experience with the MUMBLE system. 5.2 UPenn: Cooperation and Clarification. Under the direction of Aravind Joshi and Bonnie Webber at the University of.
R e s e a r c h a n d D e v e l o p m e n t in N a t u r a l L a n g u a g e P r o c e s s i n g at BBN L a b o r a t o r i e s in t h e S t r a t e g i c Computing P r o g r a m
BBN L a b o r a t o r i e s , Inc. C a m b r i d g e , MA 02238
STAFF: Ralph Weischedel (Principal Investigator), Remko Scha, Edward Walker, Damaris Ayuso, Andrew Haas, Erhard Hinrichs, Robert Ingria, Lance Ramshaw, Varda Shaked, David Stallard
1
Background
BBN's r e s p o n s i b i l i t y is t o c o n d u c t r e s e a r c h and d e v e l o p m e n t in n a t u r a l l a n g u a g e i n t e r f a c e t e c h n o l o g y . This r e s p o n s i b i l i t y h a s t h r e e a s p e c t s : o
to demonstrate state-of-the-art t e c h n o l o g y in a S t r a t e g i c Computing a p p l i c a t i o n , c o l l e c t i n g d a t a r e g a r d i n g t h e e f f e c t i v e n e s s of t h e d e m o n s t r a t e d heuristics, !
o
to c o n d u c t r e s e a r c h in n a t u r a l l a n g u a g e i n t e r f a c e t e c h n o l o g y , as i t e m i z e d in t h e d e s c r i p t i o n of JANUS l a t e r in t h i s n o t e , a n d
o
to i n t e g r a t e t e c h n o l o g y f r om o t h e r n a t u r a l l a n g u a g e i n t e r f a c e c o n t r a c t o r s , i n c l u d i n g U S C / 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 , t h e U n i v e r s i t y of P e n n s y l v a n i a , a n d t h e U n i v e r s i t y of M a s s a c h u s e t t s .
Of t h e t h r e e i n i t i a l a p p l i c a t i o n s d e s c r i b e d in t h e overvi ew , t h e F l e e t Command C e n t e r B a t t l e M a n a g e m e n t P r o g r a m (FCCBMP) h a s b e e n t h e a p p l i c a t i o n p r o v i d i n g t h e d o m a i n in which o u r w o r k is b e i n g c a r r i e d out . The FCCBMP e n c o m p a s s e s t h e d e v e l o p m e n t of e x p e r t s y s t e m c a p a b i l i t i e s at t h e P a c i f i c F l e e t Command C e n t e r in Hawaii, a n d t h e d e v e l o p m e n t of an i n t e g r a t e d n a t u r a l l a n g u a g e i n t e r f a c e t o t h e s e new c a p a b i l i t i e s as well as t o t h e e x i s t i n g d a t a b a s e s a n d g r a p h i c d i s p l a y f a c i l i t i e s . BBN is d e v e l o p i n g a s e r i e s of i n c r e a s i n g l y s o p h i s t i c a t e d 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 s y s t e m s w hi c h will s e r v e as an i n t e g r a t e d i n t e r f a c e t o s e v e r a l f a c i l i t i e s a t t h e P a c i f i c F l e e t Command C e n t e r : t h e I n t e g r a t e d Data Base (IDB), w h i c h c o n t a i n s i n f o r m a t i o n a b o u t ships, t h e i r r e a d i n e s s s t a t e s , t h e i r c a p a b i l i t i e s , et c. ; t h e O p e r a t i o n s S u p p o r t G r o u p P r o t o t y p e (OSGP), a g r a p h i c s s y s t e m which c a n d i s p l a y l o c a t i o n s a n d i t i n e r a r i e s of s h i p s on maps; a n d t h e F o r c e R e q u i r e m e n t s E x p e r t S y s t e m (FRESH) w hi ch is b e i n g built by Texas Instruments. The
target
users
for
this
application
1
are
naval
o f f i c e r s i n v o l v e d in
decision
BBN Laboratories Incorporated
