
o
g
n
it
i
o
n
ra
te
(IRR)
o
f
8
6
.
8
2
%
.
Ho
we
v
e
r,
it
s
c
a
p
a
b
il
it
ies
a
re
b
e
lo
w
th
e
BERT
m
o
d
e
l,
d
e
m
o
n
stra
ti
n
g
a
stro
n
g
a
b
il
it
y
to
a
c
c
u
ra
tely
i
n
terp
re
t
u
se
r
q
u
e
stio
n
s a
n
d
sta
tem
e
n
ts.
K
ey
w
o
r
d
s
:
C
h
atb
o
t d
esig
n
I
n
ten
t r
ec
o
g
n
itio
n
Ma
ch
in
e
lear
n
in
g
Natu
r
al
lan
g
u
ag
e
p
r
o
ce
s
s
in
g
Pro
p
h
etic
h
ad
ith
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
:
Ar
is
T
jah
y
an
to
Dep
ar
tm
en
t o
f
I
n
f
o
r
m
atio
n
Sy
s
tem
s
,
Facu
lty
o
f
I
n
tellig
en
t E
lectr
o
n
ics an
d
I
n
f
o
r
m
atics T
ec
h
n
o
lo
g
y
,
I
n
s
titu
t
T
ek
n
o
lo
g
i Sep
u
lu
h
No
p
em
b
er
Su
r
ab
ay
a,
I
n
d
o
n
esia
E
m
ail: a
r
is
tj@
its
.
ac
.
id
1.
I
NT
RO
D
UCT
I
O
N
I
n
th
is
d
ec
ad
e,
ch
atb
o
ts
h
av
e
em
er
g
ed
as
a
p
o
wer
f
u
l
to
o
l
to
im
p
r
o
v
e
cu
s
to
m
er
s
er
v
ice
,
s
im
p
lify
b
u
s
in
ess
p
r
o
ce
s
s
es,
an
d
m
ak
e
h
u
m
an
life
ea
s
ier
with
t
h
e
h
el
p
o
f
tech
n
o
lo
g
y
.
L
e
v
er
ag
in
g
a
r
tific
ial
in
tellig
en
ce
an
d
n
atu
r
al
lan
g
u
ag
e
p
r
o
ce
s
s
in
g
,
ch
atb
o
ts
h
av
e
tr
a
n
s
ce
n
d
ed
th
eir
o
r
ig
in
s
in
to
v
er
s
atile
to
o
ls
ca
p
ab
le
o
f
u
n
d
er
s
tan
d
i
n
g
a
n
d
r
esp
o
n
d
in
g
to
u
s
er
q
u
esti
o
n
s
with
asto
n
is
h
in
g
p
r
ec
is
io
n
.
Ste
m
m
in
g
f
r
o
m
ea
r
ly
d
ev
elo
p
m
e
n
ts
in
a
r
tific
ial
in
te
llig
en
ce
(
AI
)
an
d
n
at
u
r
al
lan
g
u
ag
e
p
r
o
ce
s
s
in
g
(
NL
P
)
,
ch
at
b
o
ts
ca
n
ac
c
u
r
ately
u
n
d
er
s
tan
d
a
n
d
r
esp
o
n
d
to
h
u
m
an
q
u
esti
o
n
s
.
Ap
p
licatio
n
s
o
f
ch
atb
o
ts
in
clu
d
e
cu
s
to
m
er
s
er
v
ice,
ed
u
ca
tio
n
,
h
ea
lth
s
er
v
ices,
an
d
r
elig
i
o
n
,
s
h
o
win
g
t
h
e
in
c
r
ea
s
in
g
im
p
o
r
t
an
ce
o
f
ch
atb
o
t
tech
n
o
lo
g
y
in
m
ak
in
g
h
u
m
a
n
life
ea
s
ier
[
1
]
,
[
2
]
.
C
h
atb
o
ts
h
av
e
also
ev
o
lv
ed
f
r
o
m
s
im
p
le
r
u
le
-
b
ased
s
y
s
tem
s
to
s
o
p
h
is
ticate
d
to
o
ls
d
ev
elo
p
ed
u
s
in
g
m
ac
h
in
e
lear
n
in
g
to
tr
an
s
f
o
r
m
er
s
-
b
ased
tech
n
o
lo
g
y
.
S
ev
er
al
ch
atb
o
ts
in
th
e
r
elig
io
u
s
s
ec
to
r
ar
e
s
tar
tin
g
to
em
er
g
e,
f
o
r
e
x
am
p
le,
R
ab
b
i A
n
y
tim
e,
Haji
an
d
Um
r
a,
Ask
Mo
r
m
o
n
,
an
d
s
o
o
n
[
3
]
.
W
ith
r
elig
io
u
s
ch
atb
o
ts
,
it
is
h
o
p
ed
th
at
th
e
y
ca
n
p
r
o
v
id
e
g
u
id
an
ce
,
an
s
wer
th
e
o
lo
g
ical
q
u
esti
o
n
s
,
an
d
p
r
o
v
id
e
em
o
tio
n
al
s
u
p
p
o
r
t
to
th
o
s
e
in
n
ee
d
.
O
n
e
o
f
th
e
b
en
ef
its
o
f
r
elig
io
u
s
ch
atb
o
ts
is
th
e
ab
ilit
y
to
p
r
o
v
id
e
s
p
ir
itu
al
g
u
id
a
n
ce
a
n
d
em
o
tio
n
al
s
u
p
p
o
r
t.
Ho
wev
er
,
s
ev
er
al
is
s
u
es
n
ee
d
to
b
e
f
ix
e
d
,
s
u
ch
as
co
n
ce
r
n
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
Desig
n
s
cien
ce
r
esea
r
ch
in
d
ev
elo
p
in
g
a
r
elig
io
u
s
ch
a
tb
o
t b
a
s
ed
o
n
…
(
A
r
is
Tja
h
ya
n
to
)
2783
ab
o
u
t
th
e
ac
cu
r
ac
y
o
f
th
e
in
f
o
r
m
atio
n
s
u
p
p
lied
b
y
ch
at
b
o
ts
,
u
s
er
p
r
iv
ac
y
[
4
]
,
an
d
eth
ical
q
u
esti
o
n
s
ab
o
u
t
h
o
w
AI
ca
n
b
e
u
s
ed
in
s
o
ciety
[
5
]
,
esp
ec
ially
f
o
r
r
elig
io
u
s
p
u
r
p
o
s
es.
So
m
e
p
eo
p
le
h
av
e
ex
p
r
ess
ed
co
n
ce
r
n
s
th
at
u
s
in
g
ch
atb
o
ts
co
u
ld
r
ep
lace
tr
ad
itio
n
al
f
o
r
m
s
o
f
r
elig
io
u
s
g
u
id
an
ce
,
wh
ich
s
o
m
e
s
ay
ar
e
m
o
r
e
ef
f
ec
tiv
e
in
p
r
o
v
id
i
n
g
em
o
tio
n
al
s
u
p
p
o
r
t a
n
d
b
u
il
d
in
g
c
o
m
m
u
n
ity
.
E
v
en
th
o
u
g
h
ch
atb
o
t
tech
n
o
lo
g
y
h
as
a
d
v
an
ce
d
s
o
m
u
ch
,
w
h
en
d
esig
n
in
g
it,
it
is
n
ec
ess
ar
y
to
in
v
o
lv
e
u
s
er
s
in
th
e
p
r
o
p
er
in
ter
ac
tio
n
p
r
o
ce
s
s
at
th
e
ex
p
licate
p
r
o
b
le
m
s
tag
e.
E
x
p
licatin
g
p
r
o
b
lem
s
u
s
in
g
p
r
o
to
ty
p
in
g
tech
n
iq
u
es
in
v
o
lv
es
u
s
er
s
f
r
o
m
th
e
s
tar
t
to
u
n
d
er
s
tan
d
th
ei
r
n
ee
d
s
,
ex
p
lo
r
in
g
p
o
ten
tial
c
h
atb
o
t
f
u
n
ctio
n
ality
,
an
d
r
e
f
in
in
g
th
e
p
r
o
b
lem
s
tate
m
en
t.
E
x
is
tin
g
ch
atb
o
ts
o
f
ten
s
tr
u
g
g
le
to
u
n
d
er
s
tan
d
u
s
er
in
ten
t,
ca
u
s
in
g
u
s
er
s
to
b
ec
o
m
e
f
r
u
s
tr
ated
ac
cu
r
atel
y
.
T
o
d
ev
elo
p
an
ar
tifa
ct
as
a
u
s
er
-
o
r
ien
ted
c
h
atb
o
t
p
r
o
to
ty
p
e,
we
h
av
e
s
ev
er
al
g
o
als
to
an
s
wer
th
e
f
o
llo
win
g
r
esear
ch
q
u
esti
o
n
s
:
i)
W
h
at
f
ea
tu
r
es
d
o
u
s
er
s
wan
t
in
a
ch
atb
o
t
to
f
ac
ilit
ate
r
elig
io
u
s
s
tu
d
ies
r
elate
d
to
h
a
d
ith
lear
n
in
g
?
ii)
Ho
w
ca
n
a
ch
atb
o
t
p
r
o
to
ty
p
e
b
e
d
esig
n
ed
to
p
r
o
v
id
e
o
p
tim
al
p
er
f
o
r
m
an
ce
wh
e
n
d
ev
el
o
p
in
g
a
ch
atb
o
t f
o
r
h
ad
ith
lear
n
i
n
g
s
tu
d
ies?
T
h
e
m
o
tiv
atio
n
f
o
r
th
is
r
esear
ch
lies
in
its
p
o
ten
tial
to
a
d
v
an
ce
th
e
f
ield
o
f
ch
at
b
o
t
d
esig
n
an
d
in
cr
ea
s
e
u
s
er
p
ar
ticip
atio
n
in
t
h
e
d
esig
n
p
r
o
ce
s
s
.
B
y
g
ain
in
g
d
ee
p
er
i
n
s
ig
h
ts
in
to
u
s
er
s
'
n
ee
d
s
wh
en
s
tu
d
y
in
g
r
elig
io
u
s
tex
ts
,
u
n
d
er
s
tan
d
in
g
th
eir
in
ten
t,
an
d
en
s
u
r
in
g
d
ia
lo
g
u
e
c
o
h
er
en
ce
,
th
is
s
tu
d
y
s
ee
k
s
to
cr
ea
te
m
o
r
e
ef
f
ec
tiv
e
a
n
d
u
s
er
-
f
r
ie
n
d
ly
co
n
v
er
s
atio
n
al
a
g
en
ts
.
T
h
e
f
in
d
i
n
g
s
f
r
o
m
t
h
is
r
esear
ch
ca
n
in
f
o
r
m
t
h
e
d
esig
n
a
n
d
im
p
lem
en
tatio
n
o
f
ch
atb
o
ts
ac
r
o
s
s
v
ar
io
u
s
d
o
m
ain
s
,
ex
ten
d
in
g
b
e
y
o
n
d
r
elig
io
u
s
ap
p
lic
atio
n
s
.
Ultim
ately
,
in
co
r
p
o
r
atin
g
u
s
er
in
p
u
t
d
u
r
in
g
th
e
d
esig
n
p
h
ase
ca
n
im
p
r
o
v
e
ch
atb
o
t c
ap
a
b
ilit
ies.
T
h
is
s
tu
d
y
ex
p
l
o
r
es
u
s
er
s
'
n
ee
d
s
co
n
ce
r
n
i
n
g
r
elig
i
o
u
s
ch
atb
o
ts
,
p
ar
ticu
lar
ly
f
o
r
lear
n
in
g
h
ad
ith
tex
ts
.
T
h
e
o
b
jectiv
e
is
to
tr
a
n
s
f
o
r
m
tr
ad
itio
n
al,
s
tatic
b
o
o
k
s
in
to
a
m
o
r
e
in
ter
ac
tiv
e
a
n
d
en
g
ag
in
g
lear
n
in
g
ex
p
er
ien
ce
.
Sp
ec
if
ically
,
th
is
r
esear
ch
aim
s
to
d
ev
elo
p
a
ch
atb
o
t
ca
p
ab
le
o
f
ac
cu
r
ately
in
ter
p
r
etin
g
u
s
er
in
ten
t
an
d
d
eliv
er
i
n
g
co
n
tex
tu
ally
r
elev
an
t,
r
ea
l
-
tim
e
r
esp
o
n
s
es b
ased
o
n
h
ad
ith
s
o
u
r
ce
s
f
r
o
m
B
u
lu
g
h
al
-
Ma
r
a
m
.
B
u
lu
g
h
al
-
Ma
r
am
is
a
f
a
m
o
u
s
h
ad
ith
co
llectio
n
c
o
m
p
iled
b
y
I
b
n
Haja
r
al
-
Asq
alan
i
ar
o
u
n
d
th
e
1
4
th
ce
n
tu
r
y
a
n
d
is
an
ess
en
tial
s
o
u
r
ce
f
o
r
u
n
d
er
s
tan
d
in
g
th
e
p
o
s
tu
lates
in
th
e
I
s
lam
ic
r
elig
io
n
.
T
h
e
B
u
lu
g
h
al
-
Ma
r
am
B
o
o
k
co
m
p
r
is
es
1
,
3
5
6
h
ad
ith
o
r
g
a
n
ized
b
y
to
p
ic
an
d
co
v
er
s
p
u
r
ity
,
p
r
a
y
er
,
f
a
s
tin
g
,
an
d
m
o
r
e.
I
n
B
u
lu
g
h
al
-
Ma
r
am
,
n
o
tes
o
n
t
h
e
v
alid
ity
o
f
th
e
h
ad
ith
ar
e
o
f
ten
in
clu
d
ed
,
in
d
icatin
g
w
h
eth
er
it
is
s
tr
o
n
g
(
s
a
h
ih
)
o
r
wea
k
(
d
a
'if
)
[
6
]
.
T
h
is
b
o
o
k
aim
s
to
p
r
o
v
id
e
a
co
m
p
r
eh
en
s
iv
e
r
ef
er
e
n
ce
f
o
r
s
tu
d
e
n
ts
an
d
s
ch
o
lar
s
o
f
I
s
lam
ic
ju
r
is
p
r
u
d
en
ce
.
Ov
e
r
all,
th
is
b
o
o
k
is
an
ess
en
tial
tex
t
f
o
r
th
o
s
e
wh
o
wis
h
to
u
n
d
er
s
tan
d
an
d
ap
p
ly
th
e
p
r
in
cip
les o
f
th
e
I
s
lam
ic
r
elig
i
o
n
in
e
v
er
y
d
a
y
life
[
7
]
.
R
esear
ch
r
elate
d
to
ch
atb
o
ts
h
as
p
r
o
g
r
ess
ed
s
ig
n
if
ican
tly
in
th
e
last
d
ec
ad
e,
d
r
iv
en
b
y
th
e
in
cr
ea
s
in
g
d
em
an
d
f
o
r
ch
atb
o
t
s
er
v
ices
in
v
ar
io
u
s
d
o
m
ai
n
s
.
T
h
is
s
ec
tio
n
r
ev
iews
s
ev
er
al
s
tu
d
ies
r
elev
an
t
to
c
h
atb
o
t
d
ev
elo
p
m
e
n
t,
f
o
c
u
s
in
g
o
n
id
en
tify
in
g
th
e
tech
n
iq
u
es
an
d
ch
allen
g
es
th
ey
f
ac
e.
