[PPT] - C L - N L P A N a t u r a l L a n g u a g e P PowerPoint Presentation

SLIDE 1

C L

N

L P – A N a t u r a l L a n g u a g e P r

c

e s s i n g L i b r a r y f

r

C

m

m

n

L i s p

V s e v

l
d

D y

m

k i n E u r

p

e a n L i s p S y m p

s

i u m 2 1 3

6
4

SLIDE 2

T

p

i c s

* M

t

i v a t i

n

* L i b r a r y h i g h

l

e v e l d e s i g n * O v e r v i e w

f

t h e f u n c t i

n

s * S

m

e t e c h n i c a l d e t a i l s * N e x t s t e p s

SLIDE 3

M

t

i v a t i

n

N L P & L i s p i s a m a t c h , m a d e i n h e a v e n

SLIDE 4

O t h e r l a n g u a g e s

* f

r

P y t h

n

: N L T K * f

r

J a v a : S t a n f

r

d C

r

e N L P a n d O p e n N L P

SLIDE 5

P r e v i

u

s W

r

k

* C L

L

a n g u t i l s * L e x i p a r s e , S p a r s e r , C L

E

A R L Y

P

A R S E R , B a s i c

E

n g l i s h

G

r a m m a r * W

r

d n e t i n t e r f a c e s * C M U A I R e p

s

i t

r

y * N a t u r a l L a n g u a g e U n d e r s t a n d i n g * N a t u r a l L a n g u a g e P r

c

e s s i n g i n L i s p

SLIDE 6

E s s e n t i a l S c

p

e

* C

r

p

r

a i n t e r f a c e s * L a n g u a g e m

d

e l i n g * M e a s u r e s * T

k

e n i z a t i

n

* T a g g i n g * P a r s i n g * W

r

d n e t i n t e r f a c e * C

n

s t r u c t a p i p e l i n e

SLIDE 7

R

a

d m a p

V e r s i

n

. 1 : t h e b a s e s y s t e m w i t h a t e s t s u i t e a n d m a n u a l V e r s i

n

1 . : s e v e r a l w e l l

p

t i m i z e d v e r s i

n

s

f

m

s

t a l g

r

i t h m s w i t h f u l l d

c

u m e n t a t i

n

SLIDE 8

B e y

n

d v . 1 .

A n

t

h e r s y s t e m

m

e t a

n

l p

SLIDE 9

D e v e l

p

m e n t m e t h

d
l
g

y

. . .

d

r i v e n d e v e l

p

m e n t

SLIDE 10

H i g h

l

e v e l D e s i g n

* c l

n

l p & c l

n

l p

c
n

t r i b & m

r

e * b a s e & f u n c t i

n

a l p a c k a g e s * n l p

u

s e r

SLIDE 11

S

m

e D e s i g n C h

i

c e s

* A p s e u d

h

i e r a r c h i c a l p a c k a g e d e s i g n

SLIDE 12

M

d

u l e s

* n l p . c

r

e , n l p . c

r

p

r

a , n l p . u t i l , n l p . t e s t

u

t i l * n l p . s y n t a x , n l p . g e n e r a t i

n

, n l p . p h

n

e t i c s * n l p . c

n

t r i b . w

r

d n e t , n l p . c

n

t r i b . m s

n

g r a m s

SLIDE 13

S

m

e D e s i g n C h

i

c e s

* U s e t h e w h

l

e l a n g u a g e

d

e f c l a s s & d e f s t r u c t

h

a s h

t

a b l e s & a l i s t s

d
&

l

p

SLIDE 14

S

m

e D e s i g n C h

i

c e s

* G r

w

t h e l a n g u a g e

r

u t i l s + r e a d e r m a c r

s

+ s h

r

t h a n d s + d

t

a b l e , d

l

i n e s

s

p e c i a l

p

u r p

s

e u t i l s

SLIDE 15

A S p e c i a l

P

u r p

s

e U t i l

( d e f i n e

l

a z y

s

i n g l e t

n

w

r

d

t
k

e n i z e r ( m a k e ' p

s

t p r

c

e s s i n g

r

e g e x

w
r

d

t
k

e n i z e r ) " D e f a u l t w

r

d t

k

e n i z e r . " ) ( d e f u n t

k

e n i z e

n

g r a m ( n g r a m s s t r ) " T r a n s f

r

m s t r i n g S T R t

a

l i s t i f n e c e s s a r y ( d e p e n d i n g

f
r

d e r

f

N G R A M S ) . " ( i f ( > ( n g r a m s

r

d e r n g r a m s ) 1 ) ( t

k

e n i z e < w

r

d

t
k

e n i z e r > s t r ) s t r ) )

