Envisioning Machine Translation in the Information Future: 4th Conference of the Association for Machine Translation in the Americas, AMTA 2000 Cuernavaca, Mexico, October 10–14, 2000 Proceedings

269 Pages·2000·5.53 MB·English

by  Bonnie J. Dorr

L e c t u r e N o t e s i n A r t i f i c i a l I n t e l l i g e n c e 1 9 3 4
S u b s e r i e s o f L e c t u r e N o t e s i n C o m p u t e r S c i e n c e
E d i t e d b y J . G . C a r b o n e l l a n d J . S i e k m a n n
L e c t u r e N o t e s i n C o m p u t e r S c i e n c e
E d i t e d b y G . G o o s , J . H a r t m a n i s a n d J . v a n L e e u w e n
3
B e r lin
H e id e lb e r g
N e w Y o r k
B a r c e lo n a
H o n g K o n g
L o n d o n
M ila n
P a r is
S in g a p o r e
T o k y o
J o h n S . W h i t e ( E d . )
E n v i s i o n i n g
M a c h i n e T r a n s l a t i o n
i n t h e I n f o r m a t i o n F u t u r e
4 t h C o n f e r e n c e o f t h e A s s o c i a t i o n
f o r M a c h i n e T r a n s l a t i o n i n t h e A m e r i c a s , A M T A 2 0 0 0
C u e r n a v a c a , M e x i c o , O c t o b e r 1 0 - 1 4 , 2 0 0 0
P r o c e e d i n g s
1 3
S e r ie s E d ito r s
J a im e G . C a r b o n e ll, C a r n e g ie M e llo n U n iv e r s ity , P itts b u r g h , P A , U S A
J o¨ r g S ie k m a n n , U n iv e r s ity o f S a a r la n d , S a a r b r u¨ c k e n , G e r m a n y
V o lu m e E d ito r
J o h n S . W h ite
L itto n P R C
1 5 0 0 P R C D r iv e , M c L e a n , V A 2 2 1 0 2 , U S A
E - m a il: w h ite jo h n @ p r c .c o m
C a ta lo g in g - in - P u b lic a tio n D a ta a p p lie d f o r
D ie D e u ts c h e B ib lio th e k - C I P - E in h e its a u f n a h m e
E n v is io n in g m a c h in e tr a n s la tio n in th e in f o r m a tio n f u tu r e :
C u e r n a v a c a , M e x ic o , O c to b e r 1 0 - 1 4 , 2 0 0 0 / J o h n S . W h ite ( e d .) . -
B e r lin ; H e id e lb e r g ; N e w Y o r k ; B a r c e lo n a ; H o n g K o n g ; L o n d o n ;
M ila n ; P a r is ; S in g a p o r e ; T o k y o : S p r in g e r, 2 0 0 0
( ... C o n f e r e n c e o f A s s o c ia tio n f o r M a c h in e T r a n s la tio n in th e
A m e r ic a s , A M T A ... ; 4 . 2 0 0 0 )
( L e c tu r e n o te s in c o m p u te r s c ie n c e ;
V o l. 1 9 3 4 : L e c tu r e n o te s in a r tifi c ia l in te llig e n c e )
I S B N 3 - 5 4 0 - 4 1 1 1 7 - 8
C R S u b je c t C la s s ifi c a tio n ( 1 9 9 8 ) : I .2 .7 , H .3 , F .4 .3 , H .5 , J .5
I S B N 3 - 5 4 0 - 4 1 1 1 7 - 8 S p r in g e r- V e r la g B e r lin H e id e lb e r g N e w Y o r k
T h is w o rk is su b je c t to c o p y rig h t. A ll rig h ts a re re se rv e d , w h e th e r th e w h o le o r p a rt o f th e m a te ria l is
c o n c e rn e d , sp e c ifi c a lly th e rig h ts o f tra n sla tio n , re p rin tin g , re -u se o f illu stra tio n s, re c ita tio n , b ro a d c a stin g ,
re p ro d u c tio n o n m ic ro fi lm s o r in a n y o th e r w a y , a n d sto ra g e in d a ta b a n k s. D u p lic a tio n o f th is p u b lic a tio n
o r p a rts th e re o f is p e rm itte d o n ly u n d e r th e p ro v isio n s o f th e G e rm a n C o p y rig h t L a w o f S e p te m b e r 9 , 1 9 6 5 ,
in its c u rre n t v e rsio n , a n d p e rm issio n fo r u se m u st a lw a y s b e o b ta in e d fro m S p rin g e r-V e rla g . V io la tio n s a re
lia b le fo r p ro se c u tio n u n d e r th e G e rm a n C o p y rig h t L a w .
