American Journal of Computational Linguistics Mi.crof i che 40 
NATURAL LANGUAGE UNDERSTAND I NG SYSTEMS 
WITWIN THE An I1 PARADIGM: 
A SURVEY AND SOME COMPARISONS 
YORICK WILKS 
DEPARTMENT OF ARTIFICIAL INTELLIGENCE 
UNIVERSITY OF EDINBURGH 
EDINBURGH EH8 9NW 
Revised version of Stanford Artificial Intelligence Laboratory 
Memorandum 237, supported by contract number NIE-P-75-0026 with 
the National Institute of Education. 
Zoptp-ight 1976 by the Association for Computational Linguistics 
ABS'TIWCT: The paper surveys the najcr prcjecte on th.e understanding 
of natural language that fall within what nay now 5e calle3 t5e 
artificial intelligence paradigm fcr natural Language syste~s. 
- 
c4z,'2e 
space is devoted ta arguing that the &paradigm is new a red: itv and 
different in significant respects from the generabive paradiLm ~f 
present day linguistics. The caalparison's between systems tekt3-c 
I1 
round questions aL.-ut UIC lc~~l, cc~ltralitb* and ~hancnt-n~1c7giial 
plnusik~ility" of the kn~~wlt~~l~.~~ and inft-rt.nct.s t1.1.1t- must .rv.~~l,~t-'Lt- 
to a systtlm that is to uurldt*rst,~nd ~-\*t-r>*~l.~y ls~lyu~~gr? . 
Contents 
I ntxoduction 
Winograd's Understanding System 
Some discussion of SHRDLU 
Some more general background issucs 
Second generation systems 
Some comparisons and contrasts 
Conclusion 
References 
in his report to the Science Res~arch Council, on the stato aE 
Artificial Intelligence, Sir Suer, Lighthi11 (1973) qaw &oat cf tho field 
a eather bad propnosis. One of the few hopful 
igns ho am war Winwredls 
(1972) natural language wderstanding system. Yet, only e ye-car later, 
Winograd had st~ppd wrk on ae system he mnstruuted, and had kwgurr A nnlar 
one on entirslx different principles.** He went SJ far, in a survey lecture 
(Winograd '737 of extrnordinnry modesty Ln a field not krtawtl for its mall 
cwputer systerns designed to understand natural languaga, and \rent on tc 
describe others second generation' systems. 
I shall xeturn later to this metaphor of generations, but what is cne 
to say in general terns of a field where yesterday's brightest spots are 
today's first generation systems, even though they have not been criticised 
in print, nor shown in any generally acceptable yay to be fundamentally 
wrong? Part of the answer lies in the profound role of fashion in Artificial 
Intelligence in its present pre-scientific phase. A cynital American pro- 
fessor remarked recently that Artificial ~ntelligencd (AX) had an affair with 
someonels work every year or two, and that, just as there were no reasons for 
galling in love, so, later, there were no reasons for falling out again. In 
tho csse of Winograd's work it is imprtant now to resist this fashiony and 
re-emphasize what a good piece of research it was, as 3 shall inl a m~ment. 
Another part of the answer lies ,in the still fundamental role of - meta- 
physical criticism in AI. In the field of computer vision things are bad 
enough, in that anybody who can - see feels entitled to criticise a system, on 
the ground that he is sure - he does not see using such and suck principles, 
In the field of natural language understanding things are worse: not only 
does anyone whmo can speak and write feel free to criticise on the correspandina 
grounds, but in addition theze are those trained in disciplines parasitic 
upon natural language, linguists and logicians, who often know in addition 
how things bIUST BE DONE on a priori groundsa. It is this metdphysical aspect 
of the suhject that gives its disputes their characteristically acrbnious 
- - - - . - . . -- - - . - - . -- -- - 
*"see (Winograd ' 74b) 
flavour . 