SLIDE 16

A S p e c i a l

P

u r p

s

e U t i l

( d e f m a c r

d

e f i n e

l

a z y

s

i n g l e t

n

( n a m e i n i t &

p

t i

n

a l d

c

s t r i n g ) ( w i t h

g

e n s y m s ( s i n g l e t

n

) ` ( l e t ( , s i n g l e t

n

) ( d e f u n , n a m e ( ) , d

c

s t r i n g (

r

, s i n g l e t

n

( s e t f , s i n g l e t

n

, i n i t ) ) ) ( d e f i n e

s

y m b

l
m

a c r

,

( m k s y m n a m e : f

r

m a t " < ~ A > " ) ( , n a m e ) ) ) ) )

SLIDE 17

S

m

e D e s i g n C h

i

c e s

* U s e C L O S a s a f

u

n d a t i

n

SLIDE 18

B a s i c C e l l

( d e f c l a s s r e g e x

w
r

d

t
k

e n i z e r ( t

k

e n i z e r ) ( ( r e g e x : a c c e s s

r

t

k

e n i z e r

r

e g e x : i n i t a r g : r e g e x : i n i t f

r

m ( r e : c r e a t e

s

c a n n e r " \ \ w + | [ ! \ " # $ % & ' * + , . / : ; < = > ? @ ^ ` ~ … \ \ ( \ \ ) { } \ \ [ \ \ | \ \ ] « » “ ” ‘ ’ ¶

]

" ⟨⟩ ‒–—― ) : d

c

u m e n t a t i

n

" A s i m p l e r v a r i a n t w

u

l d b e [ ^ \ \ s ] + — i t d

e

s n ' t s p l i t p u n c t u a t i

n

, y e t s

m

e t i m e s i t ' s d e s i r a b l e . " ) ) ( : d

c

u m e n t a t i

n

" R e g e x

b

a s e d w

r

d t

k

e n i z e r . " ) )

SLIDE 19

B a s i c C e l l

( d e f m e t h

d

t

k

e n i z e ( ( t

k

e n i z e r r e g e x

w
r

d

t
k

e n i z e r ) s t r i n g ) ( l

p

: f

r

( b e g e n d ) :

n

( r e : a l l

m

a t c h e s ( t

k

e n i z e r

r

e g e x t

k

e n i z e r ) s t r i n g ) : b y # ' c d d r : c

l

l e c t ( s u b s t r i n g b e g e n d ) : i n t

w
r

d s : c

l

l e c t ( c

n

s b e g e n d ) : i n t

s

p a n s : f i n a l l y ( r e t u r n ( v a l u e s w

r

d s s p a n s ) ) )

SLIDE 20

A n

t

h e r E x a m p l e

( d e f g e n e r i c p a r s e ( m

d

e l s e n t e n c e ) ( : d

c

u m e n t a t i

n

" P a r s e S E N T E N C E w i t h M O D E L . " ) ( : m e t h

d

: a r

u

n d ( m

d

e l ( s e n t e n c e s t r i n g ) ) ( c a l l

n

e x t

m

e t h

d

m

d

e l ( t

k

e n i z e < w

r

d

t
k

e n i z e r > s t r i n g ) ) ) ) ( d e f g e n e r i c p a r s e

n

( m

d

e l s e n t e n c e n ) ( : d

c

u m e n t a t i

n

" R e t u r n N b e s t p a r s e t r e e s

f

t h e S E N T E N C E w i t h M O D E L . " ) ( : m e t h

d

: a r

u

n d ( m

d

e l ( s e n t e n c e s t r i n g ) n ) ( c a l l

n

e x t

m

e t h

d

m

d

e l ( t

k

e n i z e < w

r

d

t
k

e n i z e r > s t r i n g ) n ) ) )

SLIDE 21

A v a i l a b l e f u n c t i

n

s

* c h a r , w

r

d s a n d t r e e s h e l p e r s * m e a s u r e s : e n t r

p

y , L L R * l a n g u a g e m

d

e l i n g ( n g r a m s ) * w

r

d t

k

e n i z a t i

n

a n d s e n t e n c e s p l i t t i n g * M a r k

v

c h a i n

b

a s e d g e n e r a t i

n

SLIDE 22

A v a i l a b l e f u n c t i

n

s

* i n t e r f a c e t

c
r

p

r

a :