S p rin g e r-V e rla g B e rlin H e id e lb e rg N e w Y o rk
a m e m b e r o f B e rte lsm a n n S p rin g e r S c ie n c e + B u sin e ss M e d ia G m b H
(cid:2)c S p rin g e r-V e rla g B e rlin H e id e lb e rg 2 0 0 0
P rin te d in G e rm a n y
T y p e se ttin g : C a m e ra -re a d y b y a u th o r, d a ta c o n v e rsio n b y P T P -B e rlin , S te fa n S o ssn a
P rin te d o n a c id -fre e p a p e r S P IN : 1 0 7 8 1 2 2 6 0 6 /3 1 4 2 5 4 3 2 1 0
P r e f a c e
E n v i s i o n i n g M a c h i n e T r a n s l a t i o n i n t h e I n f o r m a t i o n F u t u r e
W h e n th e o r g a n iz in g c o m m itte e o f A M T A - 2 0 0 0 b e g a n p la n n in g , it w a s in th a t b r ie f
m o m e n t in h is to r y w h e n w e w e r e a b s o r b e d in c o n te m p la tio n o f th e p a s s in g o f th e
c e n tu r y a n d th e m ille n n iu m . N e a r ly e v e r y o n e w a s c o m p a r in g lis ts o f th e m o s t
im p o r ta n t a c c o m p lis h m e n ts a n d p e o p le o f th e la s t 1 0 , 1 0 0 , o r 1 0 0 0 y e a r s , im a g in in g
th e r a d ic a l c h a n g e s lik e ly o v e r ju s t th e n e x t f e w y e a r s , a n d a t le a s t m ild ly a n x io u s
a b o u t th e p o te n tia l Y 2 K a p o c a ly p s e .
T h e m ille n n ia l th e m e f o r th e c o n f e r e n c e , “ E n v is io n in g M T in th e I n f o r m a tio n
F u tu r e ,” a r o s e f r o m th is p e r io d . T h e y e a r 2 0 0 0 h a s n o w c o m e , a n d n o th in g te r r ib le
h a s h a p p e n e d ( y e t) to o u r e le c tr o n ic in f r a s tr u c tu r e . O u r m u s in g s a b o u t g r e a t p e o p le
a n d e v e n ts p r o b a b ly d id n o t e n n o b le u s m u c h , a n d w h a te v e r s e n s e o f ju b ile e w e h e ld
h a s s in c e d is s ip a te d . S o it m a y s e e m a b it o b s o le te o r a n a c h r o n is tic to c a s t th is
A M T A c o n f e r e n c e in to v is io n a r y th e m e s .
B u t th e m ille n n ia l c o n c e p ts r e m a in p e r tin e n t to M T b e c a u s e o f w h a t it is a n d w h a t
w ill b e e x p e c te d o f it. L ik e th e p r in tin g p r e s s , th a t a r c h e ty p a l b r e a k th r o u g h in v e n tio n
o f th e la s t m ille n n iu m , M T w ill m a k e in f o r m a tio n a v a ila b le to e v e r y o n e , b r e a k in g
o p e n th e la n g u a g e - b o u n d c lo is te r s o f id e a s . L ik e p r in tin g a n d p u b lis h in g , M T h a s a n d
w ill e v o lv e f r o m a to o l th a t c a n o n ly b e c a lib r a te d a n d o p e r a te d b y s k ille d p e o p le to
o n e w h ic h a n y o n e c a n d ir e c tly o p e r a te , e v e n w h ile th e d e m a n d f o r th e p r o f e s s io n a lly
d e v e lo p e d p r o d u c t c o n tin u e s to g r o w . L ik e th e p r in tin g p r e s s , in s h o r t, M T w ill c r e a te
its o w n d e m a n d , a n d w ill g o f r o m a c a p a b ility th a t w e n e v e r th o u g h t w e w o u ld n e e d
to o n e w e c a n n o t d o w ith o u t.