B
y
lo
o
k
in
g
f
r
o
m
s
ev
er
al
an
g
les
at
p
r
ev
io
u
s
r
esear
ch
in
th
is
ar
ea
,
we
aim
to
d
em
o
n
s
tr
ate
o
u
r
r
esear
ch
p
r
o
g
r
ess
in
d
ev
elo
p
in
g
r
elig
i
o
u
s
ch
atb
o
ts
.
First,
we
ex
p
lain
d
esig
n
s
cien
ce
r
esear
ch
(
DSR
)
,
th
en
r
ev
iew
ch
atb
o
ts
'
h
i
s
to
r
ical
ev
o
lu
tio
n
,
tr
ac
in
g
th
eir
d
e
v
elo
p
m
e
n
t
f
r
o
m
r
u
le
-
b
ased
s
y
s
tem
s
to
m
o
d
e
r
n
m
ac
h
in
e
-
lear
n
i
n
g
a
p
p
r
o
ac
h
es.
Nex
t,
we
ex
p
l
o
r
e
v
ar
io
u
s
r
esear
ch
m
eth
o
d
o
lo
g
i
es
u
s
ed
in
ch
atb
o
t
d
esig
n
.
T
h
ese
in
clu
d
e
r
u
le
-
b
ased
s
y
s
tem
s
,
m
ac
h
in
e
lear
n
in
g
tech
n
iq
u
es,
n
at
u
r
al
lan
g
u
ag
e
p
r
o
ce
s
s
in
g
tech
n
i
q
u
es,
f
ea
tu
r
e
ex
tr
ac
tio
n
tec
h
n
iq
u
es
f
o
r
tex
t
d
ata,
an
d
s
o
f
twar
e
d
ev
elo
p
m
e
n
t
p
r
in
ci
p
les
th
r
o
u
g
h
p
r
o
to
ty
p
in
g
tech
n
i
q
u
es.
W
e
th
en
ex
am
in
e
h
o
w
ch
atb
o
ts
ar
e
ap
p
lied
ac
r
o
s
s
d
o
m
ain
s
s
u
ch
as
cu
s
to
m
er
s
er
v
ice,
h
ea
lth
ca
r
e,
a
n
d
ed
u
ca
tio
n
,
h
ig
h
lig
h
tin
g
th
eir
c
h
allen
g
es.
Fin
ally
,
we
d
is
cu
s
s
eth
ical
co
n
s
id
er
atio
n
s
in
ch
atb
o
t im
p
lem
en
tatio
n
,
f
o
c
u
s
in
g
o
n
p
r
iv
ac
y
an
d
t
r
an
s
p
ar
e
n
cy
is
s
u
es.
DSR
i
s
a
m
eth
o
d
o
lo
g
y
th
at
i
n
v
o
lv
es
cr
ea
tin
g
an
d
e
v
alu
ati
n
g
ar
tifa
cts
d
esig
n
ed
t
o
s
o
lv
e
a
p
r
o
b
lem
[
8
]
,
[
9
]
.
DSR
is
co
m
m
o
n
ly
u
s
ed
in
in
f
o
r
m
atio
n
s
y
s
tem
s
,
in
f
o
r
m
atics,
an
d
co
m
p
u
ter
s
cien
ce
.
T
h
e
g
o
als
o
f
DSR
r
ev
o
lv
e
a
r
o
u
n
d
cr
ea
tin
g
p
r
ac
tical
an
d
in
n
o
v
ativ
e
s
o
lu
ti
o
n
s
to
r
ea
l
-
wo
r
l
d
p
r
o
b
lem
s
,
ca
r
ef
u
lly
ev
alu
atin
g
th
o
s
e
s
o
lu
tio
n
s
,
a
n
d
p
r
o
v
id
in
g
b
o
th
p
r
ac
tical
an
d
th
e
o
r
etic
al
co
n
tr
ib
u
tio
n
s
.
Sev
e
r
al
f
r
a
m
ewo
r
k
s
h
a
v
e
b
ee
n
d
ev
elo
p
e
d
to
g
u
id
e
th
e
DSR
p
r
o
ce
s
s
.
T
h
is
f
r
am
ew
o
r
k
o
f
f
e
r
s
a
s
tr
u
ctu
r
ed
m
eth
o
d
o
lo
g
y
f
o
r
co
n
d
u
ctin
g
DSR
an
d
en
s
u
r
es
th
at
th
e
r
esear
ch
i
s
r
ig
o
r
o
u
s
a
n
d
r
elev
an
t.
Hev
n
er
'
s
DS
R
f
r
am
ewo
r
k
p
r
i
m
ar
ily
f
o
cu
s
es
o
n
g
u
id
i
n
g
th
e
r
esear
ch
p
r
o
ce
s
s
to
en
s
u
r
e
th
at
DSR
is
ca
r
r
ied
o
u
t
r
ig
o
r
o
u
s
ly
an
d
p
r
o
d
u
ce
s
p
r
ac
tical
ar
tifa
cts
g
r
o
u
n
d
ed
in
th
eo
r
y
[
1
0
]
.
Me
an
w
h
ile,
Gr
eg
o
r
an
d
Hev
n
er
'
s
DS
R
K
n
o
wled
g
e
C
o
n
tr
ib
u
tio
n
f
r
am
ewo
r
k
f
o
c
u
s
es
o
n
ca
teg
o
r
izin
g
th
e
ty
p
es o
f
k
n
o
wled
g
e
co
n
tr
ib
u
tio
n
s
m
ad
e
b
y
DSR
[
1
1
]
.
J
o
h
an
n
ess
o
n
an
d
Per
jo
n
s
'
f
r
am
ewo
r
k
,
d
escr
ib
ed
in
d
etail
in
th
e
b
o
o
k
“
I
n
tr
o
d
u
ctio
n
to
d
esig
n
s
ci
en
ce
,
”
p
r
o
v
id
es
a
s
tr
u
ctu
r
ed
ap
p
r
o
ac
h
to
c
o
n
d
u
ctin
g
DSR
th
at
em
p
h
asizes
a
s
y
s
tem
atic
p
r
o
ce
s
s
f
o
r
d
esig
n
in
g
an
d
ev
al
u
atin
g
ar
tif
ac
ts
an
d
aim
s
to
ad
d
r
ess
r
ea
l
-
wo
r
ld
p
r
o
b
lem
s
wh
ile
co
n
tr
ib
u
tin
g
to
ac
ad
em
ic
k
n
o
wled
g
e.
T
h
e
y
also
ex
p
la
in
ed
th
at
th
er
e
ar
e
at
least
f
iv
e
ty
p
ical
ca
s
es
o
f
DSR
,
o
n
e
o
f
wh
ich
is
R
eq
u
ir
em
en
ts
-
f
o
cu
s
ed
DSR
.
R
eq
u
ir
em
en
ts
-
f
o
cu
s
ed
DSR
is
a
s
p
ec
if
ic
ap
p
r
o
ac
h
th
at
em
p
h
asizes
th
e
id
en
tific
atio
n
,
an
aly
s
is
,
an
d
f
u
lf
illme
n
t
o
f
r
e
q
u
ir
em
en
ts
f
o
r
th
e
d
esig
n
an
d
d
ev
elo
p
m
en
t
o
f
an
ar
tifa
ct.
T
h
is
ap
p
r
o
ac
h
ce
n
ter
s
o
n
u
n
d
er
s
tan
d
in
g
s
tak
eh
o
l
d
er
n
ee
d
s
,
co
n
s
tr
ain
ts
,
an
d
th
e
co
n
tex
t o
f
u
s
in
g
th
e
ar
tifa
ct
[
1
2
]
.
Ad
v
an
ce
s
in
n
atu
r
al
lan
g
u
ag
e
p
r
o
ce
s
s
in
g
,
m
ac
h
in
e
lear
n
in
g
,
an
d
d
ee
p
lear
n
i
n
g
d
r
i
v
e
th
e
ev
o
lu
tio
n
o
f
m
o
d
er
n
AI
-
p
o
wer
ed
ch
atb
o
ts
.
Fro
m
ea
r
l
y
r
u
le
-
b
ased
s
y
s
te
m
s
lik
e
E
L
I
Z
A
i
n
1
9
6
6
an
d
AL
I
C
E
in
1
9
9
5
t
o
ad
v
an
ce
d
AI
m
o
d
els
lik
e
GPT
-
3
an
d
GPT
-
4
,
to
d
a
y
'
s
ch
atb
o
ts
ar
e
in
cr
ea
s
in
g
ly
ca
p
a
b
le
o
f
u
n
d
e
r
s
tan
d
in
g
a
n
d
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.
16
,
No
.
5
,
Octo
b
e
r
20
26
:
2
7
8
2
-
2
7
9
4
2784
p
r
o
d
u
cin
g
h
u
m
an
-
lik
e
co
n
v
er
s
atio
n
s
,
m
ak
in
g
th
em
p
o
ten
t
to
o
ls
in
m
an
y
way
s
[
1
3
]
,
[
1
4
]
.
T
h
e
AL
I
C
E
is
a
p
io
n
ee
r
in
g
ch
atb
o
t
t
h
at
u
s
es
n
atu
r
al
lan
g
u
ag
e
p
r
o
ce
s
s
in
g
t
o
s
im
u
late
co
n
v
er
s
atio
n
s
wit
h
h
u
m
an
u
s
er
s
.
Dr
.
R
ich
ar
d
W
allac
e
d
ev
elo
p
ed
A
L
I
C
E
.
AL
I
C
E
o
r
Aliceb
o
t
ca
n
co
n
d
u
ct
co
n
v
er
s
atio
n
s
with
h
u
m
an
s
b
y
ap
p
l
y
in
g
s
ev
er
al
h
eu
r
is
tic
p
atter
n
-
m
atc
h
in
g
r
u
les
to
in
ter
p
r
et
an
d
r
esp
o
n
d
to
u
s
er
in
p
u
t.
Af
ter
a
u
s
er
p
r
o
v
id
es
a
p
h
r
ase
o
r
q
u
esti
o
n
,
AL
I
C
E
s
ea
r
ch
es
th
e
ar
tific
ial
in
tellig
en
ce
m
ar
k
u
p
lan
g
u
a
g
e
(
AI
ML
)
f
i
le
to
f
in
d
m
atch
i
n
g
p
atter
n
s
an
d
r
etu
r
n
s
th
e
ap
p
r
o
p
r
iate
r
esp
o
n
s
e.
T
h
is
ap
p
r
o
a
ch
allo
ws
Aliceb
o
t
to
s
im
u
lat
e
co
n
v
er
s
atio
n
s
b
y
r
ec
o
g
n
izin
g
s
p
ec
if
ic
k
ey
w
o
r
d
s
an
d
p
h
r
ases
an
d
p
r
o
v
id
i
n
g
p
r
ed
ef
in
ed
r
esp
o
n
s
es
[
1
5
]
,
[
1
6
]
.
I
n
tr
o
d
u
cin
g
c
h
atb
o
t
f
r
am
ewo
r
k
s
an
d
p
latf
o
r
m
s
s
u
ch
as
Pan
d
o
r
a
b
o
ts
in
2
0
0
8
an
d
W
it.a
i
in
2
0
1
3
allo
ws
d
ev
elo
p
er
s
to
c
r
ea
te
an
d
im
p
lem
en
t
c
h
atb
o
ts
m
o
r
e
ea
s
ily
.
T
h
is
ch
atb
o
t
f
r
am
ewo
r
k
an
d
p
latf
o
r
m
m
a
k
e
it
ea
s
ier
f
o
r
d
e
v
elo
p
er
s
to
d
e
v
elo
p
,
tr
ain
,
an
d
im
p
lem
e
n
t
c
h
atb
o
ts
.
T
h
ese
p
latf
o
r
m
s
d
if
f
er
in
ap
p
r
o
ac
h
an
d
ca
p
ab
ilit
ies
,
s
ee
T
ab
le
1
,
s
er
v
in
g
v
a
r
io
u
s
n
ee
d
s
,
f
r
o
m
s
im
p
le
r
u
les
-
b
ased
ch
atb
o
t
s
to
s
o
p
h
is
ticated
co
n
v
er
s
atio
n
al
a
g
en
ts
d
r
iv
e
n
b
y
ar
tific
ial
in
tellig
en
ce
[
1
7
]
,
[
1
8
]
.
T
ab
le
1
.
C
h
atb
o
t
d
ev
elo
p
m
en
t
p
latf
o
r
m
No
P
l
a
t
f
o
r
m
N
a
m
e
D
e
v
e
l
o
p
e
r
K
e
y
f
e
a
t
u
r
e
s
a
n
d
c
a
p
a
b
i
l
i
t
i
e
s
I
n
t
e
g
r
a
t
i
o
n
o
p
t
i
o
n
1
W
i
t
.
a
i
W
i
t
.
a
i
,
I
n
c
.
(
F
a
c
e
b
o
o
k
)
N
a
t
u
r
a
l
l
a
n
g
u
a
g
e
u
n
d
e
r
st
a
n
d
i
n
g
(
N
L
U
)
,
mu
l
t
i
l
i
n
g
u
a
l
su
p
p
o
r
t
,
e
n
t
i
t
y
r
e
c
o
g
n
i
t
i
o
n
,
i
n
t
e
n
t
s
a
n
d
a
c
t
i
o
n
s
A
P
I
s a
n
d
S
D
K
s
2
D
i
a
l
o
g
f
l
o
w
A
p
i
.
a
i
(
a
c
q
.
B
y
G
o
o
g
l
e
)
I
n
t
e
n
t
r
e
c
o
g
n
i
t
i
o
n
,
e
n
t
i
t
y
e
x
t
r
a
c
t
i
o
n
,
p
r
e
b
u
i
l
t
a
g
e
n
t
s
,
N
LP,
m
u
l
t
i
-
l
a
n
g
u
a
g
e
G
o
o
g
l
e
A
ssi
st
a
n
t
,
S
l
a
c
k
,
F
a
c
e
b
o
o
k
,
Te
l
e
g
r
a
m
3
A
maz
o
n
Le
x
A
maz
o
n
W
e
b
S
e
r
v
i
c
e
s
N
LU
,
a
u
t
o
ma
t
i
c
s
p
e
e
c
h
r
e
c
o
g
n
i
t
i
o
n
(
A
S
R
)
,
m
u
l
t
i
-
l
a
n
g
u
a
g
e
su
p
p
o
r
t
,
o
m
n
i
-
c
h
a
n
n
e
l
d
e
p
l
o
y
me
n
t
A
W
S
S
e
r
v
i
c
e
s
4
R
A
S
A
R
a
sa
Te
c
h
n
o
l
o
g
i
e
s
G
mb
H
O
p
e
n
S
o
u
r
c
e
,
N
LU
,
d
i
a
l
o
g
u
e
ma
n
a
g
e
men
t
,
i
n
t
e
r
a
c
t
i
v
e
l
e
a
r
n
i
n
g
,
m
u
l
t
i
-
l
a
n
g
u
a
g
e
s
u
p
p
o
r
t
S
l
a
c
k
,
F
a
c
e
b
o
o
k
M
e
sse
n
g
e
r
,
W
h
a
t
sA
p
p
,
Te
l
e
g
r
a
m
5
K
o
r
e
.
a
i
K
o
r
e
.
a
i
,
I
n
c
.