m a k i n g a t t h e P a c i f i c F l e e t C o m m a n d C e n t e r ; t h e s e a r e e x e c u t i v e s w h o s e e f f o r t is b e t t e r s p e n t o n n a v y p r o b l e m s a n d d e c i s i o n m a k i n g t h a n o n t h e d e t a i l s of w h i c h s o f t w a r e system offers a given i n f o r m a t i o n capability, how a p r o b l e m s h o u l d be divided t o m a k e u s e of t h e v a r i o u s s y s t e m s , o r h o w t o s y n t h e s i z e t h e r e s u l t s f r o m s e v e r a l sources into the desired answer. C u r r e n t l y t h e y do n o t a c c e s s t h e d a t a b a s e o r OSGP a p p l i c a t i o n p r o g r a m s t h e m s e l v e s ; i n s t e a d , on a r o u n d - t h e - c l o c k b a s i s , two o p e r a t o r s a c t as i n t e r m e d i a r i e s b e t w e e n t h e N a v y s t a f f a n d t h e c o m p u t e r s . The u t i l i t y of a ' n a t u r a l l a n g u a g e i n t e r f a c e in s u c h a n e n v i r o n m e n t is c l e a r . The s t a r t i n g p o i n t f o r d e v e l o p m e n t of t h e n a t u r a l l a n g u a g e i n t e r f a c e s y s t e m a t t h e P a c i f i c F l e e t C o m m a n d C e n t e r w a s t h e IRUS s y s t e m , w h i c h h a s b e e n u n d e r d e v e l o p m e n t a t BBN f o r a n u m b e r of y e a r s . A n e w v e r s i o n of t h i s s y s t e m , I R U S - 8 6 , h a s b e e n i n s t a l l e d in t h e FCCBMP t e s t b e d a r e a a t t h e P a c i f i c F l e e t C o m m a n d C e n t e r f o r demonstration. Further basic research on the problems of n a t u r a l language interfacing is c o n t i n u i n g , and the results of t h i s a n d f u t u r e research will b e i n c o r p o r a t e d i n t o a n e x t g e n e r a t i o n n a t u r a l l a n g u a g e i n t e r f a c e s y s t e m c a l l e d JANUS, t o be d e l i v e r e d to the Pacific Fleet Command C e n t e r at a l a t e r date. JANUS will s h a r e m o s t of i t s d o m a i n - d e p e n d e n t d a t a w i t h I R U S - 8 6 , a n d it will s h a r e o t h e r m o d u l e s a s well; I R U S - 8 6 will t h e r e f o r e be a b l e t o e v o l v e g r a d u a l l y i n t o t h e f i n a l v e r s i o n of JANUS.
2
IRUS-86:
The I n i t i a l T e s t B e d S y s t e m
The a r c h i t e c t u r e translation modules:
of IRUS [ B a t e s
which produces
83]
is
a
a syntactic
cascade
o
An ATN p a r s e r
o
A semantic interpreter which r e p r e s e n t a t i o n l a n g u a g e MRL.
o
A postprocessor
o
A translation module which produces a formula l a n g u a g e ERL ( " E x t e n d e d R e l a t i o n a l L a n g u a g e " ) .
o
A translation module which produces underlying data base access system.
of a
sequence
the
meaning
of
tree.
produces
for resolving anaphora
consisting
a
formula
of
a n d ellipsis.
a
of t h e
sequence
of
relational
commands
data
for
base
the
I R U S - 8 6 , t h e v e r s i o n of IRUS w h i c h is n o w i n s t a l l e d a t t h e P a c i f i c F l e e t C o m m a n d C e n t e r , is a v e r s i o n of IRUS w h i c h is e x t e n d e d in s e v e r a l w a y s . Two of t h e s e extensions are especially worth mentioning:
o
I R U S - 8 6 u s e s t h e NIKL s y s t e m [ M o s e r 83] t o r e p r e s e n t i t s d o m a i n m o d e l , i.e., the relationships between the predicates and relations of t h e m e a n i n g representation l a n g u a g e MRL. The NIKL d o m a i n m o d e l s u p p o r t s t h e s y s t e m ' s t r e a t m e n t of s e m a n t i c a n o m a l y , a n a p h o r a , a n d n o m i n a l c o m p o u n d s .