T h is p r o c e s s h a s b e g u n . T h e p a p e r s in th is v o lu m e c a p tu r e th e s ta te o f M T in th e
y e a r 2 0 0 0 , a n d th e y w ill c o n tin u e to b e o f v a lu e f o r r e s e a r c h e r s , d e v e lo p e r s , u s e r s ,
tr a n s la to r s , a n d in f o r m a tio n c o n s u m e r s f o r m a n y y e a r s to c o m e . T h e y c o v e r
b r e a k th r o u g h a p p r o a c h e s to th e s c ie n c e o f k n o w le d g e r e p r e s e n ta tio n , s ta tis tic a l
m o d e lin g , in te r lin g u a s a n d tr a n s f e r s tr a te g ie s , a n d d e p lo y m e n t o f s y s te m s . T h e y
e x p r e s s th e in g e n io u s a p p lic a tio n o f M T s y s te m s a n d te c h n iq u e s to th e d e m a n d s o f
a c tu a l tr a n s la tio n e n v ir o n m e n ts , a n d th e c o lle c tio n a n d r e u s e o f c o r p o r a . T h e y d e lv e
in to th e v is io n s o f f u tu r e n e e d s , p r o g r a m s , a n d e x p e c ta tio n s , a lo n g w ith th e m e a n s b y
w h ic h w e w ill e v a lu a te c h a n g e .
T h e A M T A - 2 0 0 0 P r o g r a m C o m m itte e d e s e r v e s th e c r e d it f o r c a p tu r in g th e e s s e n c e
o f th e s ta te o f M T a t th e tu r n o f th e m ille n n iu m . T h e m e m b e r s o f th e P r o g r a m
C o m m itte e a r e :
J e f f A lle n , S o f tis s im o
R o b e r t C a in , F o r e ig n B r o a d c a s t I n f o r m a tio n S e r v ic e
G a r y C o e n , B o e in g P h a n to m W o r k s
J e n n if e r D e C a m p , M I T R E C o r p .
J e n n if e r D o y o n , L itto n P R C
U lr ic h G e r m a n n , U n iv e r s ity o f S o u th e r n C a lif o r n ia I n f o r m a tio n S c ie n c e I n s titu te
S te p h e n H e lm r e ic h , N e w M e x ic o S ta te U n iv e r s ity C o m p u tin g R e s e a r c h L a b o r a to r y
D o u g J o n e s , N a tio n a l I n s titu te o f S ta n d a r d s a n d T e c h n o lo g y
V I P r e fa c e
K e v in K n ig h t, U n iv e r s ity o f S o u th e r n C a lif o r n ia I n f o r m a tio n S c ie n c e I n s titu te
M a r jo r ie L e o n , P a n A m e r ic a n H e a lth O r g a n iz a tio n
D a n L o e h r , M I T R E C o r p .
J a c k ie M u r g id a , L e r n o u t & H a u s p ie
K a th r y n T a y lo r , G e o r g e to w n U n iv e r s ity
M y th a n k s a ls o g o to th e o r g a n iz e r s o f A M T A - 2 0 0 0 : E d H o v y , M u r ie l V a s c o n c e llo s ,
L a u r ie G e r b e r , a n d D a v e F a r w e ll, w h o p ic k e d u p m y s u n d r y d r o p p e d b a lls , h e lp e d
w ith r e v ie w s , a n d s e t th e to n e f o r a s u c c e s s f u l c o n f e r e n c e a n d p r o c e e d in g s v o lu m e .