N
LP,
C
o
n
v
e
r
sat
i
o
n
a
l
A
I
,
B
o
t
B
u
i
l
d
e
r
,
M
u
l
t
i
-
c
h
a
n
n
e
l
,
C
h
a
t
b
o
t
T
e
m
p
l
a
t
e
F
a
c
e
b
o
o
k
,
W
h
a
t
sA
p
p
6
C
h
a
t
t
e
r
b
o
t
G
u
n
t
h
e
r
C
o
x
O
p
e
n
S
o
u
r
c
e
,
P
y
t
h
o
n
-
b
a
s
e
d
l
i
b
r
a
r
y
,
L
a
n
g
u
a
g
e
I
n
d
e
p
e
n
d
e
n
c
e
,
D
a
t
a
b
a
se
B
a
c
k
e
n
d
,
A
P
I
s,
D
j
a
n
g
o
,
F
l
a
sk
NL
P
is
es
s
en
tial
f
o
r
cr
ea
tin
g
in
tellig
en
t
an
d
co
n
v
er
s
atio
n
al
ch
atb
o
ts
th
at
ca
n
ef
f
ec
tiv
ely
u
n
d
er
s
tan
d
u
s
er
in
p
u
t,
g
en
er
ate
ap
p
r
o
p
r
i
ate
r
esp
o
n
s
es,
an
d
en
g
ag
e
u
s
er
s
in
n
atu
r
al
in
ter
ac
tio
n
s
.
NL
P
h
elp
s
ch
atb
o
ts
u
n
d
er
s
tan
d
th
e
m
ea
n
i
n
g
o
f
u
s
er
q
u
esti
o
n
s
b
y
an
aly
zin
g
tex
t
f
o
r
s
em
an
tics
,
s
y
n
tax
,
an
d
co
n
tex
t.
T
h
is
in
v
o
lv
es
tex
t
an
aly
s
is
,
en
tity
r
ec
o
g
n
itio
n
,
an
d
s
en
tim
en
t
an
aly
s
is
,
wh
ich
en
ab
le
t
h
e
ch
atb
o
t
t
o
ex
tr
ac
t
r
elev
a
n
t
in
f
o
r
m
atio
n
an
d
u
n
d
e
r
s
tan
d
th
e
ap
p
r
o
p
r
iate
in
ten
t.
NL
P is
also
u
s
ed
to
g
en
e
r
ate
h
u
m
a
n
-
lik
e
r
esp
o
n
s
es th
at
ar
e
g
r
am
m
atica
lly
co
r
r
ec
t a
n
d
co
n
tex
tu
ally
ap
p
r
o
p
r
iate
[
1
9
]
.
Featu
r
e
ex
tr
ac
tio
n
tech
n
i
q
u
es
f
o
r
tex
t
d
ata
in
ch
atb
o
t
d
ev
elo
p
m
en
t
i
n
v
o
lv
e
tr
an
s
f
o
r
m
in
g
r
aw
tex
t
d
ata
in
to
n
u
m
er
ical
o
r
s
tr
u
ctu
r
ed
r
ep
r
esen
tatio
n
s
th
at
ca
n
b
e
u
s
ed
as
in
p
u
t
f
o
r
m
ac
h
in
e
l
ea
r
n
in
g
m
o
d
els
o
r
o
th
er
n
atu
r
al
lan
g
u
a
g
e
p
r
o
ce
s
s
in
g
task
s
.
T
h
ese
tech
n
i
q
u
es
ai
m
to
ca
p
tu
r
e
r
elev
a
n
t
in
f
o
r
m
at
io
n
an
d
p
atter
n
s
in
tex
t
d
ata,
en
ab
lin
g
ch
at
b
o
ts
t
o
u
n
d
er
s
tan
d
an
d
r
esp
o
n
d
to
u
s
er
q
u
er
ies
ef
f
ec
tiv
ely
.
B
y
lev
er
ag
i
n
g
f
ea
tu
r
e
ex
tr
ac
tio
n
tech
n
iq
u
es,
ch
atb
o
ts
ca
n
tr
an
s
f
o
r
m
r
aw
tex
t
d
ata
in
to
s
tr
u
ctu
r
ed
r
ep
r
esen
t
atio
n
s
th
at
ca
p
tu
r
e
r
elev
an
t
in
f
o
r
m
atio
n
an
d
p
atte
r
n
s
n
ec
ess
ar
y
to
u
n
d
e
r
s
tan
d
u
s
er
q
u
esti
o
n
s
,
g
en
er
ate
a
p
p
r
o
p
r
iate
r
esp
o
n
s
es,
an
d
p
er
f
o
r
m
v
a
r
io
u
s
n
atu
r
al
la
n
g
u
ag
e
p
r
o
ce
s
s
in
g
task
s
ef
f
ec
tiv
e
ly
.
So
m
e
co
m
m
o
n
f
ea
tu
r
e
ex
t
r
ac
tio
n
tech
n
iq
u
es
u
s
ed
in
ch
atb
o
t
d
ev
elo
p
m
en
t
:
b
ag
-
of
-
w
o
r
d
s
(
B
OW
)
[
1
9
]
,
[
2
0
]
,
ter
m
f
r
e
q
u
en
c
y
-
in
v
e
r
s
e
d
o
cu
m
en
t
f
r
e
q
u
en
c
y
(TF
-
I
DF)
,
wo
r
d
em
b
e
d
d
in
g
s
(
s
u
ch
as
W
o
r
d
2
Vec
,
Glo
V
e,
o
r
Fas
tTe
x
t)
,
s
en
ten
ce
e
m
b
ed
d
in
g
s
(
s
u
ch
as
Do
c2
Vec
,
B
E
R
T
)
,
n
am
ed
en
tity
r
ec
o
g
n
itio
n
(
NE
R
)
,
an
d
s
o
o
n
[
2
1
]
.
C
u
r
r
e
n
tly
,
m
o
s
t
ar
e
b
ased
o
n
d
ee
p
lear
n
in
g
t
o
r
ec
o
g
n
ize
t
h
e
in
ten
t
o
f
q
u
esti
o
n
s
o
r
p
r
o
m
p
ts
g
i
v
e
n
b
y
u
s
er
s
[
2
2
]
,
[
2
3
]
.
I
n
ten
t r
e
co
g
n
itio
n
m
eth
o
d
s
,
wh
ich
ar
e
th
e
b
r
ain
s
o
f
th
e
ch
a
tb
o
t,
in
clu
d
e
B
E
R
T
[
2
4
]
–
[
2
6
]
,
B
iLST
M
[
2
7
]
,
an
d
p
r
o
m
p
t
-
b
a
s
ed
m
o
d
el
[
2
2
]
.
B
id
ir
ec
tio
n
al
en
co
d
er
r
ep
r
ese
n
tatio
n
s
f
r
o
m
tr
an
s
f
o
r
m
er
s
(
B
E
R
T
)
ar
e
a
tr
an
s
f
o
r
m
er
-
b
a
s
ed
m
o
d
el
d
ev
elo
p
e
d
b
y
Go
o
g
le
th
at
is
d
esig
n
ed
to
u
n
d
er
s
tan
d
th
e
c
o
n
tex
t
o
f
wo
r
d
s
in
a
s
en
ten
c
e
in
two
d
ir
ec
ti
o
n
s
(
b
id
ir
ec
tio
n
al)
.
Sev
er
al
B
E
R
T
v
ar
ian
ts
h
av
e
b
ee
n
d
ev
el
o
p
ed
to
im
p
r
o
v
e
its
ef
f
icien
cy
an
d
p
er
f
o
r
m
an
ce
,
s
u
ch
as
AL
B
E
R
T
an
d
T
in
y
B
E
R
T
.
AL
B
E
R
T
(
A
L
ite
B
E
R
T
)
r
ed
u
ce
s
th
e
n
u
m
b
er
o
f
p
ar
am
eter
s
th
r
o
u
g
h
p
a
r
am
eter
s
h
ar
in
g
an
d
f
ac
to
r
ized
em
b
ed
d
in
g
tech
n
i
q
u
es.
Me
an
wh
ile,
T
in
y
B
E
R
T
is
a
co
m
p
r
ess
ed
v
er
s
io
n
o
f
B
E
R
T
th
at
allo
ws p
er
f
o
r
m
a
n
ce
clo
s
e
to
th
e
o
r
ig
in
al
B
E
R
T
with
a
m
u
ch
s
m
aller
m
o
d
el
s
ize
[
2
8
]
.
On
th
e
o
t
h
e
r
h
an
d
,
g
a
th
er
in
g
r
e
q
u
i
r
e
m
e
n
ts
f
o
r
a
h
a
d
it
h
lea
r
n
i
n
g
c
h
a
tb
o
t
r
e
q
u
ir
es
u
n
d
er
s
t
a
n
d
in
g
s
p
e
ci
f
ic
n
e
e
d
s
,
p
r
e
f
e
r
e
n
c
es,
an
d
s
e
n
s
it
iv
it
y
t
o
u
s
er
h
ab
its
.
T
h
e
f
i
r
s
t
s
t
e
p
is
t
o
i
d
e
n
t
if
y
a
ll
s
t
a
k
e
h
o
l
d
e
r
s
w
h
o
will
in
t
er
ac
t
w
it
h
t
h
e
c
h
at
b
o
t.
T
h
is
ca
n
i
n
cl
u
d
e
s
ta
k
e
h
o
l
d
e
r
s
,
i
n
c
lu
d
i
n
g
m
e
m
b
er
s
o
f
r
el
ig
io
u
s
c
o
m
m
u
n
iti
es,
r
el
ig
io
u
s
co
m
m
u
n
it
y
l
ea
d
e
r
s
,
r
eli
g
i
o
u
s
t
ea
c
h
e
r
s
,
s
t
u
d
e
n
ts
,
a
n
d
s
o
o
n
.
W
e
co
n
d
u
ct
f
a
ce
-
to
-
f
ac
e
o
r
g
r
o
u
p
i
n
t
e
r
v
iews
w
it
h
p
o
te
n
ti
al
u
s
e
r
s
a
n
d
s
ta
k
e
h
o
l
d
er
s
t
o
e
n
s
u
r
e
th
e
c
h
a
tb
o
t
m
e
ets
u
s
er
n
e
ed
s
an
d
e
x
p
e
cta
ti
o
n
s
.
T
h
e
g
o
al
is
t
o
co
m
p
let
e
q
u
alit
ati
v
e
in
f
o
r
m
a
ti
o
n
ab
o
u
t
u
s
e
r
s
'
n
e
ed
s
,
e
x
p
e
ct
ati
o
n
s
,
a
n
d
c
o
n
s
tr
ai
n
ts
w
h
e
n
u
s
i
n
g
ch
at
b
o
ts
.
W
e
cr
ea
t
ed
a
p
r
o
t
o
t
y
p
e
b
ase
d
o
n
th
e
i
n
i
tial
r
e
q
u
i
r
e
m
e
n
ts
a
n
d
t
este
d
it
o
n
li
m
it
ed
u
s
e
r
s
.
T
h
e
n
,
u
s
i
n
g
t
h
a
t
i
n
i
tia
l
p
r
o
t
o
t
y
p
e
,
we
g
at
h
e
r
e
d
f
ee
d
b
a
ck
o
n
t
h
e
p
r
o
t
o
t
y
p
e'
s
f
u
n
cti
o
n
a
lit
y
,
u
s
a
b
ili
ty
,
a
n
d
o
v
e
r
al
l
u
s
e
r
ex
p
e
r
i
en
ce
.
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
Desig
n
s
cien
ce
r
esea
r
ch
in
d
ev
elo
p
in
g
a
r
elig
io
u
s
ch
a
tb
o
t b
a
s
ed
o
n
…
(
A
r
is
Tja
h
ya
n
to
)
2785
C
h
atb
o
ts
h
av
e
b
ee
n
ap
p
lied
in
v
ar
io
u
s
d
o
m
ain
s
,
s
u
ch
as
cu
s
to
m
er
s
er
v
ice,
e
-
co
m
m
er
ce
,
h
ea
lth
s
er
v
ices,
en
ter
tain
m
en
t,
an
d
s
o
o
n
[
2
9
]
,
[
3
0
]
.
On
e
ex
am
p
le
is
Ask
B
o
,
wh
ich
is
a
ch
atb
o
t
d
ev
elo
p
e
d
b
y
Air
Asi
a.
T
h
is
ch
atb
o
t
is
d
esig
n
ed
to
p
r
o
v
id
e
c
u
s
to
m
er
s
er
v
ice
an
d
s
u
p
p
o
r
t
to
Air
Asi
a
p
ass
en
g
er
s
,
h
elp
in
g
th
em
with
v
ar
io
u
s
q
u
esti
o
n
s
a
n
d
task
s
r
elate
d
to
t
h
eir
tr
a
v
el
ex
p
er
ie
n
ce
.
An
o
th
er
ex
am
p
le
is
Netf
lix
C
h
atb
o
t,
wh
ich
o
f
f
er
s
s
u
p
p
o
r
t
an
d
c
o
n
ten
t
r
ec
o
m
m
e
n
d
atio
n
s
ac
c
o
r
d
in
g
to
u
s
er
n
ee
d
s
.
Netf
lix
'
s
ch
atb
o
t
h
el
p
s
u
s
er
s
with
ac
co
u
n
t
m
an
ag
em
e
n
t,
tech
n
ical
tr
o
u
b
lesh
o
o
tin
g
,
an
d
f
in
d
in
g
m
o
v
ies
an
d
T
V
s
h
o
ws
b
ased
o
n
u
s
er
p
r
ef
er
en
ce
s
.
Sev
er
al
p
lat
f
o
r
m
s
f
o
r
d
e
v
el
o
p
i
n
g
ch
at
b
o
ts
ca
n
g
e
n
e
r
a
ll
y
b
e
g
r
o
u
p
e
d
i
n
t
o
c
o
m
m
e
r
c
ial
an
d
o
p
e
n
-
s
o
u
r
c
e
ca
t
eg
o
r
ies
.
C
o
m
m
e
r
c
ial
p
lat
f
o
r
m
s
s
u
ch
as
D
ial
o
g
f
lo
w
a
n
d
Ko
r
e
.
ai
o
f
f
e
r
c
o
m
p
r
e
h
en
s
iv
e
t
o
o
ls
f
o
r
d
es
ig
n
i
n
g
,
im
p
le
m
e
n
t
in
g
,
a
n
d
m
a
n
ag
in
g
ch
at
b
o
ts
a
c
r
o
s
s
m
u
lt
i
p
le
c
h
a
n
n
els
,
as
s
ee
n
i
n
T
ab
le
1
.
O
p
e
n
-
s
o
u
r
ce
p
la
tf
o
r
m
s
in
c
lu
d
e
R
ASA
,
w
h
i
ch
p
r
o
v
id
es
f
le
x
i
b
il
it
y
a
n
d
c
u
s
t
o
m
i
za
ti
o
n
,
al
lo
wi
n
g
d
ev
el
o
p
e
r
s
to
b
u
il
d
c
h
at
b
o
t
ap
p
li
ca
ti
o
n
s
.
