Experiments we are conducting show analogous phenomena in telephone and teletype modes.. Thus, the novice would be acting because she thinks the expert intended f o r her ¢o do so.. Late
Trang 1S i g n a l l i n g t h e I n t e r p r e t a t i o n o f I n d i r e c t Speech A c t s
P h i l i p R Cohen
C e n t e r f o r t h e S t u d y o f Reading
U n i v e r s i t y o f I l l i n o i s , &
B o l t , Beranek and Newman, I n c
C a m b r i d g e , Mass
T h i s panel was asked t o c o n s i d e r how v a r i o u s " p r o b l e m
c o n t e x t s " ( e g , c o o p e r a t i v e l y a s s e m b l i n g a pump, o r
S o c r a t i c a l l y t e a c h i n g law) i n f l u e n c e t h e use o f l a n g u a g e
As a s t a r t i n g p o i n t , I s h a l l r e g a r d t h e p r o b l e m c o n t e x t
as e s t a b l i s h i n g a s e t o f e x p e c t a t i o n s and a s s u m p t i o n s
a b o u t t h e shared b e l i e f s , g o a l s , and s o c i a l r o l e s o f
t h o s e p a r t i c i p a n t s J u s t how p e o p l e n e g o t i a t e t h a t t h e y
a r e in a g i v e n p r o b l e m c o n t e x t and what t h e y know a b o u t
t h o s e c o n t e x t s a r e i n t e r e s t i n g q u e s t i o n s , b u t n o t ones I
s h a l l a d d r e s s h e r e R a t h e r , I s h a l l o u t l i n e a t h e o r y o f
language use t h a t is s e n s i t i v e ¢o those b e l i e f s , g o a l s ,
and e x p e c t a t i o n s
The t h e o r y is b e i n g a p p l i e d t o c h a r a c t e r i z e a c t u a l
d i a l o g u e s o c c u r r i n g in t h e F a m i l i a r t a s k - o r l e n t e d s l t -
u a t i o n ~O.1, in w h i c h an e x p e r t i n s t r u c t s a n o v i c e Co do
s o m e t h i n g , in o u r case t o assemble a t o y w a t e r pump In
such c i r c u m s t a n c e s , the d i a l o g u e p a r t i c i p a n t s can be
viewed as p e r f o r m i n g speech a c t s p l a n n e d , p r l m a r l ] y , t o
a c h i e v e g o a l s s e t by t h e t a s k O t h e r c o n t e x t s u n d o u b t e d -
l y emphasize the i n s t r u m e n t a l uses o f language ( e g , ~ )
b u t those p r o b l e m c o n t e x t s w i l l n o t be c o n s i d e r e d h e r e
The a p p l i c a t i o n o f a model o f speech a c t use to a c t u a l
d i a l o g u e s t r e s s e s t h e need For sources o f e v i d e n c e t o
s u b s t a n t i a t e p r e d i c t i o n s The p u r p o s e o f t h i s paper is
t o p o i n t t o one such s o u r c e - - s p e a k e r - r e f e r e n c e ~ 9 ] -
The n a t u r a l c a n d i d a t e f o r a t h e o r y o f i n s t r u m e n t a l use
o f speech a c t s is an a c c o u n t o f r a t i o n a l a c t i o n ~ - -
what is t y p i c a l l y termed " p l a n n i n g " However, c o n t r a r y
to t h e a s s u m p t i o n o f most p l a n n i n g s y s t e m s , we a r e i n -
t e r e s t e d in the p l a n n i n g o f ( u s u a l l y ) c o o p e r a t i v e a g e n t s
who a t t e m p t t o r e c o g n i z e and f a c i l i t a t e t h e p l a n s o f
t h e i r p a r t n e r s ~ , h , 5 , ] 6 , 2 0 ] Such h e l p f u l b e h a v i o r is
i n d e p e n d e n t o f t h e use o f l a n g u a g e , b u t is t h e s o u r c e o f
much conversational coherence
A p l a n based t h e o r y o f speech a c t s s p e c i f i e s t h a t p l a n