T h e v e n u e o f th e c o n f e r e n c e , a r r a n g e d m a s te r f u lly b y M u r ie l V a s c o n c e llo s , M a r in a
U r q u id i, a n d N e n a U r a n g a , is th e a n c ie n t a n d b e a u tif u l c ity o f C u e r n a v a c a , M e x ic o .
T h e tu to r ia ls a n d w o r k s h o p s w e r e o r g a n iz e d b y L a u r ie G e r b e r , w h o b u ilt b a la n c e d
p r o g r a m s e v o c a tiv e o f th e is s u e s o n th e e d g e o f M T in th is n e w c e n tu r y . K im b e r ly
K e llo g g B e lv in c o n tin u e s in h e r p o lis h e d , p r o f e s s io n a l r o le a s e x h ib its c o o r d in a to r .
M y g o o d f r ie n d s E d H o v y ( A M T A P r e s id e n t) a n d D a v e F a r w e ll ( A M T A - 2 0 0 0
C o n f e r e n c e C h a ir ) h a v e p r o v id e d m u c h n e e d e d s u p p o r t, v is io n , a n d h o r ta to r y
e x p r e s s io n s to s tim u la te th e d e v e lo p m e n t o f th e p r o g r a m r e p r e s e n te d in th is v o lu m e .
I w is h to th a n k e s p e c ia lly F lo r e n c e R e e d e r o f M I T R E C o r p o r a tio n , w h o s e
c o m m a n d o f th e q u a in t a r t o f L a T e X s titc h e r y m a d e th e a s s e m b ly o f th is v o lu m e
p o s s ib le f o r m e , w h o h a d h e r e to f o r e p r e s u m e d th a t W Y S I W Y G w o r d p r o c e s s in g w a s ,
lik e in d o o r p lu m b in g , a n o r d in a r y e x p e c ta tio n .
W h a te v e r th e v is io n o f th e f u tu r e h o ld s , w h e th e r u b iq u ito u s in f o r m a tio n a c c e s s ,
in f o r m a tio n a p p lia n c e s th a t w e w e a r , o r w h o le n e w m e ta p h o r s o f w h a t it m e a n s to
c o m m u n ic a te , tw o th in g s s h o u ld b e c le a r : o u r p r e d ic tio n s w ill b e w r o n g ( in c lu d in g
th is o n e ) , a n d v a r ia tio n in h u m a n la n g u a g e w ill r e m a in . I n th is lig h t, I h o p e th a t b o th
th e p r e s e n t a n d f u tu r e r e a d e r o f th is v o lu m e w ill b e n e f it f r o m th e s e p a p e r s , b o th in th e
c o n te x t o f to d a y a n d a c r o s s th e c h a n g e s th a t th e f u tu r e w ill h a v e b r o u g h t to th e f ie ld
o f m a c h in e tr a n s la tio n .