BBN L a b o r a t o r i e s I n c o r p o r a t e d
o
I R U S - 8 6 c o n t a i n s a new module w hi ch e x p l o i t s t h i s NIKL domain model to simplify MRL e x p r e s s i o n s ; t h i s m a k e s it p o s s i b l e t o t r a n s l a t e c o m p l e x MRLe x p r e s s i o n s i n t o ERL c o n s t a n t s , t h u s allowing f o r s i g n i f i c a n t d i v e r g e n c e s b e t w e e n t h e i n p u t English a n d t h e s t r u c t u r e of t h e u n d e r l y i n g d a t a b a s e [ S t a l l a r d 86].
In addition to accessing the NIKL domain model, the parser, semantic interpreter and M R L - t o - E R L translator access other knowledge sources which contain d o m a i n dependent information:
o
the lexicon,
o
the semantic interpretation
o
the M R L - t o - E R L mapping rules for individual M R L constants, which introduce the details of underlying system structure, such as file and field names.
rules for individual concepts,
To p o r t IRUS t o t h e n a v y domain, t h e r e l e v a n t d o m a i n - d e p e n d e n t d a t a h a d to be s u p p l i e d to t h e s y s t e m . This t a s k is b e i n g a c c o m p l i s h e d b y p e r s o n n e l at t h e Naval Ocean S y s t e m s C e n t e r (NOSC). In August, 1985, BBN p r o v i d e d NOSC with a n in itia l prototype system containing small example sets of l e x i c a l e n t r i e s , semantic i n t e r p r e t a t i o n r u l e s , a n d M R L - t o - E R L r u l e s ; u s i n g a c q u i s i t i o n t o o l s p r o v i d e d by BBN, NOSC p e r s o n n e l h a v e b e e n e n t e r i n g t h e r e s t of t h e d a t a . I R US - 86 was d e l i v e r e d to t h e FRESH d e v e l o p e r s a t T e x a s I n s t r u m e n t s in J a n u a r y 1986, was i n s t a l l e d in a t e s t b e d a r e a of t h e P a c i f i c F l e e t Command C e n t e r in April 1986, a n d will be d e m o n s t r a t e d in J u n e 1986. C u r r e n t l y , t h e l e x i c o n a n d t h e d o m a i n d e p e n d e n t r u l e s of t h e s y s t e m onl y c o v e r a r e l a t i v e l y small p a r t of t h e OSGP c a p a b i l i t i e s a n d t h e files a n d a t t r i b u t e s of t h e I n t e g r a t e d Data Base. Once e n o u g h d a t a h a v e b e e n e n t e r e d so t h a t t h e s y s t e m c o v e r s a s u f f i c i e n t l y l a r g e p a r t of t h e d a t a b as e, it will be t r i e d o u t in a c t u a l u s e by Navy p e r s o n n e l . This will e n a b l e us to g a t h e r d a t a a b o u t t h e way t h e s y s t e m p e r f o r m s in a r e a l e n v i r o n m e n t , and t o f i n e t u n e t h e s y s t e m in v a r i o u s r e s p e c t s . F o r i n s t a n c e , I R U S - 8 6 m a k e s u s e of shallow h e u r i s t i c m e t h o d s t o a d d r e s s some a s p e c t s of 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 s u c h as a n a p h o r a a n d ellipsis f o r which g e n e r a l s o l u t i o n s a r e still r e s e a r c h i s s u e s . The FCCBMP a p p l i c a t i o n p r o v i d e s a t e s t b e d in w hi ch s u c h h e u r i s t i c m e t h o d s c a n be e v a l u a t e d , a n d e n h a n c e m e n t s t o t h e m d e v e l o p e d a n d t e s t e d , as p a r t of t h e e v o l u t i o n a r y t e c h n o l o g i c a l growth i n t e n d e d to c o n t i n u e t h r o u g h o u t the Natural L a n g u a g e T e c h n o l o g y e f f o r t of t h e S t r a t e g i c C o m p u t i n g P r o g r a m .
3
B B N Laboratories Incorporated
3
F u n c t i o n a l Goals for JANUS
The I R U S - 8 6 system excels by its clean, modular structure, its broad syntactic/semantic coverage, its sophisticated domain model, and its systematic treatment of discrepancies between the English lexicon and the data base structure. We thus expect that it will demonstrate considerable utility as an interface c o m p o n e n t in the F C C B M P application. Nevertheless, I R U S - 8 6 shares with other current systems several limitations which should be overcome if natural language interfaces are to b e c o m e truly "natural". In developing JANUS, the successor of IRUS-86, we shall attempt to overcome some of those limitations. The areas of increased functionality w e are considering are: semantics and knowledge representation, ill-formedness, discourse, cooperativeness, multiple underlying systems, and knowledge acquisition.