r e c o g n i t i o n is t h e b a s i s f o r i n f e r r i n g t h e i l l o c u C i o n a r y
f o r c e ( s ) o f an u t t e r a n c e The goal o f such a t h e o r y is
t o f o r m a l i z e the s e t o f p o s s i b l e p l a n s u n d e r l y i n g t h e use
o f p a r t i c u l a r speech a c t s Co a c h i e v e a g i v e n s e t o f g o a l s
In l i g h t o f t h e i n d e p e n d e n t m o t i v a t i o n f o r p l a n g e n e r a t i o n
and r e c o g n i t i o n , such a Formalism s h o u l d t r e a t commun-
i c a t i v e and n o n - c o m m u n l c a t l v e a c t s u n i f o r m l y , by s t a t i n g
the c o m m u n i c a t i v e n a t u r e o f an i l l o c u t l o n a r y a c t as p a r t
o f c h a t a c t ' s d e f i n i t i o n A r e a s o n i n g s y s t e m , be i t
human o r c o m p u t e r , w o u l d then n o t have t o employ s p e c i a l
knowledge a b o u t c o m m u n i c a t i v e a c t s ; i t w o u l d s i m p l y a t -
tempt Co a c h i e v e o r r e c o g n i z e g o a l s
The components o f speech a c t p ] a n n l n g and r e c o g n i t i o n
systems d e v e l o p e d so f a r i n c l u d e : a Formal language f o r
d e s c r i b i n g mental s t a t e s and s t a t e s o f t h e p h y s i c a l and
s o c i a l w o r l d s , o p e r a t o r s f o r d e s c r i b i n g changes o f s t a t e ,
a s s o c i a t i o n s o f u t t e r a n c e f e a t u r e s ( e g , mood) w i t h c e r -
t a l n o p e r a t o r s , and a s e t o f p l a n c o n s t r u c t i o n and r e -
c o g n i t i o n i n f e r e n c e s I l l o c u t i o n a r ' y a c t s a r e d e f i n e d as
o p e r a t o r s t h a t p r i m a r i l y a f f e c t t h e mental s t a t e s o f
speakers and h e a r e r s L 3 , 8 , 1 3 , I 7 J
To be more s p e c i f i c , in the most f u l l y d e v e l o p e d a t -
tempt a t such a t h e o r y , P e r r a u l c and A l l e n ~ show how
p l a n r e c o g n i t i o n can " r e a s o n o u t " a c l a s s o f i n d i r e c t
speech a c t s B r i e f l y , t h e y d e f i n e " s u r f a c e =' speech a c t
o p e r a t o r s , w h i c h depend on an u t t e r a n c e ' s mood, and o p -
e r a t o r s For i l l o c u t i o n a r y a c t s such as r e q u e s t i n g Plan
r e c o g n i t i o n i n v o l v e s i n f e r e n c e s o f the form " t h e a g e n t
i n t e n d e d t o p e r f o r m a c t i o n X because he i n t e n d e d t o a c h -
i e v e i t s e f f e c t in o r d e r t o e n a b l e him t o do some o t h e r
a c t i o n Y" Such i n f e r e n c e s a r e a p p l i e d t o s u r f a c e speech
a c t o p e r a t o r s ( c h a r a c t e r i z i n g , f o r i n s t a n c e , " I s t h e s a l t
n e a r y o u ? " ) to y i e l d i i l o c u t i o n a r y o p e r a t o r s such as
* For t h i s b r i e f p a p e r , I s h a l l have Co c u r t a i l d i s c u s s i o n
o f the p l a n n i n g / p l a n r e c o g n i t i o n l i t e r a t u r e
requests to pass the s a l t The remainder of this paper attempts to i l l u s t r a t e the kinds o f predictlons made by the theory,.and the use o f anaphora to support one such p r e d i c t i o n " Consider the following dialogue fragment (transmitted over teletype)
in the water pump context described e a r l i e r : Expert: l ) '~e need a clear bent tube For the bottom
h o l e "
Novice: 2) "OK, i t ' s done."