B

r

w

n

R

e u t e r s

P

e n n T r e e b a n k

N

P S C h a t * t a g g i n g : H M M a n d G L M * p a r s i n g : P C F G & k

b

e s t P C F G * W

r

d n e t i n t e r f a c e

SLIDE 23

P a r s i n g

( d e f m e t h

d

p a r s e ( ( g r a m m a r p c f g ) ( s e n t e n c e l i s t ) ) ( C K Y ( l e t * ( ( c u r ( c

n

s r u l e ( 1

s

) ) ) ( l ( @ p i ( 1

i

) ( 1

s

) ( s e c

n

d r u l e ) ) ) ( r ( @ p i s ( 1

j

) ( t h i r d r u l e ) ) ) ( s c

r

e ( i f ( a n d l r ) ( + ( l

g

q ) l r ) m i n ) ) ) ( w h e n ( > s c

r

e (

r

m a x m i n ) ) ( s e t f m a x s c

r

e a r g c u r ) ) ) ) )

SLIDE 24

P a r s i n g

( d e f m e t h

d

p a r s e : a r

u

n d ( ( g r a m m a r p c f g ) ( s e n t e n c e l i s t ) ) ( w i t h

r

a w

r

e s u l t s ( v a l u e s ( i d x

>

n t s ( d e c

d

e

p

a r s e

t

r e e s e n t e n c e b p s l a s t i r

t

) ) ( e x p (

r

( @ p i l a s t i r

t

) m i n ) ) p i b p s ) ) )

SLIDE 25

( m a c r

l

e t ( ( C K Y ( & b

d

y b

d

y ) ` ( w i t h

s

l

t

s ( r u l e s n t s

>

i d x ) g r a m m a r ( l e t * ( ( p i # { } ) ( b p s # { } ) ; ; a l s

n

e e d t

i

n i t t h e m ( m i n m

s

t

n

e g a t i v e

s

i n g l e

f

l

a

t ) ) ( d

(

( p

s

1 ( 1 + p

s

) ) ) ( ( > = p

s

* s e n t e n c e

l

e n g t h * ) ) ( d

(

( i 1 ( 1 + i ) ) ) ( ( > i (

*

s e n t e n c e

l

e n g t h * p

s

) ) ) ( l e t ( ( j ( + i p

s

) ) ) ( d

t

a b l e ( _ k n t s

>

i d x ) ( l e t ( m a x a r g ) ( d

(

( s i ( 1 + s ) ) ) ( ( > = s j ) ) ( d

t

a b l e ( r u l e q r u l e s ) ( w h e n ( a n d ( t r y a d i c r u l e ) ( = k ( f i r s t r u l e ) ) ) , @ b

d

y ) ) ) ( w h e n ( i f ( l i s t p m a x ) m a x ( > m a x m i n ) ) ( s e t f ( @ p i ( 1

i

) ( 1

j

) k ) m a x ( @ b p s ( 1

i

) ( 1

j

) k ) a r g ) ) ) ) ) ) ) ( v a l u e s p i b p s ) ) ) ) )

SLIDE 26

( d e c l a i m ( i n l i n e @ ) ) ( d e f u n @ ( m i j k ) ( g e t # ( + ( * i * s e n t e n c e

l

e n g t h * * n t

c
u

n t * ) ( * j * n t

c
u

n t * ) k ) m ) ) ( d e f s e t f @ ( m i j k ) ( v ) ` ( s e t # ( + ( * , i * s e n t e n c e

l

e n g t h * * n t

c
u

n t * ) ( * , j * n t

c
u

n t * ) , k ) , m , v ) )

SLIDE 27

C L

N

L P C h a l l e n g e s

* B u i l d i n g a t e s t s u i t e

r

e g r e s s i

n

t e s t s

q

u a l i t y t e s t s * M

d

e l s e r i a l i z a t i

n

a n d d i s t r i b u t i

n

f

r

m a t * I m p l e m e n t i n g a l l t h e a l g

r

i t h m s (

b

v i

u

s l y )

SLIDE 28

S u m m a r y

* C L

N

L P i s a s u i t e

f

N L P t

l

s a l l

w

i n g t

b

u i l d c

m

p l e x p i p e l i n e s * A t t h e c u r r e n t s t a t e i t i s 7 % f e a t u r e

c
m

p l e t e . S h

u

l d b e r e a d y b y e n d

f

' 1 3 * T h e b i g g e s t s h

r

t

t

e r m c h a l l e n g e : r

b