3.1
Semantics and Knowledge Representation
IRUS-86, like m o s t o t h e r c u r r e n t s y s t e m s , r e p r e s e n t s s e n t e n c e m e a n i n g s as f o r m u l a s of a l o g i c a l l a n g u a g e which is a sl i ght e x t e n s i o n of f i r s t - o r d e r logic. As a c o n s e q u e n c e , m a n y i m p o r t a n t p h e n o m e n a in E ngl i sh h a v e no e q u i v a l e n t in t h e m e a n i n g representation language, a n d c a n n o t be d e a l t with c o r r e c t l y , e.g., m o d a l i t i e s , propositional attitudes, generics, collective quantification, and context-dependence. Thus, o n e f o r e g o e s o n e of t h e m ost i m p o r t a n t p o t e n t i a l a s s e t s of a n a t u r a l l a n g u a g e interface: t h e c a p a c i t y of e x p r e s s i n g c o m p l e x s e m a n t i c s t r u c t u r e s in a s u c c i n c t a n d c o m f o r t a b l e way. In JANUS, we will t h e r e f o r e a d o p t a new m e a n i n g r e p r e s e n t a t i o n l a n g u a g e w h i c h c o m b i n e s f e a t u r e s f r om PHILIQAI's e n r i c h e d l a m b d a - c a l c u l u s [ S c h a 76] with i d e a s u n d e r l y i n g M o n t a g u e ' s I n t e n s i o n a l Logic [ M o n t a g u e 70], a n d p o s s i b l y a d i s t r i b u t e d q u o t e - o p e r a t o r [Haas 86]. It will h a v e s u f f i c i e n t e x p r e s s i v e p o w e r t o i n c o r p o r a t e a v e r s i o n of C a r l s o n ' s t r e a t m e n t of g e n e r i c s [ C a r l s o n 79], a v e r s i o n of S c h a ' s t r e a t m e n t of q u a n t i f i c a t i o n [ S c h a 81], M o n t a g u e ' s t r e a t m e n t of m o d a l i t y , a n d v a r i o u s p o s s i b l e approaches to propositional attitudes and context-dependence. In adopting a higher order logic as proposed, one confronts problems of formula simplification and the need to apply meaning postulates to reduce the semantic representation of an input sentence to an expression appropriate to the underlying system, e.g., a relational algebra expression in the case that the underlying system is a data base. To do this, w e will investigate the limited inference mechanisms of K L T W O [Moser 83, Vilain 85], following up on our previous w o r k [Stallard 86]. The advantage of these inference mechanisms is their tractability; discovering their p o w e r and limitations in this complex problem domain should be an interesting result.
4
BBN L a b o r a t o r i e s
3.2
Incorporated
Discourse
T h e m e a n i n g of a s e n t e n c e d e p e n d s in m a n y w a y s o n t h e c o n t e x t w h i c h h a s b e e n set up by the preceding discourse. IRUS a n d o t h e r s y s t e m s , h o w e v e r , c u r r e n t l y i g n o r e m o s t of t h e s e d e p e n d e n c i e s , a n d e m p l o y a r a t h e r s h a l l o w m o d e l of d i s c o u r s e s t r u c t u r e . To a l l o w t h e u s e r t o e x p l o i t t h e full e x p r e s s i v e p o t e n t i a l of a n a t u r a l l a n g u a g e interaction, the system must track topics, reference times, possible antecedents for a n a p h o r a , e t c . ; it m u s t b e a b l e t o r e c o g n i z e t h e c o n s t i t u e n t u n i t s of a d i s c o u r s e a n d the subordination or coordination relations obtaining between them. A substantial a m o u n t of w o r k h a s b e e n d o n e a l r e a d y on s e v e r a l of t h e s e i s s u e s , m u c h of it b y BBN researchers [ S i d n e r 85, H i n r i c h s 81, P o l a n y i 84, G r o s z 86]. R e s e a r c h in t h i s a r e a continues under a separate DARPA-funded contract. We.expect to be able to integrate s o m e of t h e r e s u l t s of t h a t r e s e a r c h in t h e JANUS s y s t e m .