Expert: 3) "OK, now, s t a r t pumping"
The example is constructed to i l l u s t r a t e my p o i n t , but i t does not " f e e l " a r t i f i c i a l Experiments we are conducting show analogous phenomena in telephone and teletype modes The theory predicts two inference paths For utterance
I - - " h e l p f u l " and "intended" In the Former case, the novice observes the surface-lnform speech act indicated
by a declarative utterance, and interprets i t simply as
an inform act that communicates a j o i n t need Then, be- cause the novice is h e l p f u l , she continues to recognize the plan behind the expert's utterance and attempts to
f u r t h e r i t by performing the action o f putting the spout over the hole The novice, therefore, is acting on her own, evaluating the reasonableness o f the plan inferred
f o r the expert using private b e l i e f s about the expert's
b e l i e f s and intentions A l t e r n a t i v e l y , she could i n f e r that the expert intended for i t to be mutually believed that he intended her to put on the tube Thus, the novice would be acting because she thinks the expert intended
f o r her ¢o do so Later, she could summarize the expert's utterance and intentions as a request ~7] Perrault and Alien supply heuristics that would predlct-~" the preferred inference route to be the "intended" path since i t is mutually believed that putting the tube on is the relev- ant a c t , and h i s i n t e n d i n g t h a t she p e r f o r m p u m p - r e l a t e d
a c t s is an e x p e c t e d g o a l in t h i s p r o b l e m c o n t e x t To use
P e r r a u l t and A l i e n ' s model For a n a l y z i n g c o n v e r s a t i o n ,
such p r e d i c t i o n s must be v a l i d a t e d a g a i n s t e v i d e n c e o f
t h e n o v i c e ' s i n t e r p r e t a t i o n o f the e x p e r t ' s i n t e n t Signalling I n t e r p r e t a t i o n o f Intent
For t h i s p r o b l e m c o n t e x t and c o m m u n i c a t i o n m o d a l i t y ,
t h e n o v i c e and e x p e r t s h a r e d knowledge t h a t t h e e x o e r t
w i l l a t t e m p t t o g e t the n o v i c e t o a c h i e v e each subgoal
o f t h e p h y s i c a l t a s k , and t h e n o v i c e must i n d i c a t e s u c -
c e s s f u l c o m p l e t i o n o f t h o s e s u b t a s k s However, n o t a l l
c o m m u n i c a t i v e a c t s a c h i e v i n g the goal o f i n d i c a t i n g suc-
c e s s f u l c o m p l e t i o n p r o v i d e e v i d e n c e o f t h e n o v i c e ' s i n -
t e r p r e t a t i o n o f i n t e n t For i n s t a n c e , the n o v l c e m i g h t say " I ' v e p u t the b e n t tube o n " s i m p l y t o keep the e x p e r t
i n f o r m e d o f t h e s i t u a t l o n Such an i n f o r m a t i v e a c t c o u l d
a r i s e i f t h e p r o b l e m c o n t e x t and p r i o r c o n v e r s a t i o n d l d
n o t make t h e s a l i e n c e o f p u t t i n g t h e tube on m u t u a l l y known To s u p p l y e v i d e n c e o f t h e n o v i c e ' s i n t e r p r e t a t i o n
of intent, her response must pragmatically presuppose that i n t e r p r e t a t i o n
In our example, the novice has used " i t " to r e f e r to the action she has performed I t has been proposed that
d e f i n i t e and pronomlnal/pro-verbal reference requires mutual b e l i e f chat the object in question_ is in Focus
O0,,s] and s a t i s f i e s the " d e s c r i p t , o n ' l t6,l Assuming
that the,_inferring of mutually believed goals places them
in focusU~ , the shared knowledge needed to refer using
" i t " is supplied by only one o f the above interpretations
- - the one summarizable as an indirect request
Robinson ~!~ has i d e n t i f i e d this problem of reference
t o a c t i o n s and has implemented a system t o r e s o l v e them
In c h l s p a p e r , I s t r e s s t h e i m p o r t a n c e o f t h a t w o r k to
t h e o r i e s o f speech a c t use
29
Trang 2Other s i g n a l s o f the i n t e r p r e t a t i o n o f i n t e n t need to
be i d e n t i f i e d to e x p l a i n how the e x p e r t i s "OK, now s t a r t
pumping" communicates t h a t he t h i n k s she has i n t e r -
p r e t e d him c o r r e c t l y - - mutual s i g n a l l i n g o f i n t e n t
and i t s i n t e r p r e t a t i o n is c e n t r a l to c o n v e r s a t i o n a l
Success
A formal theory t h a t could capture the b e l i e f , i n -
t e n t i o n , and focus c o n d i t i o n s f o r s p e a k e r - r e f e r e n c e is
thus c l e a r l y needed to v a l i d a t e models o f speech act use
A plan-based theory might accomodate such an a n a l y s i s v i a
a decomposition o f c u r r e n t l y p r i m i t i v e s u r f a c e speech