A u g u s t, 2 0 0 0 J o h n S . W h ite
T u t o r i a l D e s c r i p t i o n s
O n t o lo g ic a l S e m a n t ic s
S e r g e i N i r e n b u r g
C o m p u t i n g R e s e a r c h L a b o r a t o r y , N e w M e x i c o S t a t e U n i v e r s i t y
I n c o m p u ta tio n a l lin g u is tic s th e te r m o n to lo g y h a s c o m e to d e n o te a w o r ld m o d e l u s e d
f o r s p e c if y in g th e m e a n in g o f le x ic a l u n its in a la n g u a g e . E le m e n ts o f th e o n to lo g y ,
th u s , c a n b e v ie w e d a s th e le x is o f a m e ta la n g u a g e f o r d e s c r ib in g th e le x ic a l s e m a n tic s
o f a p a r tic u la r la n g u a g e . O n c e th e o n to lo g ic a l a p p r o a c h is c h o s e n f o r d e s c r ib in g
le x ic a l m e a n in g , th e le x ic o n a n d th e o n to lo g y b e c o m e c o u p le d . D e p e n d in g o n th e
ty p e o f c o m p u ta tio n a l lin g u is tic a p p lic a tio n th a t a le x ic o n is s u p p o s e d to s u p p o r t, th e
o n to lo g y th a t u n d e r lie s its s e m a n tic c o m p o n e n t w ill c o n ta in d if f e r e n t ( th o u g h p o s s ib ly
c o m p a tib le ) in f o r m a tio n . A m o n g th e p o s s ib le a p p lic a tio n s a r e : k n o w le d g e - b a s e d
m a c h in e tr a n s la tio n ( M T ) ; le x ic a l d is a m b ig u a tio n a s a m o d u le in tr a n s f e r - b a s e d M T
o r in a n in f o r m a tio n e x tr a c tio n ( I E ) s y s te m ; te x t s u m m a r iz a tio n ; h u m a n - c o m p u te r
in te r a c tio n ; p la n n in g a n d p la n r e c o g n itio n f o r a s o c ie ty o f s o f tw a r e a n d h u m a n a g e n ts ;
o b je c t a n d s c e n e r e c o g n itio n ; a n d o th e r s . T o illu s tr a te th e a p p lic a tio n - o r ie n te d
d if f e r e n c e s in o n to lo g y c o n te n t, th e w o r k o n a g e n ts r e q u ir e s d e ta ile d s ta te m e n ts a b o u t
" w o r k f lo w s c r ip ts " th a t th e s e a g e n ts f o llo w a s w e ll a s d o m a in - r e la te d p la n s , b o th
r e a liz a b le a s c o m p le x e v e n ts , w h ile th e w o r k o n k n o w le d g e - b a s e d M T ty p ic a lly d o e s
n o t. L e x ic a l d is a m b ig u a tio n is o f te n c o n s id e r e d f e a s ib le w ith o u t o n to lo g ic a l
u n d e r p in n in g s in th e le x ic o n b u t b a s e d o n a s e t o f s e m a n tic f e a tu r e s a s s ig n e d to a
le x ic a l ite m ( if n o t b a s e d e n tir e ly o n c o r p u s - b a s e d c o - o c c u r r e n c e c a lc u la tio n s ) .
T h e a p p lic a tio n o n w h ic h w e w ill c o n c e n tr a te w ill b e k n o w le d g e - b a s e d M T . I n th e
f r a m e w o r k o f k n o w le d g e - b a s e d M T , o n to lo g y s u p p lie s m a jo r c h u n k s o f th e
m e ta la n g u a g e n o t o n ly f o r th e s e m a n tic c o m p o n e n t o f th e le x ic o n b u t a ls o f o r th e
la n g u a g e in w h ic h th e m e a n in g o f te x ts is r e p r e s e n te d . T h e la tte r la n g u a g e ( c a lle d
T M R , f o r T e x t M e a n in g R e p r e s e n ta tio n ) is th e in te r lin g u a in th e K B M T s y s te m .
T h e tu to r ia l w ill in c lu d e th e f o llo w in g to p ic s :
D e s ig n o f a n M T s y s t e m b a s e d o n o n t o lo g ic a l s e m a n t ic s
T h e S t a t ic K n o w le d g e S o u r c e s f o r K B M T : th e T M R , th e O n to lo g y a n d th e L e x ic o n
T h e T M R
a ) T h e T M R c o n te n t
b ) T h e T M R f o r m a t
T h e O n t o lo g y
c ) T h e s y n ta x o f th e o n to lo g y e n tr y
d ) T h e c o n te n t o f th e o n to lo g y
e ) A b r ie f c o m p a r is o n w ith o th e r o n to lo g ie s u s e d f o r la n g u a g e
p r o c e s s in g , n o ta b ly , C Y C , W o r d N e t a n d S e n s u s .