3.3
M-formedness
A n a t u r a l i n t e r f a c e s y s t e m s h o u l d b e f o r g i v i n g of a u s e r ' s d e v i a t i o n s f r o m i t s expectations, be they misspellings, typographical errors, unknown words, poor syntax, incorrect presuppositions, fragmentary forms, or violated selection restrictions. E m p i r i c a l s t u d i e s s h o w t h a t a s m u c h a s 25% of t h e i n p u t to d a t a b a s e q u e r y s y s t e m s is ill-formed. IRUS c u r r e n t l y h a n d l e s s o m e c l a s s e s of i l l - f o ' r m e d n e s s b y u s i n g a c o m b i n a t i o n of shallow heuristics and user interaction. It c a n c o r r e c t f o r t y p o g r a p h i c a l m i s s p e l l i n g s , for omitted determiners or prepositions, and for some ungrammaticalities, like determiner-noun and subject-verb disagreement. T h e JANUS s y s t e m will e m p l o y a more general approach to ill-formedness that will h a n d l e a larger class of ungrammatical constructions a n d a l a r g e r c l a s s of w o r d s e l e c t i o n p r o b l e m s , a n d t h a t will a l s o e x p l o r e c o r r e c t i n g s e v e r a l t y p e s of s e m a n t i c i l l - f o r m e d n e s s . T h e s e c a p a b i l i t e s h a v e m a j o r i m p l i c a t i o n s f o r t h e c o n t r o l of t h e u n d e r s t a n d i n g process, since considering such possibilities can exponentially expand the search space. Maintaining control will r e q u i r e care in i n t e g r a t i n g the ill-formedness c a p a b i l i t y i n t o t h e r e s t of t h e s y s t e m , a n d a l s o m a k i n g m a x i m a l u s e of t h e g u i d a n c e t h a t c a n b e d e r i v e d f r o m a m o d e l of t h e d i s c o u r s e a n d u s e r ' s g o a l s t o c o n s t r a i n t h e search.
3.4
Cooperativeness
A t r u l y h e l p f u l s y s t e m s h o u l d n o t r e a c t t o t h e l i t e r a l m e a n i n g of a s e n t e n c e , b u t to its perceived intent. If in t h e c o n t e x t of a g i v e n a p p l i c a t i o n it is p o s s i b l e t o characterize the goals that a user may be expected to be pursuin$ through his interaction with the system, the system should try to infer from the user-input what t h e u n d e r l y i n g g o a l c o u l d be. A s y s t e m c a n do t h i s b y a c c e s s i n g a g o a l - s u b g o a l
5
B B N Laboratories Incorporated
hierarchy which links the speech acts expressed by individual utterances to the global goals that the user m a y have. This strategy has been applied successfully to rather small domains [Allen 83, Sidner 85]. We wish to investigate whether it carries over to the F C C B M P applications.
3.5
Modelling the Capabilities o_.fMultiple System
The w a y in which I R U S - 8 6 decides whether an input sentence translates into an IDB query or an O S G P c o m m a n d m a y be refined. There is a need for w o r k on what kind of knowledge would be necessary to interface smoothly and intelligently to multiple underlying systems. A reasoning c o m p o n e n t is needed that can determine which underlying system or systems can best fulfill a user's request. Such a reasoning c o m p o n e n t would have to combine a model of the capabilites of the underlying systems with a model of the user goals and current intentions in the discourse context in order to choose the correct system(s). Such a model would also be useful for providing supporting information to the user.