acts to include r e f e r e n c e acts [ 2 , 1 8 J By p l a n n i n g r e f -
erence acts to f a c i l i t a t e the h e a r e r s ' plans ( o f ~43),
a system could perhaps a l s o answer qu es t io ns coopera-
t i v e l y w i t h o u t r e s o r t i n g to Gricean maxims o r "room
t h e o r i e s " [19.~
I have given a bare bones o u t l i n e o f how a d e s c r i p -
t i o n o f s p e a k e r - r e f e r e n c e can ser~e as a source o f em-
p i r i c a l support to a theory o f speech a c t s However,
much more research must take p l a c e to f l e s h out the
t h e o r e t i c a l c onnections I have a l s o d e l i b e r a t e l y av-
oided problems o f computation h e r e , but hope the panel
w i l l discuss these i s s u e s , e s p e c i a l l y the u t i l i t y o f
computational mode is to ethnographers o f c o n v e r s a t i o n
Acknowledgements:
I would l l k e to thank Chip Bruce, Scott F e r t i g , and
Sharon 0 v l a t t for comments on an e a r l i e r d r a f t
References:
1 A l l e n , J A plan-based approach to speech act ~eco~-
n i t l o n (Tech Pep No 131/79) Toronto: U n i v e r s i , o r
T o r o n t o , Department o f Computer Science, January 1979o
2 Appelt, 0 P r o b l e m - s o l v i n g a p p l i e d to language gen-
e r a t i o n (This volume)
3- Bruce, B B e l i e f systems and language understandln~
(BBN Report NO Z973) Cambridge, Hess.: B o l t , Beranek
and Newman, January 1975
4 Bruce, B., & Newman, 0 I n t e r a c t i n g plans Cocjnl-
t i r e Science, 1978, ~, 195-233
5 C a r b o n e l l , J G J r POLITICS: Automated i d e o l o g i -
cal reasoning C o ~ n i t l v e Science, 1978, ~, 27-51
6 C l a r k , N H., & h s r s h e l l , C O e f l n i t e r e f e r e n c e and
mutual knowledge In A K J o s h l , I A Sag, & B L
Webber ( E d s ) , Proceedings o f the Workshop on Computa-
t i o n a l Aspects o f L i n g u i s t i c S t r u c t u r e and Discourse
S e t t i n g Ne, York: Cambridge U n i v e r s i t y Press, in press
7 Cohen, P R., & Levesque, H L Speech acts and the
r e c o g n i t i o n o f shared plans In Proceedlngs: Annual
meetin~ o f the Canadian Societ~ f o r the Computational
Study o f Intei, l i ~ e n c e , V i c t o r i a , B.C., 19B0
B Cohen, P R., & P e r r a u i t , C R Elements o f a p l a n -
based t h e o r y o f speech a c t s C o ~ n i t t v e Science, 1979, ~,
177-212
9 Donnell4m, K Speaker r e f e r e n c e s , d e s c r i p t i o n s , and
anaphora In P Cole ( E d ) , Syntax and semantics (Vol
~): Pra~matics New York: Academic Press, 1978
10 Grosz, B The r e p r e s e n t a t i o n and use o f focus in
d i a l o ~ u e understandin~ (Technical Note 151) Reflio Park,
C a l i f : Stanford Research I n s t i t u t e , A r t i f i c i a l I n t e l l i -
gence Center, J u l y 1977
I1 Hobbs, J R., 8 Evans, D E Co n v e r s a ti o n as planned
behavior (Technical Note 203) ~enlo Park, C a l l f :
Stanford Research I n s t i t u t e , A r t i f i c i a l I n t e l l i g e n c e
Center, 1979
12 Norgan, J L Toward a r a t i o n a l model o f d i s c o u r s e
c o m r e h e n s i o n , in O Waltz (Ed.), Proceedings: T h e o r e t -
cal Issues in Natural Language Understandinq Urbane:
U n i v e r s i t y o f I l l i n o i s , Coordinated Science L a b o r a t o r y ,
1978
13 P e r r a u l t , C R., & A l l e n , J F A plan-based a n a l -
y s i s o f i n d i r e c t speech acts In submission
14 P e r r a u i t , C R., & Cohen P R Inaccurate r e f e r -
ence In A K J o s h i , I A t jg, & B L Webber ( E d s ) ,
Proceedings o f the Workshop on Computational Aspects o f
L i n g u i s t i c S t r u c t u r e and 0i s co ur se S e t t i n g New York:
Cambridge U n i v e r s i t y Press, in press
15 Robinson, A E The i n t e r p r e t a t i o n o f verb ~hrases
in d i a l o 9 s (Technical Note 206) Henio Park, C a l i f :
S t a n f o r d Research I n s t i t u t e , A r t i f i c i a l I n t e l l i g e n c e Center, 1980
16 Schank, R., S Abe lson, R S c r i p t s , plans r ~ o a l s , and u n d e r s t a n d l n ~ H i l l s d a l e , N J : Erlbaum, 1977
17 S o l i d i , C F Understanding human a c t i o n , in Proceedings o f the conference on T h e o r e t i c a l Issues in Natural Language Processing Cambridge, ~ a s s , 1975
18 Seerte, J R Speech a c t s : An essay in the p h i l o s - ophy o f language Cambridge: Cambridge U n i v e r s i t y Press, 1969
19 Shannon, B ~/here-questions In Proceedings o f the Seventeenth Annual P~etin~ o f the ACL, San Diego, 1979
Pp 73-75
20 Wllensky, R Understandin~ 9De i-based s t o r i e s (Research Rap No 140) New Haven, Conn.: Yale U n i v e r -
s i t y , 0apartment o f Computer Science, September 1978
30