Ad
d
i
ti
o
n
all
y
,
t
h
e
r
e
a
r
e
Py
th
o
n
-
b
ase
d
li
b
r
ar
ies
s
u
c
h
as
C
h
a
tte
r
B
o
t
th
at
o
f
f
e
r
s
i
m
p
lic
it
y
a
n
d
ea
s
e
o
f
u
s
e
f
o
r
b
eg
in
n
er
s
,
wit
h
a
f
o
c
u
s
o
n
r
u
l
e
-
b
ase
d
r
es
p
o
n
s
es
a
n
d
b
asic
n
at
u
r
al
la
n
g
u
a
g
e
p
r
o
ce
s
s
i
n
g
t
ask
s
[
1
7
]
,
[
1
8
]
.
I
n
ad
d
itio
n
,
eth
ical
c
o
n
s
id
er
at
io
n
s
wh
en
u
s
in
g
ch
atb
o
ts
ar
e
ess
en
tial
to
m
in
im
ize
p
o
ten
tia
l
h
ar
m
to
u
s
er
s
.
T
h
in
g
s
t
h
at
n
ee
d
t
o
b
e
co
n
s
id
er
e
d
in
clu
d
e
p
r
iv
ac
y
,
t
r
an
s
p
ar
en
cy
,
ac
c
o
u
n
tab
ilit
y
,
a
n
d
u
s
er
au
to
n
o
m
y
.
T
h
u
s
,
it
is
n
ec
ess
ar
y
to
b
u
ild
an
d
im
p
lem
en
t
c
h
atb
o
ts
t
h
at
ca
n
b
e
tr
u
s
ted
an
d
p
a
y
atten
tio
n
to
eth
ical
s
tan
d
ar
d
s
.
Ap
ar
t f
r
o
m
th
at,
u
p
d
ates to
ch
atb
o
t p
o
licies ar
e
also
n
ee
d
ed
to
m
ain
tain
p
u
b
lic
t
r
u
s
t
[
3
1
]
,
[
3
2
]
.
Sev
er
al
im
p
o
r
tan
t
id
ea
s
em
er
g
e
b
y
ex
p
lain
in
g
DSR
,
r
ev
iewin
g
th
e
d
ev
elo
p
m
en
t
o
f
ch
atb
o
t
tech
n
o
lo
g
y
,
a
n
d
s
u
m
m
ar
izin
g
f
in
d
in
g
s
f
r
o
m
p
r
ev
i
o
u
s
r
esea
r
ch
.
Pre
v
io
u
s
r
esear
c
h
h
as
s
h
o
wn
th
at
m
ac
h
in
e
lear
n
in
g
tech
n
i
q
u
es'
p
er
f
o
r
m
a
n
ce
an
d
d
ee
p
lear
n
in
g
ar
c
h
ite
ctu
r
e
ar
e
im
p
r
o
v
in
g
ch
atb
o
t
c
ap
ab
ilit
ies.
E
ar
lier
r
esear
ch
also
ex
p
lain
s
th
e
im
p
o
r
tan
ce
o
f
i
n
v
o
lv
i
n
g
u
s
er
s
d
u
r
in
g
t
h
e
d
esig
n
p
r
o
ce
s
s
an
d
in
clu
d
es
eth
ical
co
n
s
id
er
atio
n
s
in
ch
atb
o
t
d
e
v
elo
p
m
en
t.
W
ith
th
e
en
lig
h
t
en
m
en
t
f
r
o
m
p
r
io
r
r
esear
ch
,
th
is
p
ap
er
aim
s
to
p
r
o
v
id
e
a
f
r
am
ewo
r
k
f
o
r
ad
v
an
cin
g
c
h
atb
o
t
tech
n
o
l
o
g
y
,
esp
ec
ially
f
o
r
d
e
v
elo
p
in
g
r
eli
g
io
u
s
ch
atb
o
ts
u
s
in
g
DSR
.
T
h
e
m
eth
o
d
o
lo
g
y
u
s
ed
i
n
t
h
is
r
esear
ch
in
v
o
l
v
es
a
co
m
p
r
eh
en
s
iv
e
a
p
p
r
o
ac
h
to
r
e
q
u
ir
em
en
ts
elicitatio
n
an
d
ch
atb
o
t
d
esig
n
.
W
e
attem
p
ted
to
co
n
d
u
ct
a
th
o
r
o
u
g
h
r
ev
iew
o
f
th
e
e
x
is
tin
g
liter
atu
r
e
o
n
ch
atb
o
t
tech
n
o
l
o
g
y
,
n
atu
r
al
la
n
g
u
ag
e
p
r
o
ce
s
s
in
g
alg
o
r
ith
m
s
,
an
d
co
n
v
er
s
atio
n
al
ag
en
t
d
e
s
ig
n
.
Nex
t,
we
will
d
ev
elo
p
a
ch
atb
o
t
p
r
o
to
ty
p
e
u
s
in
g
a
m
ac
h
in
e
-
lear
n
in
g
f
r
a
m
ewo
r
k
.
T
h
e
ch
atb
o
t
will
b
e
tr
ain
ed
b
ased
o
n
a
d
iv
er
s
e
d
ata
s
et
o
f
u
s
er
q
u
esti
o
n
s
an
d
r
esp
o
n
s
es
to
o
p
tim
ize
its
n
atu
r
al
lan
g
u
ag
e
u
n
d
er
s
tan
d
in
g
ca
p
a
b
ilit
ies.
Nex
t,
we
will
co
n
d
u
ct
a
u
s
er
t
esti
n
g
s
ess
io
n
to
ev
al
u
ate
th
e
ch
atb
o
t'
s
ac
cu
r
ac
y
p
er
f
o
r
m
an
c
e.
Fin
ally
,
we
will
an
aly
ze
th
e
r
esu
lts
an
d
iter
ati
v
ely
r
ef
i
n
e
th
e
c
h
atb
o
t
d
esig
n
b
ased
o
n
u
s
er
f
ee
d
b
ac
k
an
d
i
n
s
ig
h
ts
g
ain
ed
f
r
o
m
th
e
ev
alu
atio
n
p
r
o
ce
s
s
.
T
o
p
r
o
v
i
d
e
a
co
m
p
r
e
h
en
s
iv
e
o
v
er
v
iew
o
f
o
u
r
r
esear
ch
,
th
e
s
tr
u
ctu
r
e
o
f
th
is
p
ap
er
will
b
e
ex
p
lain
ed
.
I
n
th
e
f
ir
s
t
s
ec
tio
n
,
we
b
r
ief
ly
ex
p
lain
d
esig
n
s
cien
ce
r
esear
ch
an
d
th
e
n
r
ev
iew
r
ele
v
an
t
li
ter
atu
r
e
o
n
c
h
atb
o
t
tech
n
o
lo
g
y
,
p
r
ev
i
o
u
s
r
esear
c
h
f
in
d
in
g
s
,
an
d
cu
r
r
en
t
tr
e
n
d
s
in
th
e
f
ield
.
Af
ter
th
at,
we
will
p
r
esen
t
th
e
m
eth
o
d
o
l
o
g
y
u
s
ed
i
n
d
esig
n
in
g
an
d
e
v
alu
atin
g
o
u
r
ch
at
b
o
t
s
y
s
tem
,
d
etailin
g
th
e
s
tep
s
in
v
o
lv
e
d
in
its
d
ev
elo
p
m
e
n
t
an
d
test
in
g
.
Nex
t,
we
will
s
h
o
w
th
e
ty
p
es
o
f
u
s
er
n
ee
d
s
f
o
r
ch
atb
o
ts
an
d
t
h
e
r
esu
lts
o
f
test
in
g
s
ess
io
n
s
an
d
d
is
cu
s
s
th
e
im
p
licatio
n
s
o
f
o
u
r
f
in
d
i
n
g
s
.
Fin
ally
,
we
will
co
n
clu
d
e
with
a
s
u
m
m
ar
y
o
f
o
u
r
co
n
tr
ib
u
tio
n
s
,
s
tu
d
y
lim
itatio
n
s
,
an
d
d
ir
ec
tio
n
s
f
o
r
f
u
tu
r
e
r
esear
ch
.
2.
M
E
T
H
O
D
T
h
e
m
eth
o
d
o
lo
g
y
u
s
ed
i
n
t
h
is
r
esear
ch
in
v
o
l
v
es
a
co
m
p
r
eh
en
s
iv
e
a
p
p
r
o
ac
h
to
r
e
q
u
ir
em
en
ts
elicitatio
n
an
d
ch
atb
o
t
d
esig
n
,
f
o
llo
win
g
th
e
s
tag
es
o
f
d
esig
n
s
cien
ce
r
esear
ch
m
eth
o
d
o
l
o
g
y
(
DSR
M)
.
W
e
attem
p
ted
to
co
n
d
u
ct
a
th
o
r
o
u
g
h
r
e
v
iew
o
f
th
e
ex
is
tin
g
liter
atu
r
e
o
n
ch
at
b
o
t
tech
n
o
lo
g
y
a
n
d
n
at
u
r
al
lan
g
u
ag
e
p
r
o
ce
s
s
in
g
alg
o
r
ith
m
s
.
Nex
t,
we
will
d
ev
elo
p
a
ch
atb
o
t
p
r
o
to
ty
p
e
u
s
in
g
a
m
ac
h
in
e
-
lea
r
n
i
n
g
f
r
am
ew
o
r
k
.
T
h
e
ch
atb
o
t
will
b
e
tr
ain
e
d
b
ased
o
n
a
d
ataset
co
n
tai
n
in
g
q
u
esti
o
n
s
an
d
r
esp
o
n
s
e
an
s
wer
s
,
a
c
o
llectio
n
o
f
h
a
d
ith
s
f
r
o
m
t
h
e
b
o
o
k
B
u
lu
g
h
al
-
Ma
r
am
.
Nex
t,
we
will
co
n
d
u
ct
a
test
in
g
s
ess
io
n
to
ev
al
u
ate
th
e
ch
atb
o
t'
s
in
ten
t
r
ec
o
g
n
itio
n
r
ate
(
I
R
R
)
p
er
f
o
r
m
an
ce
.
Fin
ally
,
we
will
an
aly
ze
th
e
r
esu
lts
an
d
iter
ativ
ely
r
ef
in
e
th
e
ch
atb
o
t
d
esig
n
b
ased
o
n
u
s
er
f
ee
d
b
ac
k
an
d
in
s
ig
h
ts
g
ain
e
d
f
r
o
m
th
e
ev
alu
atio
n
p
r
o
ce
s
s
.
T
h
e
DSR
M
r
e
s
ea
r
ch
m
eth
o
d
o
lo
g
y
ap
p
r
o
ac
h
u
s
ed
to
d
eter
m
in
e
tech
n
ical
p
o
licy
m
o
d
el
ar
t
if
ac
ts
f
o
r
d
ev
elo
p
m
e
n
t
an
d
ap
p
licatio
n
d
ev
elo
p
m
e
n
t
h
as
f
i
v
e
s
tag
es:
ex
p
licate
th
e
p
r
o
b
lem
,
d
ef
i
n
e
r
eq
u
ir
em
en
ts
,
d
esig
n
an
d
d
e
v
elo
p
ar
tifa
cts,
im
p
le
m
en
t a
n
d
d
em
o
n
s
tr
ate
ar
tifa
cts,
an
d
ev
alu
ate
a
r
tifa
cts
[
8
]
.
2
.
1
.
E
x
pli
ca
t
e
pro
blem
At
th
e
“
E
x
p
licate
p
r
o
b
le
m
s
”
s
tag
e,
ef
f
o
r
ts
ar
e
m
a
d
e
to
clar
if
y
th
e
p
r
o
b
lem
b
y
id
e
n
tify
in
g
a
n
d
d
ef
in
in
g
th
e
is
s
u
e
in
m
o
r
e
d
etail.
T
h
is
b
eg
an
with
a
th
o
r
o
u
g
h
liter
atu
r
e
r
ev
iew
to
u
n
d
er
s
tan
d
p
r
ev
io
u
s
ap
p
r
o
ac
h
es
an
d
e
x
p
lo
r
e
o
n
lin
e
r
eso
u
r
ce
s
in
th
e
f
o
r
m
o
f
FAQs
.
T
h
e
n
ex
t
s
tep
is
to
co
n
d
u
ct
in
ter
v
iews
with
s
ev
er
al
s
tak
eh
o
ld
er
s
to
o
b
tain
a
b
r
o
a
d
er
p
ictu
r
e.
T
h
is
s
tep
en
s
u
r
es
th
at
th
e
r
esear
ch
is
b
ased
o
n
ac
tu
al
an
d
r
elev
an
t p
r
o
b
lem
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.
16
,
No
.
5
,
Octo
b
e
r
20
26
:
2
7
8
2
-
2
7
9
4
2786
Attem
p
tin
g
to
g
et
q
u
ick
a
n
d
ac
cu
r
ate
an
s
wer
s
to
s
p
ir
itu
al
q
u
esti
o
n
s
is
o
f
ten
ch
allen
g
i
n
g
.
W
h
eth
er
lo
o
k
in
g
f
o
r
g
u
id
an
c
e
in
d
ail
y
r
elig
io
u
s
p
r
ac
tices,
u
n
d
er
s
t
an
d
in
g
c
o
m
p
lex
t
h
eo
lo
g
ical
co
n
ce
p
ts
,
o
r
s
im
p
ly
f
in
d
in
g
q
u
o
tes
f
r
o
m
h
ad
ith
te
x
ts
,
th
e
p
r
o
ce
s
s
is
co
m
p
licate
d
an
d
r
eq
u
ir
es
tim
e
o
r
ef
f
o
r
t
i
f
d
o
n
e
th
r
o
u
g
h
th
ick
tex
tb
o
o
k
s
.
I
n
g
ettin
g
a
n
s
wer
s
,
it
is
u
s
u
ally
ea
s
ier
to
ask
r
elig
io
u
s
lead
er
s
d
ir
ec
tly
o
r
s
ea
r
ch
v
ar
io
u
s
o
n
lin
e
s
o
u
r
ce
s
,
alth
o
u
g
h
t
h
ey
ar
e
n
o
t
alwa
y
s
r
eliab
le.
T
h
u
s
,
a
s
o
lu
tio
n
is
n
ee
d
ed
to
p
r
o
v
i
d
e
f
ast,
r
eliab
le,
an
d
ac
cu
r
ate
in
f
o
r
m
atio
n
tailo
r
e
d
t
o
r
elig
io
u
s
n
ee
d
s
in
an
ea
s
ily
a
cc
ess
ib
le
an
d
u
s
er
-
f
r
ien
d
ly
wa
y
.
2
.
2
.
Def
ine
re
qu
irem
ent
s
At
th
e
“
Def
in
e
r
eq
u
ir
em
en
ts
”
s
tag
e,
th
e
s
ec
o
n
d
s
tag
e
o
f
DSR
M,
as
s
ee
n
in
Fig
u
r
e
1
,
d
etailed
r
eq
u
ir
em
e
n
ts
an
d
c
r
iter
ia
ar
e
d
eter
m
in
e
d
as
th
e
b
asis
f
o
r
ef
f
ec
tiv
e
c
h
atb
o
t
d
esig
n
.
T
h
is
s
tag
e
id
en
tifie
s
f
u
n
ctio
n
al
a
n
d
n
o
n
-
f
u
n
ctio
n
al
r
eq
u
ir
em
e
n
ts
an
d
en
s
u
r
es
th
at
ea
ch
r
eq
u
i
r
em
en
t
h
as
b
ee
n
d
e
s
cr
ib
ed
th
o
r
o
u
g
h
ly
an
d
clea
r
l
y
.