3.8
Knowledge Acquisition
Further research is a l s o c a l l e d f o r t o e x p a n d t h e p o w e r of t h e k n o w l e d g e a c q u i s i t i o n t o o l s t h a t a r e u s e d in a d d i n g t o t h e l e x i c o n , t h e s e t of c a s e f r a m e r u l e s , t h e ~ m o d e l of d o m a i n p r e d i c a t e s , a n d t h e s e t of t r a n s f o r m a t i o n rules between the Meaning Representation L a n g u a g e a n d t h e l a n g u a g e s of t h e u n d e r l y i n g s y s t e m s . The a c q u i s i t i o n t o o l s a v a i l a b l e in IRUS, u n l i k e t h o s e in s o m e o t h e r s y s t e m s , a r e n o t t i e d t o t h e s p e c i f i c f i e l d s a n d r e l a t i o n s in t h e u n d e r l y i n g d a t a b a s e . The a c q u i s i t i o n t o o l s s h o u l d w o r k o n t h e h i g h e r l e v e l of t h e d o m a i n m o d e l , s i n c e t h a t p r o v i d e s a m o r e general and transportable result. The k n o w l e d g e a c q u i s i t i o n f a c i l i t i e s f o r JANUS will a l s o n e e d t o b e r e d e s i g n e d t o s u p p o r t a n d t o m a k e m a x i m a l u s e of t h e p o w e r of t h e new meaning representation l a n g u a g e b a s e d on i n t e n s i o n a l logic.
4
4.1
New Underlying Technologies
Coping with Ambiguity
The n e w f u n c t i o n a l i t i e s we d e s c r i b e d in t h e p r e v i o u s s e c t i o n , a n d t h e t e c h n i q u e s we i n t e n d t o u s e t o a c h i e v e t h e m , r a i s e a n i s s u e w h i c h h a s i m p o r t a n t c o n s e q u e n c e s f o r t h e d e s i g n of JANUS: we will b e f a c e d w i t h a n e x p l o s i o n in t h e n u m b e r of interpretations t h a t t h e s y s t e m will h a v e t o p r o c e s s ; e v e r y s e n t e n c e will b e m a n i f o l d ambiguous. One s o u r c e of t h i s p h e n o m e n o n is t h e i m p r o v e m e n t of t h e s e m a n t i c c o v e r a g e a n d t h e b r o a d e n i n g of t h e d i s c o u r s e c o n t e x t . Distinctions and ambiguities w h i c h so f a r w e r e i g n o r e d will b e d e a l t w i t h : f o r i n s t a n c e , d i f f e r e n t i n t e r p r e t a t i o n and
6
BBN L a b o r a t o r i e s
Incorporated
s c o p e s of q u a n t i f i e r s will b e c o n s i d e r e d , a n d d i f f e r e n t a n t e c e d e n t s f o r p r o n o u n s . Even m o r e s e r i o u s is t h e p r o c e s s i n g of i l l - f o r m e d s e n t e n c e s , w h i c h m a y r e q u i r e t r y i n g o u t all p a r t i a l interpretations to see which one c a n be e x t e n d e d to a complete interpretation after relaxing one or more constraints.
To cut d o w n on the processing of spurious interpretations, it is very important that interpretations of sentences and their constituents be tested for plausibility at an early stage. Different techniques must probably be used in conjunction: o
Simplification transformations m a y s h o w that an interpretation is absurd, by reducing it to T R U E or FALSE or the empty set.
o
The d i s c o u r s e c o n t e x t a n d t h e on expected sentences.
4.2
m o d e l of t h e
user's
goals impose constraints
Parallel Parsing
S i n c e s o m e of t h e t e c h n i q u e s t h a t we i n t e n d t o u s e t o f i g h t t h e a m b i g u i t y explosion are themselves rather computation-intensive, it is c l e a r l y u n a v o i d a b l e t h a t t h e i m p r o v e d s y s t e m f u n c t i o n a l i t y t h a t we aim f o r will l e a d to a c o n s i d e r a b l e i n c r e a s e in t h e a m o u n t of p r o c e s s i n g r e q u i r e d . To a v o i d a s e r i o u s d e c r e a s e of t h e n e w s y s t e m ' s r e s p o n s e t i m e s , we will t h e r e f o r e m o v e it t o a s u i t a b l e p a r a l l e l m a c h i n e s u c h a s BBN's B u t t e r f l y o r M o n a r c h , r u n n i n g a p a r a l l e l C o m m o n Lisp. This in i t s e l f h a s rather serious consequences for the software design. It m e a n s t h a t f r o m t h e o u t s e t we will k e e p p a r a l l e l i z a b i l i t y of t h e s o f t w a r e in mind.
