Text Plans and World Plans in Natural Discourse

D i s c o u r s e i s b o t h abou t t h e w o r l d and a n accomp l i shmen t i n t h e w o r l d . T h i s f a c t has l e d t o two approaches t o t h e s t u d y o f d i s c o u r s e I n a r t i f i c i a l i n t e l l i g e n c e , one i n v e s t i g a t i n g " t e x t p l a n s * ' , t h e o t h e r " w o r l d p l a n s " . By a n a l y z i n g a f r a g m e n t o f a n a r r a t i v e i n w h i c h b o t h k i n d s o f p l a n s f i g u r e i m p o r t a n t l y , w e e x p l o r e t he r e l a t i o n s h i p between t h e two k i n d s o f p l a n s , l o o k i n g t owa rd a s y n t h e s i s o f t h e two approaches . 1. Two Views of P lans in D i s c o u r s e R e c e n t l y , n a t u r a l l anguage d i s c o u r s e has been a n a l y z e d i n te rms o f t h e a r t i f i c i a l i n t e l l i g e n c e n o t i o n o f p l a n n i n g . But t h e p l a n s have been o f two d i s t i n c t s o r t s , and t h i s d i s t i n c t i o n has g i v e n t h e f i e l d two approaches . Those u s i n g t h e f i r s t app roach h y p o t h e s i z e abou t t h e p l a n s t h a t t h e p a r t i c i p a n t s i n a d i a l o g u e o r t h e w r i t e r o f a t e x t must h a v e . Bruce ( 1 9 7 5 ) , Schmid t ( 1 9 7 5 ) , and Cohen and P e r r a u l t ( 1 9 7 9 ) , f o r e x a m p l e , i n v e s t i g a t e t h e p l a n s a d i a l o g u e sys tem w o u l d have t o g e n e r a t e t o p e r f o r m f e l i c i t o u s i n d i v i d u a l speech a c t s . A l l e n and P e r r a u l t ( 1980 ) d e v e l o p p r o c e s s e s t h a t wou ld a l l o w a l i s t e n e r t o r e c o g n i z e a s p e a k e r ' s p l a n t o p e r f o r m a p a r t i c u l a r speech a c t . There have a l s o been a t t e m p t s t o e x t e n d t h e p l a n n i n g metaphor t o l a r g e r s t r e t c h e s o f d i s c o u r s e . The f i r s t a u t h o r (Hobbs 1978) has sough t t o I n t e r p r e t t h e s t r u c t u r e t h a t many i n v e s t i g a t o r s f i n d i n d i s c o u r s e ( e . g . Gr imes 1975, Longac re 1976) as means by w h i c h a speake r can r e a l i z e g o a l s o f a " t e x t u a l " o r " l i s t e n e r d i r e c t e d " n a t u r e . Winograd ( 1977 ) and Levy ( 1 9 7 9 ) a l s o d e m o n s t r a t e how t h e s t r u c t u r e o f d i s c o u r s e can r e s u l t f r o m t h e s p e a k e r ' s g o a l s i n t a l k i n g . R e c e n t l y we have been a n a l y z i n g c o n v e r s a t i o n s I n te rms o f t h e p a r t i c i p a n t s ' d e v e l o p i n g p l a n s f o r c a r r y i n g on t h e c o n v e r s a t i o n (Hobbs and Evans 1980, Agar and Hobbs 1981a. Agar and Hobbs 1981b, Hobbs and Agar 1 9 8 1 ) . I n a l l o f t h i s w o r k , t h e s p e a k e r i s assumed v iewed as u s i n g some k i n d o f p l a n n i n g mechanism t o g e n e r a t e p l a n s whose a c t i o n s a r e t he u t t e r a n c e s i n t h e d i a l o g u e o r t h e s e n t e n c e s i n t h e t e x t . W e w i l l c a l l t h e s e p l a n s " t e x t p l a n s " and t h e app roach t h e " t e x t a p p r o a c h " . B y c o n t r a s t , t h o s e u s i n g t h e o t h e r approach e x p l i c a t e t h e p l a n s o f t h e c h a r a c t e r s i n t h e s t o r y i t s e l f . For e x a m p l e , Schank and A b e l s o n (1977 ) show how knowledge o f p e o p l e ' s t y p i c a l g o a l s can be used t o u n d e r s t a n d s t o r i e s abou t t h e i r a c t i v i t i e s . W i l e n s k y ( 1 9 7 8 ) examines s t o r i e s b u i l t a round t h e c o n f l i c t i n g g o a l s and p l a n s o f c h a r a c t e r s . Bruce and Newman ( 1 9 7 8 ) , Bruce ( 1 9 8 0 ) , and Beaugrande ( 1 9 8 0 ) a l l a n a l y z e t r a d i t i o n a l s t o r i e s o r l i t e r a r y wo rks i n t e rms o f t h e c h a r a c t e r s ' i n i t i a l g o a l s and M i c h a e l Agar Depar tment o f A n t h r o p o l o g y U n i v e r s i t y o f M a r y l a n d t h e i r d e v e l o p i n g p l a n s t o r e a l i z e t h e g o a l s . R e l a t e d t o t h i s work i s t h e i n v e s t i g a t i o n o f how t h e p l a n f o r a c c o m p l i s h i n g a t a s k can s t r u c t u r e a d i a l o g u e abou t t h e t a s k (Grosz 1977, Hobbs and Rob inson 1 9 7 9 ) . I n c o g n i t i v e a n t h r o p o l o g y t h e r e has been a s i m i l a r i n t e r e s t i n d i s c o v e r i n g f rom d i s c o u r s e some o f t h e c e n t r a l p l a n s i n p e o p l e ' s l i v e s , i n c l u d i n g work b y t h e second a u t h o r (Aga r 1973) and b y H u t c h i n s ( 1 9 8 0 ) . I n a l l t h e s e examples t h e p l a n s a r e concerned not w i t h "how t o t a l k " bu t w i t h "how t o d o " . They a r e p l a n s f o r a c h i e v i n g g o a l s i n t h e w o r