Fu
n
ctio
n
al
r
eq
u
ir
em
en
ts
d
ef
in
e
wh
at
a
s
y
s
t
em
m
u
s
t
d
o
,
d
escr
ib
in
g
th
e
s
p
ec
if
ic
b
e
h
av
io
r
,
f
u
n
ctio
n
s
,
an
d
f
ea
tu
r
es
a
s
y
s
tem
m
u
s
t
h
av
e
t
o
m
ee
t
th
e
n
e
ed
s
o
f
its
u
s
er
s
as
s
h
o
wn
in
T
ab
le
2
.
Me
an
wh
ile,
non
-
f
u
n
ctio
n
al
r
eq
u
ir
em
en
ts
s
p
ec
if
y
p
er
f
o
r
m
an
ce
,
s
ec
u
r
ity
,
s
ca
lab
ilit
y
,
an
d
r
eu
s
ab
ilit
y
as
s
h
o
wn
in
T
ab
le
3
.
At
th
is
s
tag
e,
in
p
u
t
f
r
o
m
v
a
r
i
o
u
s
u
s
er
s
is
v
er
y
im
p
o
r
tan
t
to
en
s
u
r
e
all
r
elev
an
t
n
ee
d
s
h
av
e
b
ee
n
co
n
s
id
er
e
d
.
T
h
e
r
esu
lt
o
f
th
is
s
tag
e
is
a
c
o
m
p
r
eh
en
s
iv
e
r
eq
u
ir
em
en
ts
s
p
e
cif
icatio
n
d
o
cu
m
en
t
p
r
ep
ar
ed
u
s
in
g
th
e
I
E
E
E
8
3
0
Stan
d
ar
d
,
wh
ich
will late
r
b
e
u
s
ed
as a
g
u
id
e
in
t
h
e
d
esig
n
a
n
d
d
ev
elo
p
m
en
t
p
r
o
ce
s
s
.
Fig
u
r
e
1
.
I
DE
F0
d
iag
r
am
f
o
r
d
ev
elo
p
in
g
B
u
lu
g
h
al
-
Ma
r
am
c
h
atb
o
t
T
ab
le
2
.
Fu
n
ctio
n
al
R
eq
u
ir
em
en
ts
f
o
r
B
u
lu
g
h
al
-
Ma
r
am
c
h
a
tb
o
t
ID
R
e
q
u
i
r
e
me
n
t
s
C
a
t
e
g
o
r
y
UA1
Th
e
sy
s
t
e
m
a
l
l
o
w
s
u
sers
t
o
c
r
e
a
t
e
a
n
a
c
c
o
u
n
t
b
y
p
r
o
v
i
d
i
n
g
t
h
e
r
e
q
u
i
r
e
d
i
n
f
o
r
mat
i
o
n
,
s
u
c
h
a
s
n
a
me
,
e
ma
i
l
,
a
n
d
p
a
s
sw
o
r
d
,
a
n
d
v
e
r
i
f
y
i
n
g
t
h
e
u
ser’
s
i
d
e
n
t
i
t
y
t
h
r
o
u
g
h
a
se
c
u
r
e
a
u
t
h
e
n
t
i
c
a
t
i
o
n
mec
h
a
n
i
sm.
U
ser A
u
t
h
e
n
t
i
c
a
t
i
o
n
H
I
1
Th
e
sy
s
t
e
m
a
l
l
o
w
s
u
sers
t
o
sa
v
e
a
n
d
d
i
sp
l
a
y
a
c
h
r
o
n
o
l
o
g
y
o
f
c
h
a
t
b
o
t
q
u
e
s
t
i
o
n
s a
n
d
r
e
sp
o
n
s
e
s
H
i
st
o
r
y
TA
1
Th
e
sy
s
t
e
m
p
r
o
v
i
d
e
s
f
a
c
i
l
i
t
i
e
s
t
o
a
c
c
e
ss h
a
d
i
t
h
t
e
x
t
s
i
n
I
n
d
o
n
e
si
a
n
,
A
r
a
b
i
c
,
o
r
b
o
t
h
.
Te
x
t
A
c
c
e
ss
a
n
d
N
a
v
i
g
a
t
i
o
n
TA
2
U
sers c
a
n
e
a
s
i
l
y
q
u
e
r
y
a
n
d
n
a
v
i
g
a
t
e
p
a
r
t
s
o
f
t
h
e
h
a
d
i
t
h
b
o
o
k
,
su
c
h
a
s
c
h
a
p
t
e
r
s,
v
e
r
ses
,
a
n
d
o
t
h
e
r
p
a
r
t
s.
Te
x
t
A
c
c
e
ss
a
n
d
N
a
v
i
g
a
t
i
o
n
TA
3
U
sers c
a
n
q
u
e
r
y
c
e
r
t
a
i
n
p
a
r
t
s
o
f
t
h
e
h
a
d
i
t
h
b
a
s
e
d
o
n
k
e
y
w
o
r
d
s
i
n
t
h
e
t
e
x
t
.
Te
x
t
A
c
c
e
ss
a
n
d
N
a
v
i
g
a
t
i
o
n
LM
1
U
sers c
a
n
a
sk
q
u
e
st
i
o
n
s
a
b
o
u
t
s
p
e
c
i
f
i
c
t
e
x
t
s
a
n
d
r
e
c
e
i
v
e
e
x
p
l
a
n
a
t
i
o
n
s.
Le
a
r
n
i
n
g
M
o
d
e
s
LM
2
U
sers c
a
n
t
e
s
t
t
h
e
i
r
k
n
o
w
l
e
d
g
e
w
i
t
h
q
u
i
z
z
e
s
o
n
v
a
r
i
o
u
s
p
a
r
t
s
o
f
t
h
e
h
a
d
i
t
h
t
e
x
t
.
Le
a
r
n
i
n
g
M
o
d
e
s
N
LP1
C
h
a
t
b
o
t
s
y
st
e
ms
c
a
n
u
n
d
e
r
st
a
n
d
a
n
d
r
e
sp
o
n
d
t
o
u
ser
q
u
e
st
i
o
n
s
i
n
n
a
t
u
r
a
l
l
a
n
g
u
a
g
e
.
N
a
t
u
r
a
l
La
n
g
u
a
g
e
P
r
o
c
e
ss
i
n
g
N
LP2
Th
e
c
h
a
t
b
o
t
sy
st
e
m c
a
n
i
n
t
e
r
p
r
e
t
q
u
e
s
t
i
o
n
s
a
b
o
u
t
v
e
r
ses
o
r
c
e
r
t
a
i
n
c
o
n
c
e
p
t
s
i
n
h
a
d
i
t
h
t
e
x
t
s.
N
a
t
u
r
a
l
La
n
g
u
a
g
e
P
r
o
c
e
ss
i
n
g
C
U
1
C
h
a
t
b
o
t
s
y
st
e
ms
c
a
n
m
a
i
n
t
a
i
n
c
o
n
v
e
r
s
a
t
i
o
n
c
o
n
t
e
x
t
t
o
p
r
o
v
i
d
e
c
o
h
e
r
e
n
t
a
n
d
r
e
l
e
v
a
n
t
r
e
s
p
o
n
ses
.
C
o
n
t
e
x
t
u
a
l
U
n
d
e
r
s
t
a
n
d
i
n
g
C
U
2
U
sers c
a
n
a
sk
f
o
l
l
o
w
-
u
p
q
u
e
st
i
o
n
s
,
a
n
d
t
h
e
c
h
a
t
b
o
t
u
n
d
e
r
s
t
a
n
d
s
t
h
e
c
o
n
t
e
x
t
w
i
t
h
o
u
t
r
e
p
e
a
t
i
n
g
t
h
e
p
r
e
v
i
o
u
s
q
u
e
s
t
i
o
n
.
C
o
n
t
e
x
t
u
a
l
U
n
d
e
r
s
t
a
n
d
i
n
g
C
R
1
Th
e
c
h
a
t
b
o
t
sy
st
e
m c
a
n
p
r
o
v
i
d
e
s
u
g
g
e
st
i
o
n
s
o
r
r
e
c
o
mm
e
n
d
a
t
i
o
n
s fo
r
c
o
m
p
l
e
me
n
t
a
r
y
ma
t
e
r
i
a
l
s
b
a
se
d
o
n
u
s
e
r
r
e
q
u
e
st
s.
C
o
n
t
e
n
t
R
e
c
o
m
me
n
d
a
t
i
o
n
s
AV1
U
sers c
a
n
l
i
s
t
e
n
t
o
a
u
d
i
o
r
e
c
i
t
a
t
i
o
n
s
o
f
t
h
e
r
e
q
u
e
s
t
e
d
h
a
d
i
t
h
t
e
x
t
.
A
u
d
i
o
a
n
d
V
i
s
u
a
l
S
u
p
p
o
r
t
AV2
Th
e
sy
s
t
e
m
c
a
n
d
i
sp
l
a
y
i
ma
g
e
s,
d
i
a
g
r
a
ms,
o
r
v
i
d
e
o
s r
e
l
a
t
e
d
t
o
t
e
x
t
a
n
d
t
h
e
i
r
i
n
t
e
r
p
r
e
t
a
t
i
o
n
a
c
c
o
r
d
i
n
g
t
o
u
ser r
e
q
u
e
st
s.
A
u
d
i
o
a
n
d
V
i
s
u
a
l
S
u
p
p
o
r
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
Desig
n
s
cien
ce
r
esea
r
ch
in
d
ev
elo
p
in
g
a
r
elig
io
u
s
ch
a
tb
o
t b
a
s
ed
o
n
…
(
A
r
is
Tja
h
ya
n
to
)
2787
T
ab
le
3
.
No
n
-
f
u
n
ctio
n
al
r
e
q
u
ir
em
en
ts
f
o
r
B
u
lu
g
h
al
-
Ma
r
am
ch
atb
o
t
ID
R
e
q
u
i
r
e
me
n
t
s
C
a
t
e
g
o
r
y
N
P
1
C
h
a
t
b
o
t
s
y
st
e
ms
c
a
n
r
e
s
p
o
n
d
t
o
u
ser
q
u
e
s
t
i
o
n
s
q
u
i
c
k
l
y
a
n
d
h
a
n
d
l
e
m
u
l
t
i
p
l
e
r
e
q
u
e
s
t
s
si
mu
l
t
a
n
e
o
u
s
l
y
.
P
e
r
f
o
r
ma
n
c
e
NU1
Th
e
c
h
a
t
b
o
t
sy
st
e
m
h
a
s
a
u
ser
-
f
r
i
e
n
d
l
y
u
ser
i
n
t
e
r
f
a
c
e
d
e
si
g
n
t
h
a
t
i
s e
a
sy
t
o
n
a
v
i
g
a
t
e
a
n
d
si
m
i
l
a
r
t
o
o
t
h
e
r
c
h
a
t
b
o
t
s.
U
sab
i
l
i
t
y
N
R
1
C
h
a
t
b
o
t
s
a
r
e
a
v
a
i
l
a
b
l
e
2
4
/
7
w
i
t
h
mi
n
i
mal
d
o
w
n
t
i
m
e
.
R
e
l
i
a
b
i
l
i
t
y
N
R
2
B
a
c
k
u
p
a
n
d
r
e
c
o
v
e
r
y
me
c
h
a
n
i
sms
a
r
e
i
m
p
l
e
me
n
t
e
d
t
o
p
r
o
t
e
c
t
u
ser
d
a
t
a
.
R
e
l
i
a
b
i
l
i
t
y
N
S
1
U
ser d
a
t
a
i
s
e
n
c
r
y
p
t
e
d
a
n
d
s
t
o
r
e
d
sec
u
r
e
l
y
i
n
t
h
e
c
l
o
u
d
.
S
e
c
u
r
i
t
y
N
S
2
A
u
t
h
e
n
t
i
c
a
t
i
o
n
m
e
c
h
a
n
i
sm
s
p
r
o
t
e
c
t
u
s
e
r
a
c
c
o
u
n
t
s
f
r
o
m
u
n
a
u
t
h
o
r
i
z
e
d
a
c
c
e
ss
.
S
e
c
u
r
i
t
y
N
C
1
C
h
a
t
b
o
t
s
c
a
n
b
e
a
c
c
e
ss
e
d
o
n
v
a
r
i
o
u
s
d
e
v
i
c
e
s
,
i
n
c
l
u
d
i
n
g
smar
t
p
h
o
n
e
s,
t
a
b
l
e
t
s
,
a
n
d
d
e
s
k
t
o
p
c
o
m
p
u
t
e
r
s
.
C
o
m
p
a
t
i
b
i
l
i
t
y
N
C
1
Th
e
c
h
a
t
b
o
t
sy
st
e
m s
u
p
p
o
r
t
s m
a
n
y
o
p
e
r
a
t
i
n
g
s
y
st
e
ms
a
n
d
b
r
o
w
sers.
C
o
m
p
a
t
i
b
i
l
i
t
y
2
.
3
.
Desig
n a
nd
dev
elo
p
c
ha
t
bo
t
T
h
e
“De
s
ig
n
a
n
d
d
ev
elo
p
ch
at
b
o
t
”
s
tag
e
in
v
o
lv
es
d
esig
n
in
g
an
d
b
u
ild
in
g
a
ch
at
b
o
t
s
y
s
tem
b
ased
o
n
s
p
ec
if
ied
r
eq
u
ir
em
en
ts
.
T
h
is
s
tag
e
b
eg
i
n
s
with
s
elec
tin
g
a
c
h
atb
o
t
p
latf
o
r
m
to
en
s
u
r
e
th
at
th
e
p
r
o
to
t
y
p
e
will
b
e
d
e
v
elo
p
ed
ef
f
e
ctiv
ely
.
T
h
e
d
esig
n
o
f
th
e
ch
atb
o
t
p
r
o
to
ty
p
e
was
d
o
n
e
f
r
o
m
s
cr
atch
u
s
in
g
lib
r
ar
ies
av
ailab
le
in
Py
th
o
n
,
o
f
f
e
r
in
g
h
ig
h
f
le
x
ib
ilit
y
an
d
p
r
o
v
id
in
g
co
m
p
lete
c
o
n
tr
o
l o
v
er
th
e
tech
n
o
l
o
g
y
u
s
ed
.
T
h
e
d
esig
n
p
r
o
ce
s
s
in
clu
d
es
cr
ea
tin
g
a
ch
atb
o
t
ar
c
h
itectu
r
e,
d
esig
n
in
g
a
u
s
er
-
f
r
ie
n
d
l
y
in
ter
f
ac
e,
d
ef
in
in
g
t
h
e
ch
atb
o
t
co
n
v
er
s
a
tio
n
f
lo
w,
a
n
d
in
teg
r
atin
g
th
e
b
o
o
k
B
u
lu
g
h
al
-
Ma
r
am
as
a
k
n
o
wled
g
e
b
ase.
Dev
elo
p
m
en
t
in
v
o
lv
es
co
d
i
n
g
th
e
ch
atb
o
t,
a
p
p
ly
in
g
NL
P
alg
o
r
ith
m
s
,
an
d
d
ee
p
lea
r
n
in
g
.