We h a v e b e g u n t o a d d r e s s t h i s i s s u e in t h e a r e a of s y n t a x . A new d e c l a r a t i v e g r a m m a r is b e i n g w r i t t e n , w h i c h will u l t i m a t e l y h a v e a c o v e r a g e of E n g l i s h l a r g e r t h a n t h e c u r r e n t RUS g r a m m a r ; t h e g r a m m a r is w r i t t e n in a s i d e - e f f e c t - f r e e f o r m a l i s m (a context-free g r a m m a r with v a r i a b l e s ) so t h a t d i f f e r e n t p a r s i n g a l g o r i t h m s m a y be explored which are easily parallelizable. The f i r s t s u c h a l g o r i t h m w a s i m p l e m e n t e d in May 1986 o n BBN's B u t t e r f l y .
5
5.1
C o n t r i b u t i o n s from Other Sites
ISI/UMass:
Generation
We s h o u l d n o t e x p e c t t h a t JANUS will a l w a y s b e a b l e t o a s s e s s c o r r e c t l y w h i c h interpretation of a s e n t e n c e is t h e i n t e n d e d o n e . In l i g h t of s u c h s i t u a t i o n s , it is v e r y i m p o r t a n t t h a t t h e s y s t e m c a n give a p a r a p h r a s e of t h e i n p u t t o t h e u s e r , w h i c h shows the system's interpretation. This m a y b e d o n e e i t h e r e x p l i c i t l y o r a s p a r t of the answer. To b e a b l e t o d e v e l o p s u c h c a p a b i l i t i e s , w o r k o n N a t u r a l L a n g u a g e G e n e r a t i o n is n e e d e d . At U S C / I S I a p r o j e c t d i r e c t e d b y William M a n n a n d N o r m a n
7
BBN L a b o r a t o r i e s I n c o r p o r a t e d
S o n d h e i m e r is u n d e r w a y t o d e v e l o p t h e g e n e r a t i o n s y s t e m PENMAN, u s i n g t h e NIGEL s y s t e m i c g r a m m a r . PENMAN will be i n t e g r a t e d to b e c o m e t h e g e n e r a t i o n c o m p o n e n t of JANUS. PENMAN i t s e l f c o n s i s t s of s e v e r a l s u b c o m p o n e n t s . Some of t h e s e , s p e c i f i c a l l y t h e " t e x t p l a n n i n g " c o m p o n e n t , will be d e v e l o p e d t h r o u g h j o i n t w o r k b e t w e e n USC/ISI a n d David McDonald a t t h e U n i v e r s i t y of M a s s a c h u s e t t s , b a s e d on t h e f a r t e r ' s e x p e r i e n c e with t h e MUMBLE s y s t e m .
5.2
UPenn:
Cooperation and Clarification
U n d e r t h e d i r e c t i o n of A r a v i n d J o s h i a n d Bonni e Webber a t t h e U n i v e r s i t y of P e n n s y l v a n i a , several f o c u s s e d s t u d i e s have b e e n c a r r i e d out to investigate various a s p e c t s of c o o p e r a t i v e s y s t e m b e h a v i o u r a n d c l a r i f i c a t i o n i n t e r a c t i o n s . (For m o re d e t a i l , s e e t h e i r p a p e r in t h i s i s s u e . ) As p a r t of t h e S t r a t e g i c Com put i ng N a t u r a l L a n a u g e e f f o r t , U P e n n will e v e n t u a l l y d e v e l o p t h i s i n t o a m o d u l e which c a n be i n t e g r a t e d i n t o JANUS to f u r t h e r e n h a n c e its c a p a b i l i t i e s .
BBN L a b o r a t o r i e s I n c o r p o r a t e d
References
[Allen 83]
Allen, J.F. Recognizing I n t e n t i o n s from N a t u r a l L a n g u a g e U t t e r a n c e s . In M. B r a d y a n d R.C. Berwick ( e d i t o r s ) , C o m p u t a t i o n a l Models of D i s c our s e , p a g e s 1 0 7 - 1 6 6 . M a s s a c h u s e t t s I n s t i t u t e Technology P r e s s , 1983.
[Bates 83]
Bates, M. and Bobrow, R.J. A T r a n s p o r t a b l e N a t u r a l L a n g u a g e I n t e r f a c e for I n f o r m a t i o n Retrieval. In P r o c e e d i n g s of the 6t h A n n u a l I n t e r n a t i o n a l ACM SIGIR Conference. ACM Special I n t e r e s t Group on I n f o r m a t i o n Retrieval and American S o c i e t y for I n f o r m a t i o n S c i e n c e , Washington, D.C., June, 1983.