l d , no t i n t h e t e x t , and w e w i l l r e f e r t o them a s " w o r l d p l a n s " , and t o t h e app roach a s t he " w o r l d a p p r o a c h " . Those a d o p t i n g t h e t e x t approach t y p i c a l l y see u n d e r s t a n d i n g d i s c o u r s e as a b o t t o m u p , d a t a d i r e c t e d p r o c e s s . T h a t i s , i t has been e a s i e r t o s t a t e how p o s s i b l e i n t e r p r e t a t i o n s a r e c o n s t r a i n e d b y t h e d i s c o u r s e i t s e l f t h a n b y o n e ' s e x p e c t a t i o n s abou t i t s s t r u c t u r e . T h e o r i e s o f t e x t s t r u c t u r e have e i t h e r had t o o l i t t l e c o v e r a g e , a s w i t h s t o r y grammars ( R u m e l h a r t 1975) and d i a l o g u e games (Mann, Moore and L e v i n 1 9 7 7 ) , o r t hey have been i n s u f f i c i e n t l y c o n s t r a i n i n g , a s i s t h e f i r s t a u t h o r ' s coherence t h e o r y (Hobbs 1 9 7 8 ) . I n g e n e r a l , t e x t p l a n s a r e e p h e m e r a l . They a r e no t u s u a l l y c o n s t r u c t e d o u t o f l a r g e p r e s t r u c t u r e d p i e c e s . R a t h e r , t h e y a r e b u i l t " o n t h e f l y " i n response t o u n i q u e s i t u a t i o n s . C o n s e q u e n t l y , t h e ma jo r p r o b l e m w i t h t h e t e x t app roach i s t h a t s e v e r a l e q u a l l y p l a u s i b l e cohe rence s t r u c t u r e s may f i t t h e d a t a , and a g r e a t d e a l o f i n f e r e n c l n g m i g h t be r e q u i r e d t o d i s c o v e r any o f them. Those a d o p t i n g t h e w o r l d app roach t y p i c a l l y v i e w comprehens ion o f a t e x t as g u i d e d by l a r g e , p r e s t r u c t u r e d p l a n s t h a t a r e s i m p l y i n s t a n t i a t e d f o r the o c c a s i o n . T o i n t e r p r e t a n u t t e r a n c e i s t o d e t e r m i n e what s t e p o r s t e p s i n t h e w o r l d p l a n t h e u t t e r a n c e r e f e r s t o . T h i s a p p r o a c h p r o v i d e s v e r y s t r o n g c o n s t r a i n t s o n p o s s i b l e i n t e r p r e t a t i o n s o f u t t e r a n c e s . The m a j o r p r o b l e m , however , i s t h a t w e a r e no t g e n e r a l l y g i v e n t h e r e l e v a n t p l a n a t t h e b e g i n n i n g o f a t e x t . The l i s t e n e r o r r e a d e r has t o p i c k t h e a p p r o p r i a t e p l a n f r o m a l a r g e c o l l e c t i o n o f p o s s i b l e p l a n s , o r more f r e q u e n t l y , has t o c o n s t r u c t a new p l a n f o r t h e o c c a s i o n . The w o r l d app roach d o e s n ' t say how t h i s i s d o n e . For t h e pas t y e a r , we have been a n a l y z i n g f r a g m e n t s f r o m a l a r g e c o r p u s o f e t h n o g r a p h i c l i f e h i s t o r y i n t e r v i e w s , a t t e m p t i n g t o b r i n g f o r m a l app roaches t o d i s c o u r s e d e v e l o p e d i n a r t i f i c i a l i n t e l l i g e n c e t o bea r o n t h e p rob lems o f c o g n i t i v e a n t h r o p o l o g y . I n t h e c o u r s e o f o u r r e s e a r c h we have f o u n d i t u s e f u l t o a n a l y z e o u r t e x t s b o t h i n te rms o f t h e t e x t p l a n s and t h e w o r l d p l a n s t h a t a r e e x h i b i t e d . T h i s r a i s e s a n a t u r a l q u e s t i o n : what i s t h e r e l a t i o n s h i p between t h e two approaches t o d i s c o u r s e , between t e x t p l a n s and w o r l d p l a n s ? In t h i s p a p e r , we f o c u s on one f r a g m e n t o f an In te rv iew in which both wor ld plans and tex t plans f i g u r e impo r tan t l y , and we explore t h e i r r e l a t i o n s h i p , in an attempt to br ing about a synthesis between the two approaches to discourse. The conclusion we a r r i v e at has important consequences f o r discourse understanding systems. Each approach can be seen to aid in the s o l u t i o n of the major problem in the other approach. The text s t r u c t u r e , espec ia l l y in the pa t te rn o f e l abo ra t i ons , f requent l y h i g h l i g h t s c r i t i c a l areas of the world plan that must be constructed in I n t e r p r e t i n g a t e x t . Conversely, where the tex t p lan is ambiguous, the wor ld plan tha t has been developed imposes the most c o n s t r a i n t s . As w i l l be obvious, there is no system tha t is capable of performing the ana lys is tha t we present , nor do we have any in ten t ion of t r y i n g to implement such a system. Rather our e f f o r t is to use the soph is t i ca ted formalisms developed in a r t i f i c i a l i n t e l l i gence to make sense of complex data that another f i e l d must grapple w i t h , and in that con tex t , to i nves t i ga te the mapping between text and wor ld , toward a synthesis of the two dominant views o f discourse in A I .