T
esti
n
g
in
itially
u
s
es
a
lis
t
o
f
q
u
esti
o
n
s
s
elec
ted
an
d
d
eter
m
in
e
d
b
ased
o
n
th
e
p
r
ev
io
u
s
s
tag
e.
T
h
e
lis
t
o
f
q
u
es
tio
n
s
is
th
en
g
iv
en
d
ir
ec
tly
to
th
e
ch
atb
o
t
m
ac
h
in
e,
an
d
th
e
r
esp
o
n
s
e
is
o
b
s
er
v
e
d
.
Ap
ar
t
f
r
o
m
th
at,
test
in
g
was
also
ca
r
r
ied
o
u
t
b
y
ask
in
g
s
ev
er
al
u
s
er
s
to
ask
q
u
esti
o
n
s
ab
o
u
t
th
e
ch
at
b
o
t
p
r
o
to
ty
p
e.
User
f
ee
d
b
ac
k
is
th
en
co
llected
a
n
d
an
aly
ze
d
,
a
n
d
th
e
r
esu
lts
ar
e
u
s
ed
to
r
ef
in
e
a
n
d
im
p
r
o
v
e
th
e
ch
atb
o
t.
2
.
4
.
De
m
o
ns
t
ra
t
e
cha
t
bo
t
T
h
e
“De
m
o
n
s
tr
ate
ch
atb
o
t
”
s
tag
e
is
u
s
ed
to
d
em
o
n
s
tr
ate
th
e
ca
p
ab
ilit
ies
an
d
ef
f
ec
tiv
e
n
ess
o
f
th
e
ch
atb
o
t
p
r
o
to
t
y
p
e.
At
th
is
s
ta
g
e,
s
ev
er
al
ac
tu
al
u
s
er
s
ar
e
s
elec
ted
to
in
ter
ac
t
with
th
e
c
h
atb
o
t
a
n
d
aim
to
v
alid
ate
wh
eth
er
t
h
e
ch
atb
o
t
m
ee
ts
th
e
s
p
ec
if
ied
r
eq
u
ir
em
e
n
ts
.
User
s
ar
e
p
r
o
v
i
d
ed
with
s
ev
er
al
s
h
o
r
t
p
r
o
m
p
ts
to
ask
q
u
esti
o
n
s
in
th
eir
d
i
ctio
n
.
Feed
b
ac
k
f
r
o
m
th
is
s
tag
e
is
v
er
y
im
p
o
r
tan
t
b
ec
a
u
s
e
it
attem
p
ts
to
d
em
o
n
s
tr
ate
th
e
ch
atb
o
t'
s
s
tr
en
g
th
s
an
d
r
ev
ea
l
wea
k
n
ess
es.
I
n
ter
ac
tio
n
s
b
etwe
en
th
e
c
h
atb
o
t
an
d
th
e
u
s
er
will
b
e
s
to
r
ed
an
d
an
aly
ze
d
to
en
s
u
r
e
th
e
ch
atb
o
t
p
r
o
v
id
es
ac
cu
r
ate
an
d
f
ast
r
esp
o
n
s
es.
An
y
is
s
u
es
en
co
u
n
ter
ed
f
r
o
m
th
is
s
tag
e
will b
e
n
o
ted
a
n
d
u
s
ed
f
o
r
f
u
r
th
er
im
p
r
o
v
em
e
n
ts
.
2
.
5
.
E
v
a
lua
t
e
cha
t
bo
t
At
th
e
“
C
h
atb
o
t
ev
alu
atio
n
”
s
tag
e,
an
ev
alu
atio
n
is
ca
r
r
ied
o
u
t
r
eg
ar
d
in
g
ch
atb
o
t
u
s
er
s
'
p
er
f
o
r
m
an
ce
,
ef
f
ec
tiv
en
ess
,
an
d
s
atis
f
ac
tio
n
b
ased
o
n
p
r
e
d
eter
m
in
e
d
r
eq
u
ir
em
en
ts
an
d
o
b
jectiv
es.
E
v
alu
atio
n
at
t
h
e
“
Desig
n
an
d
d
ev
elo
p
c
h
atb
o
t
”
s
tag
e
aim
s
to
en
s
u
r
e
th
at
th
e
ch
atb
o
t
m
ee
ts
u
s
er
n
ee
d
s
an
d
allo
ws
f
o
r
r
ep
ea
ted
im
p
r
o
v
em
e
n
ts
.
Me
an
wh
ile,
th
e
ev
alu
atio
n
at
th
e
“
Dem
o
n
s
tr
ate
ch
atb
o
t
”
s
tag
e
aim
s
to
e
n
s
u
r
e
th
at
th
e
c
h
atb
o
t
en
g
in
e
ca
n
p
r
o
v
id
e
ap
p
r
o
p
r
iat
e
r
esp
o
n
s
es
to
a
p
r
ed
eter
m
in
e
d
lis
t
o
f
q
u
esti
o
n
s
.
E
v
alu
atio
n
is
ca
r
r
ied
o
u
t
b
y
m
ea
s
u
r
in
g
th
e
I
R
R
v
alu
e.
W
e
u
s
e
th
e
I
R
R
in
d
icato
r
b
ec
au
s
e
th
e
d
ata
u
s
ed
f
o
r
test
in
g
is
to
o
s
m
all
co
m
p
ar
ed
to
th
e
n
u
m
b
er
o
f
in
ten
t
lab
els.
I
R
R
is
a
m
etr
ic
u
s
ed
to
as
s
es
s
th
e
ac
cu
r
ac
y
o
f
a
ch
atb
o
t
in
id
en
tify
in
g
a
q
u
er
y
o
r
q
u
esti
o
n
p
r
o
v
id
e
d
b
y
a
u
s
er
,
s
ee
(
1
)
.
=
100%
(
1
)
W
h
er
e
C
r
ep
r
esen
ts
th
e
n
u
m
b
er
o
f
c
o
r
r
ec
tly
r
ec
o
g
n
ize
d
in
ten
ts
,
a
n
d
T
r
ep
r
esen
ts
th
e
to
tal
n
u
m
b
er
o
f
q
u
esti
o
n
s
o
r
u
tter
a
n
ce
s
.
T
h
is
m
ea
s
u
r
e
m
ea
s
u
r
es
th
e
p
r
o
p
o
r
tio
n
o
f
s
u
cc
ess
f
u
lly
r
ec
o
g
n
ized
in
ten
ts
to
th
e
to
t
al
q
u
er
ies
p
r
o
v
id
e
d
.
A
h
ig
h
I
R
R
s
co
r
e
in
d
icate
s
th
at
th
e
ch
atb
o
t c
an
u
n
d
er
s
tan
d
an
d
ca
teg
o
r
ize
t
h
e
in
p
u
t p
r
o
v
id
ed
b
y
th
e
u
s
er
.
T
h
is
m
etr
ic
is
cr
itical
f
o
r
ev
alu
atin
g
th
e
p
er
f
o
r
m
an
c
e
o
f
a
ch
atb
o
t'
s
“
Pre
p
r
o
ce
s
s
in
g
”
an
d
“
C
lass
if
ier
”
co
m
p
o
n
en
ts
.
Facto
r
s
in
f
lu
en
ci
n
g
I
R
R
in
clu
d
e
th
e
tr
ain
in
g
d
ata
q
u
ality
,
th
e
lan
g
u
ag
e
m
o
d
el's
s
o
p
h
is
ticatio
n
,
an
d
th
e
ch
atb
o
t'
s
ab
ilit
y
to
h
an
d
le
a
wid
e
r
an
g
e
o
f
p
h
r
ase
s
an
d
lan
g
u
ag
e
v
ar
iatio
n
s
.
T
h
is
ca
n
b
e
d
o
n
e
to
in
cr
ea
s
e
I
R
R
b
y
ad
d
in
g
tr
ain
in
g
d
ata
an
d
o
p
tim
izin
g
th
e
clas
s
if
ier
m
o
d
el
ar
ch
itectu
r
e.
E
v
alu
atio
n
is
also
d
o
n
e
b
y
c
o
llectin
g
q
u
esti
o
n
s
an
d
r
esp
o
n
s
es
wh
en
u
s
er
s
in
ter
ac
t
with
th
e
ch
atb
o
t.
E
ac
h
q
u
esti
o
n
will
b
e
m
atch
e
d
to
th
e
r
esp
o
n
s
e
an
d
co
m
p
a
r
ed
to
in
itial
g
o
als
an
d
ex
p
ec
t
atio
n
s
to
d
eter
m
in
e
wh
eth
er
th
e
ch
at
b
o
t
m
ee
ts
th
e
d
esire
d
s
tan
d
ar
d
s
.
An
y
d
if
f
e
r
en
ce
s
o
r
d
ef
icien
cies
a
r
e
id
e
n
t
if
ied
an
d
a
n
aly
ze
d
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.
16
,
No
.
5
,
Octo
b
e
r
20
26
:
2
7
8
2
-
2
7
9
4
2788
to
p
r
o
ce
e
d
with
th
e
n
ec
ess
ar
y
m
o
d
if
icatio
n
s
o
r
im
p
r
o
v
em
e
n
ts
.
Ov
er
all,
th
is
p
h
ase
h
elp
s
v
a
lid
ate
th
e
ch
atb
o
t'
s
f
u
n
ctio
n
ality
,
u
s
ab
ilit
y
,
an
d
o
v
er
all
im
p
ac
t,
en
s
u
r
in
g
th
e
c
h
atb
o
t is r
ea
d
y
f
o
r
b
r
o
a
d
er
im
p
le
m
en
tatio
n
.
3.
RE
SU
L
T
S AN
D
D
I
SCU
SS
I
O
N
I
n
th
is
s
ec
tio
n
,
we
p
r
esen
t
th
e
r
esu
lts
o
f
d
e
v
elo
p
in
g
a
ch
atb
o
t
to
h
elp
s
tu
d
y
th
e
h
ad
ith
co
n
tain
ed
i
n
th
e
b
o
o
k
B
u
lu
g
h
al
-
Ma
r
am
.
I
t
s
tar
ts
b
y
d
is
cu
s
s
in
g
h
o
w
to
cr
ea
te
th
e
d
ataset
u
s
ed
f
o
r
i
n
itial
ex
p
er
im
en
ts
.
T
h
en
,
it e
x
p
lain
s
h
o
w
to
c
o
n
d
u
ct
ex
p
er
im
e
n
ts
an
d
ev
al
u
ate
ch
atb
o
ts
h
an
d
lin
g
u
s
er
q
u
esti
o
n
s
.
3
.
1
.
Da
t
a
s
et
co
ns
t
ruct
io
n
T
h
e
d
ataset
is
a
cr
u
cial
p
ar
t
n
ee
d
ed
at
t
h
e
tr
ain
in
g
a
n
d
test
in
g
s
tag
e
o
f
th
e
ch
atb
o
t
class
if
ier
m
o
d
el.
B
ased
o
n
th
e
tr
ain
in
g
d
ata
p
r
o
v
id
ed
allo
ws
t
h
e
m
o
d
el
to
lear
n
d
ata
p
atter
n
s
a
n
d
r
elatio
n
s
h
i
p
s
an
d
en
s
u
r
es
th
e
m
o
d
el
ca
n
p
r
ed
ict
o
r
class
if
y
in
ten
ts
ac
co
r
d
in
g
l
y
.
T
h
e
t
esti
n
g
d
ata
in
th
is
r
esear
ch
co
n
s
is
ts
o
f
s
ev
er
al
q
u
esti
o
n
s
th
at
h
av
e
n
ev
er
b
ee
n
u
s
ed
in
p
r
ev
io
u
s
s
tag
es.
T
es
tin
g
d
ata
is
u
s
ed
to
ev
alu
ate
th
e
p
er
f
o
r
m
an
ce
an
d
ab
ilit
y
o
f
th
e
class
if
ier
m
o
d
el
to
p
r
ed
ict
a
p
p
r
o
p
r
iate
in
ten
t
b
a
s
ed
o
n
th
e
q
u
esti
o
n
s
g
iv
en
.
T
h
e
d
ataset
f
o
r
tr
ain
in
g
co
n
s
is
ts
o
f
6
4
6
h
ad
ith
s
f
r
o
m
all
1
,
3
5
4
h
ad
ith
s
in
t
h
e
b
o
o
k
B
u
lu
g
h
al
-
Ma
r
am
(
T
h
e
b
o
o
k
o
f
Pu
r
if
icatio
n
,
Pr
ay
er
,
Fu
n
e
r
als,
Z
ak
ah
,
Fas
tin
g
,
an
d
Hajj)
an
d
a
co
llectio
n
o
f
FAQs
r
elate
d
to
h
ad
ith
s
.
R
aw
d
ata
o
r
ig
in
atin
g
f
r
o
m
th
e
b
o
o
k
is
p
r
o
ce
s
s
ed
at
th
e
p
r
ep
r
o
ce
s
s
in
g
s
tag
e
an
d
lab
eled
to
m
ak
e
it
ea
s
ier
to
id
en
tify
in
ten
ts
.
I
n
t
h
e
r
esu
ltin
g
d
ataset,
ea
ch
h
ad
i
th
co
m
p
o
n
en
t
will
b
e
r
ep
r
ese
n
ted
b
y
th
e
o
r
ig
in
al
tex
t
an
d
k
e
y
wo
r
d
s
ex
tr
ac
ted
f
r
o
m
t
h
e
B
u
lu
g
h
al
-
Ma
r
am
h
a
d
ith
co
llectio
n
,
p
lu
s
s
ev
er
al
o
t
h
er
k
ey
wo
r
d
s
tak
en
f
r
o
m
FAQs
th
at
h
a
v
e
a
s
o
lid
c
o
n
n
ec
tio
n
to
t
h
e
co
n
ten
t
o
f
th
e
h
ad
ith
.
T
h
is
d
ataset
is
th
en
u
s
ed
f
o
r
th
e
tr
ain
i
n
g
p
r
o
ce
s
s
,
wh
ich
p
r
o
d
u
ce
s
th
e
in
ten
t c
lass
if
ier
m
o
d
el
u
s
ed
in
t
h
e
ch
atb
o
t
p
r
o
to
t
y
p
e.
Data
s
et
cr
ea
tio
n
co
n
s
is
ts
o
f
two
s
tag
es,
as
s
ee
n
in
Fig
u
r
e
2
.
I
n
th
e
f
ir
s
t
s
tag
e,
a
s
m
all
-
s
ca
le
d
ataset
was
cr
ea
ted
f
r
o
m
th
e
b
o
o
k
Pu
r
if
icatio
n
(
Th
a
h
a
r
a
h
)
.
T
h
is
m
in
i
d
ataset
was
m
ad
e
m
an
u
ally
with
th
e
aim
o
f
b
etter
u
n
d
er
s
tan
d
i
n
g
th
e
d
ata
m
o
d
el
th
at
will
b
e
u
s
ed
.
Sev
er
al
q
u
esti
o
n
s
o
r
u
tter
an
ce
s
ar
e
co
llected
f
o
r
ea
ch
h
ad
ith
tex
t,
wh
ich
will
b
ec
o
m
e
p
r
o
m
p
ts
f
o
r
th
e
h
ad
ith
tex
t.
Ap
ar
t
f
r
o
m
th
at,
th
e
p
r
o
m
p
t
is
also
en
r
ich
e
d
wit
h
k
ey
wo
r
d
s
e
x
tr
ac
ted
f
r
o
m
ea
c
h
h
a
d
ith
tex
t.