O n t o lo g y A c q u is it io n
a ) T h e a c q u is itio n m e th o d o lo g y
b ) E x a m p le s o f c o n c e p t a c q u is itio n
V I I I T u to r ia l D e s c r ip tio n s
T h e L e x ic o n
a ) T h e a n a ly s is le x ic o n
b ) T h e g e n e r a tio n le x ic o n
c ) T h e o n o m a s tic o n
L e x ic o n A c q u is it io n
a ) T h e a c q u is itio n m e th o d o lo g y
b ) E x a m p le s o f le x ic o n e n tr y a c q u is itio n
I n t e r a c t io n a m o n g th e T M R , th e O n to lo g y a n d th e L e x ic o n in M ik r o k o s m o s
O n to lo g ic a l s u p p o r t f o r a p p lic a t io n s o t h e r t h a n M T ( I E , s u m m a r iz a tio n , a g e n ts ) .
T h e tu to r ia l is in te n d e d f o r c o m p u ta tio n a l le x ic o g r a p h e r s , d e s ig n e r s a n d im p le m e n te r s
o f N L P s y s te m s , in c lu d in g M T , I E , I R , a n d te x t s u m m a r iz e r s .
A G e n t l e I n t r o d u c t i o n t o M T : T h e o r y a n d C u r r e n t
P r a c t i c e
E d u a r d H o v y
I n f o r m a t i o n S c i e n c e s I n s t i t u t e o f t h e U n i v e r s i t y o f S o u t h e r n
C a l i f o r n i a
T h is tu to r ia l p r o v id e s a n o n - te c h n ic a l in tr o d u c tio n to m a c h in e tr a n s la tio n . I t r e v ie w s
th e w h o le s c o p e o f M T , o u tlin in g b r ie f ly its h is to r y a n d th e m a jo r a p p lic a tio n a r e a s
to d a y , a n d d e s c r ib in g th e v a r io u s k in d s o f M T te c h n iq u e s th a t h a v e b e e n in v e n te d - - -
f r o m d ir e c t r e p la c e m e n t th r o u g h tr a n s f e r to th e h o ly g r a il o f in te r lin g u a s . I t b r ie f ly
o u tlin e s th e d if f ic u lt q u e s tio n s o f M T e v a lu a tio n a n d p r o v id e s a n in tr o d u c tio n to th e
n e w e s t s ta tis tic s - b a s e d te c h n iq u e s ( w h ic h a r e th e to p ic o f a n o th e r tu to r ia l) .
T o p ic s in c lu d e :
• H is to r y a n d d e v e lo p m e n t o f M T
• T h e o r e tic a l f o u n d a tio n s o f M T
• T r a d itio n a l a n d m o d e r n M T te c h n iq u e s
• L a te s t M T r e s e a r c h
• T h o r n y q u e s tio n s o f e v a lu a tin g M T s y s te m s
E d u a r d H o v y is th e d ir e c to r o f th e N a tu r a l L a n g u a g e G r o u p a t th e I n f o r m a tio n
S c ie n c e s I n s titu te o f th e U n iv e r s ity o f S o u th e r n C a lif o r n ia , a n d is a m e m b e r o f th e
C o m p u te r S c ie n c e D e p a r tm e n ts o f U S C a n d o f th e U n iv e r s ity o f W a te r lo o . H is
r e s e a r c h f o c u s e s o n m a c h in e tr a n s la tio n , a u to m a te d te x t s u m m a r iz a tio n , a u to m a te d
q u e s tio n a n s w e r in g , m u ltilin g u a l in f o r m a tio n r e tr ie v a l, a n d th e s e m i- a u to m a te d
c o n s tr u c tio n o f la r g e le x ic o n s a n d te r m in o lo g y b a n k s . H e is th e a u th o r o r e d ito r o f
f o u r b o o k s a n d o v e r 1 0 0 te c h n ic a l a r tic le s . C u r r e n tly D r . H o v y s e r v e s a s th e P r e s id e n t
o f th e A s s o c ia tio n o f M a c h in e T r a n s la tio n in th e A m e r ic a s ( A M T A ) a n d a s V ic e
P r e s id e n t o f th e A C L a n d a s P r e s id e n t- E le c t o f th e I n te r n a tio n a l A s s o c ia tio n o f
M a c h in e T r a n s la tio n ( I A M T ) . D r . H o v y r e g u la r ly c o - te a c h e s a c o u r s e in th e n e w
M a s te r ’s D e g r e e P r o g r a m in C o m p u ta tio n a l L in g u is tic s a t th e U n iv e r s ity o f S o u th e r n
C a lif o r n ia , a s w e ll a s o c c a s io n a l s h o r t c o u r s e s o n M T a n d o th e r to p ic s a t u n iv e r s itie s
a n d c o n f e r e n c e s .