[Carlson 79]
Carlson, G. R e f e r e n c e to K i n d s i n E n g l i s h . G a r l a n d P r e s s , New York, 1979.
[Grosz 86]
Grosz, B.J. and Sidner, C.L. The S t r u c t u r e s of Discourse S t r u c t u r e . In L. P o l a n y i (editor), D i s c o u r s e S t r u c t u r e . Ablex P u b l i s h e r s , Norwood, NJ, 1986.
[Haas 86]
Haas, A.R. A S y n t a c t i c T h e o r y of Belief a n d Action. A r t i f i c i a l I n t e l l i g e n c e , 1986. Forthcoming.
[Hinrichs 81]
Hinrichs, E. Temporale A n a p h o r a im E n g l i s c h e n . 1981. U n p u b l i s h e d ms., U n i v e r s i t y of T u e b i n g e n .
[Montague 70]
Montague, R. P r a g m a t i c s a n d I n t e n s i o n a l Logic. S y n t h e s e 2 2 : 6 8 - 9 4 , 1970.
[Moser
83]
[ P o l a n y i 84]
Moser, M.G. An Overview of NIKL, the New I m p l e m e n t a t i o n of KL-ONE. In Sidner, C. L., et al. ( e d i t o r s ) , R e s e a r c h i n Knowledge R e p r e s e n t a t i o n f o r 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 - A n n u a l Report, f S e p t e m b e r 1982 - 31 A u g u s t 1983, p a g e s 7 - 2 6 . BBN L a b o r a t o r i e s R e p o r t No. 5421, 1983. Polanyi, L. a n d Scha, R. A S y n t a c t i c A p p r o a c h to D i s c o u r s e S e m a n t i c s . In P r o c e e d i n g s of Int'l. C o n f e r e n c e on C o m p u t a t i o n a l L i n g u i s t i c s . S t a n f o r d University, S t a n f o r d , CA, 1984.
BBN L a b o r a t o r i e s I n c o r p o r a t e d
[Scha 76]
Scha, R.J.tI. S e m a n t i c Types in PHLIQA1. In P r o c e e d i n g s of the 6 t h I n t e r n a t i o n a l C o n f e r e n c e on C o m p u t a t i o n a l Linguistics. 1978.
[Scha 81]
Scha, R.J.H. D i s t r i b u t i v e , Collective a n d C u m u l a t i v e Q u a n t i f i c a t i o n . Formal Methods i n the S t u d y of L a n g u a g e , P a r t 2. M a t h e m a t i s c h C e n t r u m , Amsterdam, 1981, p a g e s 4 8 3 - 5 1 2 . R e p r i n t e d in: J.A.G. G r o e n e n d i j k , T.M.V. J a n s s e n a n d M.B.J. S t o k h o f ( e d i t o r s ) . Truth, I n t e r p r e t a t i o n a n d I n f o r m a t i o n . GRASS 3. D o r d r e c h t , Foris, 1984.
[ S i d n e r 85]
Sidner, C.L. Plan p a r s i n g for i n t e n d e d r e s p o n s e r e c o g n i t i o n in d i s c o u r s e . Computational I n t e l l i g e n c e 1 ( 1 ) : 1 - 1 0 , F e b r u a r y , 1985.
[ S t a l l a r d 86]
S t a l l a r d , D.G. A Terminological Simplification T r a n s f o r m a t i o n for N a t u r a l L a n g u a g e Question-Answering Systems. In P r o c e e d i n g s of the 2 4 t h A n n u a l M e e t i n g of the A s s o c i a t i o n f o r Computational L i n g u i s t i c s . A s s o c i a t i o n for C o m p u t a t i o n a l Linguistics, June, 1986.
[Vilain 85]
Vilain, M. The R e s t r i c t e d L a n g u a g e A r c h i t e c t u r e of a Hybrid R e p r e s e n t a t i o n System. In P r o c e e d i n g s of IJCAI85, p a g e s 5 4 7 - 5 5 1 . I n t e r n a t i o n a l Joint C o n f e r e n c e s on Artificial I n t e l l i g e n c e , Inc., Morgan K a u f m a n n P u b l i s h e r s , Inc., Los Angeles, CA, August, 1985.
10