T
h
e
p
u
r
p
o
s
e
o
f
ad
d
i
n
g
t
h
ese
k
ey
w
o
r
d
s
is
s
o
th
at
we
ca
n
s
till
r
ec
o
g
n
ize
p
r
o
m
p
ts
o
r
q
u
esti
o
n
s
g
iv
en
b
y
u
s
er
s
b
ased
o
n
th
e
k
ey
wo
r
d
s
.
Fig
u
r
e
2
.
T
h
e
p
r
o
ce
s
s
o
f
d
atas
et
co
n
s
tr
u
ctio
n
I
n
th
e
s
ec
o
n
d
s
tag
e,
t
h
e
d
ataset
was
ad
d
ed
f
r
o
m
t
h
e
h
ad
ith
c
o
n
tain
ed
in
th
e
Pra
y
er
,
Fu
n
er
a
ls
,
Z
ak
ah
,
Fas
tin
g
,
an
d
Hajj
b
o
o
k
s
.
Sev
er
al
p
r
o
ce
s
s
es
ar
e
ca
r
r
ie
d
o
u
t
at
th
is
s
tag
e,
s
u
ch
as
co
n
v
er
tin
g
th
e
B
u
lu
g
h
al
-
Ma
r
am
tex
t
d
ata.
Star
tin
g
with
th
e
t
o
k
en
izatio
n
p
r
o
ce
s
s
co
n
tin
u
ed
b
y
ch
an
g
in
g
th
e
c
h
ar
ac
ter
s
to
lo
wer
ca
s
e,
r
em
o
v
in
g
p
u
n
ctu
atio
n
an
d
s
to
p
wo
r
d
s
,
a
n
d
th
e
n
th
e
s
tem
m
i
n
g
p
r
o
ce
s
s
r
ed
u
ce
d
th
e
wo
r
d
s
to
th
eir
b
asic
f
o
r
m
.
T
h
e
r
esu
lts
o
f
th
is
p
r
o
ce
s
s
ar
e
th
en
co
m
b
i
n
ed
with
s
ev
er
al
q
u
esti
o
n
s
o
r
p
r
o
m
p
ts
f
o
r
ea
ch
h
ad
ith
co
m
p
o
n
e
n
t
lab
eled
o
r
tag
g
e
d
to
o
b
tain
a
d
ataset
u
s
ed
f
o
r
th
is
ch
atb
o
t
p
r
o
to
ty
p
e.
T
h
e
d
ataset
s
h
o
ws
ea
ch
b
o
o
k
ca
teg
o
r
y
'
s
d
is
tr
ib
u
tio
n
in
Fig
u
r
e
3.
Du
e
to
th
e
lim
ited
n
u
m
b
er
o
f
q
u
esti
o
n
s
/u
tter
an
ce
s
co
llected
m
an
u
ally
,
th
is
p
a
p
er
also
u
til
izes
in
p
u
t
f
r
o
m
u
s
er
s
wh
o
tr
ie
d
o
u
t
th
e
c
h
atb
o
t
p
r
o
to
ty
p
e.
Af
ter
th
e
d
a
ta
f
ilter
in
g
a
n
d
clea
n
i
n
g
p
r
o
ce
s
s
is
ca
r
r
ied
o
u
t
t
o
r
em
o
v
e
o
th
er
r
ed
u
n
d
a
n
t
in
f
o
r
m
atio
n
,
s
u
c
h
as
p
u
n
ctu
atio
n
,
an
d
o
th
er
in
f
o
r
m
atio
n
th
at
m
ay
i
n
v
o
lv
e
u
s
er
p
r
iv
ac
y
,
s
u
ch
as
a
p
er
s
o
n
'
s
n
am
e.
Fin
ally
,
a
d
ataset
was
o
b
tain
ed
f
o
r
test
in
g
with
a
to
tal
o
f
a
r
o
u
n
d
1
5
0
q
u
esti
o
n
s
/u
tter
an
ce
s
,
wh
ich
w
er
e
lab
eled
as g
r
o
u
n
d
tr
u
th
.
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
Desig
n
s
cien
ce
r
esea
r
ch
in
d
ev
elo
p
in
g
a
r
elig
io
u
s
ch
a
tb
o
t b
a
s
ed
o
n
…
(
A
r
is
Tja
h
ya
n
to
)
2789
Fig
u
r
e
3
.
T
h
e
p
r
o
p
o
r
tio
n
o
f
ea
ch
ca
teg
o
r
y
in
th
e
d
ataset
3
.
2
.
E
x
perim
ent
s
et
t
ing
s
T
o
th
o
r
o
u
g
h
l
y
ass
ess
ch
atb
o
t
p
er
f
o
r
m
a
n
ce
,
we
cr
ea
ted
a
s
tr
u
ctu
r
ed
ex
p
e
r
im
en
tal
s
etu
p
d
esig
n
ed
to
m
im
ic
r
ea
l
-
wo
r
ld
co
n
v
er
s
a
tio
n
al
s
ce
n
ar
io
s
.
E
x
p
er
im
en
ts
wer
e
co
n
d
u
cted
o
n
a
co
m
p
u
ter
with
an
AM
D
R
y
ze
n
5
p
r
o
ce
s
s
o
r
5
6
0
0
H
wit
h
R
ad
eo
n
Gr
ap
h
ics 1
6
GB
R
A
M.
T
h
is
ch
atb
o
t p
r
o
to
ty
p
e
was
b
u
ilt u
s
in
g
a
d
ee
p
lear
n
in
g
m
o
d
el
in
th
e
f
o
r
m
o
f
a
f
ee
d
f
o
r
war
d
n
eu
r
al
n
etwo
r
k
d
esig
n
ed
f
o
r
m
u
lti
-
class
class
i
f
icatio
n
task
s
.
T
h
e
m
o
d
el
s
tar
ts
with
a
d
e
n
s
e
la
y
er
o
f
1
0
2
4
n
eu
r
o
n
s
,
wh
ic
h
p
r
o
ce
s
s
th
e
i
n
p
u
t
d
ata
with
t
h
e
R
eL
U
ac
tiv
atio
n
f
u
n
ctio
n
.
I
t
f
o
llo
ws
with
a
d
r
o
p
o
u
t
lay
e
r
th
at
r
an
d
o
m
ly
s
et
s
5
0
%
o
f
in
p
u
t
u
n
its
to
ze
r
o
d
u
r
in
g
tr
ai
n
in
g
to
p
r
ev
en
t o
v
er
f
itti
n
g
.
T
h
e
n
ex
t d
en
s
e
lay
er
with
1
0
2
4
n
eu
r
o
n
s
an
d
R
eL
U
ac
tiv
atio
n
f
u
r
th
er
r
ef
in
es th
e
ex
tr
ac
ted
f
ea
tu
r
es,
an
d
th
en
a
s
ec
o
n
d
d
r
o
p
o
u
t
lay
er
is
ap
p
lied
to
m
ain
tain
r
o
b
u
s
tn
ess
.
T
h
e
f
in
al
o
u
tp
u
t
lay
er
u
s
es
a
So
f
tMa
x
ac
tiv
atio
n
f
u
n
ctio
n
t
o
g
en
e
r
ate
a
p
r
o
b
ab
ilit
y
d
is
tr
i
b
u
tio
n
ac
r
o
s
s
th
e
d
i
f
f
er
en
t
o
u
t
p
u
t
class
es,
en
s
u
r
in
g
th
e
s
u
m
o
f
th
e
p
r
o
b
ab
ilit
ies
eq
u
als
o
n
e.
T
h
is
m
o
d
el
is
s
tr
u
ctu
r
ed
with
ca
teg
o
r
ical
cr
o
s
s
-
en
tr
o
p
y
as
th
e
lo
s
s
f
u
n
ctio
n
.
T
h
e
ex
p
e
r
im
en
t
in
v
o
lv
ed
a
s
er
ies
o
f
u
s
er
in
ter
ac
tio
n
s
,
m
o
s
tly
s
im
p
le
q
u
esti
o
n
s
,
to
test
th
e
ch
atb
o
t'
s
ab
ilit
y
to
u
n
d
e
r
s
tan
d
co
n
te
x
t
an
d
g
en
e
r
ate
ac
cu
r
ate
r
esp
o
n
s
es.
T
h
e
d
ataset
is
d
iv
id
ed
in
t
o
tr
ain
in
g
d
ata
an
d
v
alid
atio
n
d
ata
f
o
r
test
in
g
.
T
h
e
p
er
f
o
r
m
an
ce
m
et
r
ics
in
clu
d
e
tr
ain
in
g
an
d
v
alid
atio
n
ac
cu
r
ac
y
an
d
I
R
R
.
T
h
e
ch
atb
o
t
p
r
o
to
ty
p
e
ca
n
b
e
ac
ce
s
s
ed
v
ia
th
e
ad
d
r
ess
h
ttp
:
//1
0
1
.
5
0
.
3
.
1
2
1
:
3
0
0
0
,
w
h
ile
th
e
p
r
o
ce
s
s
s
eq
u
en
ce
f
r
o
m
s
tar
t to
tr
ial
ca
n
b
e
s
ee
n
in
t
h
e
ch
atb
o
t a
r
ch
itectu
r
e
in
Fig
u
r
e
4.
Fig
u
r
e
4
.
T
h
e
ar
ch
itectu
r
e
o
f
t
h
e
p
r
o
p
o
s
ed
m
o
d
el
Pre
p
r
o
ce
s
s
in
g
aim
s
to
p
r
e
p
ar
e
th
e
d
ataset
n
ee
d
ed
t
o
tr
ain
an
d
test
th
e
m
o
d
el.
T
h
is
p
r
o
ce
s
s
in
v
o
lv
es
ch
an
g
in
g
to
l
o
wer
ca
s
e,
clea
n
i
n
g
u
n
n
ec
ess
ar
y
c
h
ar
ac
ter
s
,
r
e
m
o
v
in
g
s
to
p
wo
r
d
s
,
an
d
s
tem
m
in
g
.
I
n
g
en
er
al,
th
is
p
r
o
ce
s
s
will
p
r
o
d
u
ce
a
clea
n
i
n
ten
ts
d
atab
ase
th
at
ca
n
p
r
o
v
i
d
e
a
class
if
ier
m
o
d
el
with
g
o
o
d
p
er
f
o
r
m
a
n
ce
an
d
p
r
ed
ict
th
e
in
ten
t
o
f
a
g
iv
en
q
u
esti
o
n
.
T
h
e
p
r
o
p
o
s
ed
m
o
d
el
i
s
b
u
ilt
u
s
in
g
T
en
s
o
r
Flo
w
an
d
Ker
as
.
T
h
is
m
o
d
el,
wh
ich
h
as
a
f
ee
d
f
o
r
war
d
ar
c
h
i
tectu
r
e
(
as
s
h
o
wn
in
Fig
u
r
e
5
,
h
as
th
r
ee
m
ain
lay
er
s
:
an
in
p
u
t
lay
er
with
1
,
0
2
4
n
eu
r
o
n
s
an
d
a
R
eL
U
ac
tiv
atio
n
f
u
n
ctio
n
,
f
o
llo
wed
b
y
a
d
r
o
p
o
u
t
lay
er
(
0
.
5
)
to
r
e
d
u
ce
o
v
e
r
f
itti
n
g
b
y
r
an
d
o
m
ly
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.
16
,
No
.
5
,
Octo
b
e
r
20
26
:
2
7
8
2
-
2
7
9
4
2790
ig
n
o
r
in
g
5
0
%
o
f
n
e
u
r
o
n
s
d
u
r
i
n
g
tr
ain
in
g
s
o
th
at
th
e
m
o
d
el
b
ec
o
m
es
m
o
r
e
g
e
n
er
alis
t
an
d
less
d
ep
en
d
en
t
o
n
tr
ain
in
g
d
ata.
T
h
en
,
t
h
er
e
is
a
s
ec
o
n
d
h
id
d
en
lay
e
r
with
1
,
0
2
4
n
eu
r
o
n
s
,
a
R
eL
U
ac
tiv
atio
n
f
u
n
ctio
n
,
an
d
th
e
s
am
e
d
r
o
p
o
u
t
f
o
r
tr
ain
in
g
s
tab
ilizatio
n
.
Fin
ally
,
th
e
m
o
d
el
h
as
an
o
u
tp
u
t
lay
er
with
7
9
4
n
eu
r
o
n
s
.
I
t
u
s
es
So
f
tMa
x
ac
tiv
atio
n
,
wh
ic
h
is
s
u
itab
le
f
o
r
m
u
lti
-
class
.
Fig
u
r
e
5
.
Pro
p
o
s
ed
n
eu
r
al
n
et
wo
r
k
ar
ch
itectu
r
e
f
o
r
B
u
lu
g
h
-
al
Ma
r
am
ch
atb
o
t
3
.
3
.
T
ra
ini
ng
t
he
mo
dels
A
ce
r
tain
am
o
u
n
t
o
f
tr
ain
in
g
d
ata
is
p
r
o
v
id
ed
at
th
e
tr
ain
in
g
s
tag
e
s
o
th
e
class
if
ier
m
o
d
el
ca
n
r
ec
o
g
n
ize
th
e
q
u
esti
o
n
s
'
in
ten
t.
T
h
e
c
h
atb
o
t
class
if
ier
m
o
d
el
f
ac
es
a
d
ataset
with
k
n
o
wn
f
ea
tu
r
es
an
d
tag
s
o
r
class
lab
els,
allo
win
g
th
e
m
o
d
el
to
lear
n
p
atter
n
s
an
d
r
elatio
n
s
h
ip
s
b
etwe
en
i
n
p
u
t
f
ea
tu
r
es
an
d
tar
g
et
class
es.
I
n
th
is
r
esear
ch
,
f
ea
tu
r
es
a
r
e
o
b
tain
ed
b
y
ap
p
l
y
in
g
t
h
e
b
ag
o
f
wo
r
d
s
(
B
OW
)
alg
o
r
ith
m
to
th
e
r
esu
lts
o
f
p
r
ep
r
o
ce
s
s
in
g
h
ad
ith
tex
ts
,
wh
er
e
ea
ch
h
ad
ith
will
b
e
g
i
v
en
a
d
if
f
er
en
t
tag
o
r
lab
el.
T
h
e
tr
ain
ed
ch
atb
o
t
class
if
ier
will th
en
p
r
ed
ict
th
e
class
o
r
in
ten
t o
f
th
e
q
u
esti
o
n
s
g
iv
en
.
I
n
th
e
tr
ain
in
g
s
tag
e,
s
ev
er
al
m
etr
ics
ar
e
r
ec
o
r
d
ed
as
tr
ain
i
n
g
h
is
to
r
y
in
v
o
lv
in
g
a
n
aly
s
is
o
f
ac
cu
r
ac
y
p
lo
ts
o
v
er
a
ce
r
tain
ep
o
c
h
r
a
n
g
e
to
ev
alu
ate
t
h
e
m
o
d
el
p
er
f
o
r
m
an
ce
d
u
r
in
g
tr
ain
in
g
.
I
n
Fig
u
r
e
6
,
th
e
tr
ain
i
n
g
cu
r
v
e
s
h
o
ws
a
g
r
ad
u
al
in
cr
ea
s
e
in
ac
cu
r
ac
y
,
with
th
e
v
alid
atio
n
m
etr
ics
tr
ailin
g
th
e
tr
ain
in
g
m
etr
ics
u
n
til
ar
o
u
n
d
ep
o
c
h
6
.