T u to r ia l D e s c r ip tio n s I X
C o n t r o l l e d L a n g u a g e s
T e r u k o M i t a m u r a a n d E r i c N y b e r g
C a r n e g i e M e l l o n U n i v e r s i t y
T h e n o tio n o f C o n tr o lle d L a n g u a g e ( C L ) is b e c o m in g in c r e a s in g ly im p o r ta n t f o r b o th
a u th o r s a n d tr a n s la to r s w o r k in g a la r g e - s c a le d o c u m e n t p r o d u c tio n e n v ir o n m e n t.
G o o d d e s ig n , p r o c e s s a n d im p le m e n ta tio n o f a C o n tr o lle d L a n g u a g e c a n p r o v id e
h ig h e r - q u a lity d o c u m e n ta tio n a n d m o r e p r o d u c tiv e tr a n s la tio n . E v e n s o , th e r e a r e
s o m e is s u e s a s s o c ia te d w ith in tr o d u c in g C o n tr o lle d L a n g u a g e in to d o c u m e n t
p r o d u c tio n e n v ir o n m e n t w h ic h m u s t b e c o n s id e r e d c a r e f u lly . T h e g o a l o f th is tu to r ia l
is to in tr o d u c e th e c o n c e p t o f C o n tr o lle d L a n g u a g e , to d is c u s s d e s ig n a n d d e p lo y m e n t
is s u e s , a n d to s u m m a r iz e th e s ta te o f th e a r t in C L d e v e lo p m e n t.
I n te n d e d a u d ie n c e : M T u s e r s , A u th o r s , T r a n s la to r s , a n y o n e w h o w o u ld b e
in te r e s te d in le a r n in g a b o u t C L .
• I n tr o d u c tio n
• W h a t is C o n tr o lle d L a n g u a g e ?
• G o a ls o f C o n tr o lle d L a n g u a g e
• H is to r y o f C o n tr o lle d L a n g u a g e & A p p lic a tio n s
• H u m a n C o m m u n ic a tio n s
• D o c u m e n t A u th o r in g
• D o c u m e n t T r a n s la tio n
• D e s ig n in g a C o n tr o lle d V o c a b u la r y
• D e s ig n in g a C o n tr o lle d G r a m m a r
• H o w T o B u ild a n d D e p lo y a C o n tr o lle d L a n g u a g e
• F o r a u th o r in g o n ly
• F o r a u th o r in g a n d M T
• E v a lu a tin g th e U s e o f C o n tr o lle d L a n g u a g e
• A u th o r ’s P e r s p e c tiv e
• T r a n s la to r ’s P e r s p e c tiv e
• D e v e lo p e r ’s P e r s p e c tiv e
• C u r r e n t S ta tu s o f C o n tr o lle d L a n g u a g e
• T h e F u tu r e o f C o n tr o lle d L a n g u a g e
S t a t i s t i c a l M a c h i n e T r a n s l a t i o n
K e v i n K n i g h t
I n f o r m a t i o n S c i e n c e s I n s t i t u t e o f t h e U n i v e r s i t y o f S o u t h e r n
C a l i f o r n i a
T h e s ta tis tic a l a p p r o a c h to m a c h in e tr a n s la tio n ( M T ) s e e k s to e x tr a c t tr a n s la tio n
k n o w le d g e a u to m a tic a lly f r o m o n lin e b ilin g u a l te x ts ( e .g ., p u b lic a tio n s o f th e
C a n a d ia n o r H o n g K o n g g o v e r n m e n ts ) . T h is id e a c a n b e tr a c e d b a c k to s u g g e s tio n s