Desp
ite
th
e
d
if
f
er
en
ce
s
b
etwe
en
th
e
tr
ain
in
g
an
d
v
alid
atio
n
c
u
r
v
es,
th
e
m
o
d
el
p
er
f
o
r
m
s
well
o
n
th
e
v
alid
atio
n
d
ata.
Sev
er
al
q
u
esti
o
n
s
/u
tter
an
ce
s
ar
e
g
iv
en
t
o
v
alid
ate
th
e
ch
a
tb
o
t
m
o
d
el,
as
s
ee
n
in
T
ab
le
4
.
I
n
te
n
t
p
r
ed
ictio
n
in
th
is
ch
atb
o
t
p
r
o
t
o
ty
p
e
aim
s
to
u
n
d
er
s
tan
d
t
h
e
q
u
esti
o
n
s
ask
ed
b
y
th
e
u
s
er
.
T
h
is
p
r
o
ce
s
s
in
v
o
lv
es
tex
t
an
aly
s
is
o
f
q
u
esti
o
n
s
g
iv
en
b
y
th
e
u
s
er
an
d
class
if
y
in
g
th
em
in
to
p
r
e
d
eter
m
in
ed
class
lab
els.
B
ef
o
r
e
th
e
class
if
icatio
n
p
r
o
ce
s
s
o
r
i
n
te
n
t
r
ec
o
g
n
itio
n
,
an
in
itial
ex
a
m
in
atio
n
is
co
n
d
u
cte
d
to
d
et
er
m
in
e
wh
eth
e
r
th
e
q
u
esti
o
n
s
'
m
ea
n
in
g
is
clea
r
.
I
f
it
is
u
n
clea
r
,
th
e
ch
atb
o
t
will
tr
y
to
clar
if
y
it
to
th
e
u
s
er
.
I
f
th
e
q
u
esti
o
n
is
clea
r
,
a
p
r
o
ce
s
s
will
b
e
ca
r
r
ied
o
u
t
to
r
ec
o
g
n
ize
th
e
in
ten
t
u
s
in
g
an
in
ten
t
class
if
ier
.
B
y
id
e
n
tify
in
g
u
s
er
in
ten
t,
ch
atb
o
ts
ca
n
p
r
o
v
id
e
r
elev
a
n
t
an
d
co
n
tex
tu
alize
d
r
esp
o
n
s
es.
I
n
ten
t
p
r
ed
ictio
n
is
cr
itical
t
o
en
s
u
r
in
g
th
at
th
e
ch
atb
o
t
in
ter
p
r
ets
u
s
er
q
u
esti
o
n
s
co
r
r
ec
tly
.
B
ased
o
n
th
e
in
ten
t
p
r
ed
ictio
n
r
esu
lts
,
it
will
s
ea
r
ch
f
o
r
th
e
ap
p
r
o
p
r
iate
an
s
wer
in
th
e
d
ata
b
ase
an
d
p
r
o
v
id
e
it to
th
e
u
s
er
.
I
n
ten
t
p
r
ed
ictio
n
s
ar
e
d
eter
m
in
ed
b
ased
o
n
th
e
p
r
o
b
a
b
ilit
y
d
is
tr
ib
u
tio
n
v
alu
es
p
r
o
d
u
c
ed
b
y
th
e
ch
atb
o
t
in
ten
t
class
if
ier
.
T
h
e
h
ig
h
est
p
r
o
b
a
b
ilit
y
will
b
e
s
elec
ted
as
th
e
p
r
ed
icted
in
ten
t,
s
h
o
win
g
th
e
m
o
d
el's
co
n
f
id
en
ce
in
th
e
i
n
ten
t
class
if
icatio
n
.
T
h
e
s
elec
tio
n
u
s
es
th
e
a
r
g
ma
x
f
u
n
ctio
n
,
wh
ich
i
d
en
tifie
s
th
e
in
d
ex
with
th
e
h
ig
h
est
p
r
o
b
ab
ilit
y
an
d
m
ee
ts
th
e
th
r
esh
o
l
d
v
a
lu
e
to
en
s
u
r
e
th
e
m
o
d
el
co
n
f
id
en
ce
m
ee
ts
th
e
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
Desig
n
s
cien
ce
r
esea
r
ch
in
d
ev
elo
p
in
g
a
r
elig
io
u
s
ch
a
tb
o
t b
a
s
ed
o
n
…
(
A
r
is
Tja
h
ya
n
to
)
2791
m
in
im
u
m
lev
el.
I
f
th
e
h
ig
h
est
p
r
o
b
ab
ilit
y
v
alu
e
is
b
elo
w
th
is
th
r
esh
o
ld
,
th
en
th
e
q
u
esti
o
n
g
iv
en
b
y
th
e
u
s
er
ca
n
b
e
class
if
ied
as
“
u
n
k
n
o
w
n
”
o
r
“
u
n
ce
r
tai
n
.
”
Ap
ar
t
f
r
o
m
th
at,
th
e
class
if
ier
m
o
d
el
ca
n
also
p
r
o
d
u
ce
m
o
r
e
th
an
o
n
e
in
ten
t
p
r
ed
ictio
n
o
r
h
as
m
an
y
an
s
wer
s
,
wh
ich
m
ea
n
s
th
er
e
is
m
o
r
e
th
a
n
o
n
e
h
ad
it
h
th
at
is
co
n
s
id
er
ed
to
m
atch
th
e
q
u
esti
o
n
/u
tter
an
c
e
g
iv
en
.
Fig
u
r
e
6
.
C
h
atb
o
t
in
ten
t c
lass
if
ier
m
o
d
el
v
alid
atio
n
T
ab
le
4
.
E
x
am
p
les o
f
q
u
esti
o
n
s
/u
tter
an
ce
s
an
d
in
ten
t p
r
ed
ictio
n
#
Q
u
e
st
i
o
n
s
/
U
t
t
e
r
a
n
c
e
s
P
r
e
d
i
c
t
e
d
I
n
t
e
n
t
s
I
n
d
o
n
e
si
a
n
En
g
l
i
sh
1
t
o
l
o
n
g
t
u
n
j
u
k
k
a
n
d
a
f
t
a
r
h
a
d
i
t
s
p
a
d
a
k
i
t
a
b
s
h
a
l
a
t
p
l
e
a
se
sh
o
w
m
e
t
h
e
l
i
s
t
o
f
h
a
d
i
t
h
s
i
n
t
h
e
b
o
o
k
o
f
p
r
a
y
e
r
h
a
d
i
t
sk
i
t
a
b
2
b
a
g
a
i
ma
n
a
n
a
i
k
h
a
j
i
h
o
w
t
o
g
o
o
n
p
i
l
g
r
i
ma
g
e
p
r
o
s
e
sca
r
a
3
a
p
a
k
a
h
sh
a
l
a
t
t
a
h
a
j
u
d
w
h
a
t
i
s
t
h
e
t
a
h
a
j
j
u
d
p
r
a
y
e
r
?
t
a
n
y
a
a
p
a
k
a
h
4
a
p
a
k
a
h
sh
a
l
a
t
mal
a
m
w
h
a
t
i
s
n
i
g
h
t
p
r
a
y
e
r
?
t
a
n
y
a
a
p
a
k
a
h
5
a
p
a
k
a
h
sh
o
l
a
t
su
b
u
h
?
w
h
a
t
i
s
mo
r
n
i
n
g
p
r
a
y
e
r
?
t
a
n
y
a
a
p
a
k
a
h
6
b
e
r
a
p
a
r
a
k
a
a
t
s
h
o
l
a
t
s
u
b
u
h
?
h
o
w
ma
n
y
r
a
k
a
a
h
s
i
s
t
h
e
m
o
r
n
i
n
g
p
r
a
y
e
r
?
t
a
n
y
a
b
e
r
a
p
a
7
b
a
g
a
i
ma
n
a
sh
o
l
a
t
su
b
u
h
d
i
l
a
k
s
a
n
a
k
a
n
?
h
o
w
i
s
t
h
e
m
o
r
n
i
n
g
p
r
a
y
e
r
p
e
r
f
o
r
me
d
?
p
r
o
s
e
sca
r
a
8
men
g
a
p
a
sh
o
l
a
t
su
b
u
h
d
u
a
r
a
k
a
a
t
?
w
h
y
d
o
e
s
t
h
e
mo
r
n
i
n
g
p
r
a
y
e
r
h
a
v
e
t
w
o
r
a
k
a
a
h
s
?
t
a
n
y
a
me
n
g
a
p
a
9
a
p
a
k
a
h
sh
o
l
a
t
su
b
u
h
d
u
a
r
a
k
a
a
t
?
i
s t
h
e
m
o
r
n
i
n
g
p
r
a
y
e
r
t
w
o
r
a
k
a
a
h
s?
t
a
n
y
a
a
p
a
k
a
h
10
b
a
g
a
i
ma
n
a
j
i
k
a
t
e
l
a
t
me
l
a
k
sa
n
a
k
a
n
s
h
o
l
a
t
s
u
b
u
h
?
w
h
a
t
i
f
y
o
u
a
r
e
l
a
t
e
f
o
r
m
o
r
n
i
n
g
p
r
a
y
e
r
s?
p
r
o
s
e
sca
r
a
11
b
a
g
a
i
ma
n
a
a
p
a
b
i
l
a
l
u
p
a
s
h
o
l
a
t
s
u
b
u
h
?
w
h
a
t
i
f
y
o
u
f
o
r
g
e
t
t
h
e
mo
r
n
i
n
g
p
r
a
y
e
r
?
sh
a
l
a
t
3
0
5
12
a
p
a
sa
j
a
h
a
d
i
t
s
t
e
r
k
a
i
t
sh
o
l
a
t
su
b
u
h
?
w
h
a
t
a
r
e
t
h
e
h
a
d
i
t
h
s r
e
l
a
t
e
d
t
o
m
o
r
n
i
n
g
p
r
a
y
e
r
s?
men
y
e
b
u
t
k
a
n
13
a
p
a
s
h
o
l
a
t
y
a
n
g
d
i
l
a
k
s
a
n
a
k
a
n
se
b
e
l
u
m
sh
o
l
a
t
su
b
u
h
?
w
h
a
t
p
r
a
y
e
r
s a
r
e
p
e
r
f
o
r
me
d
b
e
f
o
r
e
t
h
e
mo
r
n
i
n
g
p
r
a
y
e
r
?
sh
a
l
a
t
9
7
14
a
p
a
k
a
h
a
d
a
s
h
o
l
a
t
s
u
n
n
a
h
se
t
e
l
a
h
s
h
o
l
a
t
s
u
b
u
h
?
i
s t
h
e
r
e
a
su
n
n
a
h
p
r
a
y
e
r
a
f
t
e
r
t
h
e
m
o
r
n
i
n
g
p
r
a
y
e
r
?
t
a
n
y
a
a
p
a
k
a
h
15
a
p
a
k
a
h
b
o
l
e
h
b
e
r
w
u
d
l
u
d
e
n
g
a
n
a
i
r
l
a
u
t
i
s i
t
p
e
r
m
i
ssi
b
l
e
t
o
p
e
r
f
o
r
m
a
b
l
u
t
i
o
n
w
i
t
h
se
a
w
a
t
e
r
?
t
a
n
y
a
a
p
a
k
a
h
16
b
o
l
e
h
k
a
h
w
u
d
l
u
p
a
k
a
i
a
i
r
l
a
u
t
c
a
n
I
u
se
s
e
a
w
a
t
e
r
f
o
r
a
b
l
u
t
i
o
n
?
j
e
n
a
z
a
h
1
2
17
a
p
a
k
a
h
a
i
r
l
a
u
t
i
t
u
s
u
c
i
?
i
s se
a
w
a
t
e
r
p
u
r
e
?
t
a
n
y
a
a
p
a
k
a
h
18
a
p
a
k
a
h
a
i
r
l
a
u
t
s
u
c
i
?
i
s se
a
w
a
t
e
r
p
u
r
e
?
t
a
n
y
a
a
p
a
k
a
h
19
a
i
r
l
a
u
t
s
u
c
i
p
u
r
e
se
a
w
a
t
e
r
t
h
a
h
a
r
a
h
1
3
.
4
.
Co
m
pa
riso
n o
f
t
he
re
s
ults
T
h
e
p
e
r
f
o
r
m
an
ce
o
f
th
e
i
n
ten
t
class
if
ier
is
ev
alu
ated
u
s
in
g
th
e
I
R
R
m
etr
ic,
w
h
ich
is
u
s
ed
to
ass
ess
th
e
ch
atb
o
t'
s
ac
cu
r
ac
y
in
p
r
e
d
ictin
g
in
ten
t
b
ased
o
n
th
e
q
u
esti
o
n
s
p
r
o
v
i
d
ed
.
T
h
is
ex
p
er
im
e
n
t
o
b
tain
ed
a
n
I
R
R
o
f
8
6
.
8
2
%,
wh
ich
is
q
u
ite
g
o
o
d
ev
en
th
o
u
g
h
it
o
n
ly
u
s
ed
B
OW
f
ea
tu
r
es
ex
tr
ac
ted
f
r
o
m
q
u
esti
o
n
s
/u
tter
an
ce
s
.
T
h
e
I
R
R
v
alu
e
is
n
o
t
y
et
m
a
x
im
al,
p
ar
tly
d
u
e
to
t
h
e
u
s
e
o
f
ter
m
s
d
if
f
er
en
t
f
r
o
m
th
e
q
u
esti
o
n
s
g
iv
en
to
th
e
ter
m
s
wr
itten
in
th
e
B
u
lu
g
h
al
-
Ma
r
am
b
o
o
k
.
Fo
r
e
x
am
p
le,
I
n
d
o
n
esian
p
eo
p
le
u
s
u
ally
u
s
e
th
e
ter
m
s
“
p
er
g
i
h
aji
,
”
“
b
ay
ar
za
k
at
”
wh
ich
ar
e
n
o
t
k
n
o
wn
in
B
u
lu
g
h
al
-
M
ar
am
.
B
ec
au
s
e
th
is
p
r
o
to
ty
p
e
o
n
ly
u
s
es
s
tan
d
ar
d
ter
m
in
o
lo
g
y
f
o
u
n
d
in
th
e
B
u
lu
g
h
al
-
Ma
r
am
b
o
o
k
,
q
u
esti
o
n
s
s
u
ch
as
“
B
ag
aim
an
a
p
er
h
itu
n
g
an
b
a
y
ar
za
k
at?
”
ca
n
n
o
t
b
e
an
s
wer
ed
s
atis
f
ac
to
r
ily
.
Un
til
th
is
ex
p
er
im
en
t
was
ca
r
r
ied
o
u
t,
id
en
tific
atio
n
an
d
co
llectio
n
o
f
n
o
n
-
s
tan
d
ar
d
ter
m
s
o
f
ten
u
s
ed
d
a
ily
wer
e
s
till
b
ein
g
ca
r
r
ied
o
u
t
s
o
th
at
th
e
class
if
ier
'
s
p
er
f
o
r
m
an
ce
co
u
ld
b
e
f
u
r
th
er
im
p
r
o
v
ed
.
Evaluation Warning : The document was created with Spire.PDF for Python.