In this paper I want to sort out a little what is agreed and what is 
noti 
what are swre of the outstanding disputes and how testable are the 
claims being made. 
If what follows seems unduly philosophical, it should 
be remetsabered that Uttle - is agreed, and almost no achievements are beyond 
question. To pretend otherwise, by concentrating only tm the detaibof 
established programs, 
~uld be meretricious and misleading. 
To euntey an enewetic field like thie one is inevitably to laavo a 
great deal of excellent work unextiminad, at least if one ia going to do 
more than give a paragraph to each research project. I have left out of 
cotasideration at least seven groups of projects: 
(1) 
Early work in Artificial Intelligence and Natural Language 
that has been sumeyed by Wfnograd (1973) and Simmons (1970a) 
among others. 
(2) 
Work by graduate students of, or intellectually dependent upsn 
that of, people discussed in same detail here. 
(3) 
Wxk that derives essentially from projects described in detail 
here. This embraces several groups interested in testing 
psychological hypotheses, as re11 as others constructing large- 
scale systems for speech recognition. I have devoted no space 
to speech recognition as such here, for it seems to me to depend 
upon the quality of semantic and inferential understanding as 
much as anything, and so I have concentrated upon this more 
fundamental task. 
(4) Work on language generators, as opposed to analysers and under- 
standers. 
They are essential for obtaining any testable output, 
but are thearetically secondary. 
(5) All the many and varied reasoning schemzs now availdle in AI, 
hcluding PLANNER (Hewitt 19691, QA4 fRulifson et a1 19721, MERLIb 
(*ore and Newell 197a as well as automatic programming (Balzer 
et a1 1974) (tleidor- 174) and debugging (Sussman 1974) projects, 
many of which are producing formalisas that appear increasingly 
like natural lwuaae . 
(6) Conservative reasoning schames, such as first order predcicatc! 
calculus, thab have boen appliud ts, or ild~~~uatsrf for, the 
aqalysis of natural language: tblma~thy and Hayes L?>t.?) tCalrr?n 
1972) (Sandewall 1972) . 
(71 X have also ignored, as one musk in oldor to write at all fro a 
rapidly changing field, Uaa interpr,etntion given t~ d4inskjw' a 
(1975) notian bf l"'frmelq auring 1975 by Chsmiak and ScEaadc. 
During this year Lmth have product4 skctch~a Eer a rrprasant- 
aticn UP knuwladqrs sn a larger scallr than any 3ls;usss.l ln this 
survey: roughly speaking, they have each produced a schmd Pok 
a whole story. The value and function of sucll a larger-scale 
representation is much under discussion at the manent, bdt acne 
of it invalidates what! is contained here, except for sane 
qualification to the position of Schank which is noted under 
the heading "Centrality"' in section 6. 
The exclusions under (2) above are particularly unfair to the wark in 
the unpublished theses of Rieger 11974) and McDesmott (1974), and can only 
be justified, like those of sections (5) and (6) above, by space, bias and 
the considerations advanced in a later section of this survey concerning 
what it is for A1 research to be nlmut natural lmquaqe, ra'tht3r than slwut. 
sanething else, like human psych~l~~~y, or logic, as the bargaining hhaviour 
of chil-dsen under stress. 
One final remark &wut the style of this survey. I have not indulged 
the n~rmal critical luxury of careful and extensive quotation from authoys 
followed by detailed and meticulous criticism. That would be wholly in- 
appropriate in the present state of things. A great deal of work is being 
done at the moment, and many of the principal researchers change their views 
on very fundamental questions between one paper and the next without drawiw 
any attention to the fact. Cheap self-contradictions and changes of mind 
are all too easy to find, so criticism and smparisons are best drawn with a 
very broad brush and a light stroke. 
2. Winograd's Understanding System 
Winograd's systea runs as a dialogue, in real time, between a human 
operator who types in meSqes, and the system proper, called SHRDLU, which 
displays on a screen pictures of a closed world of coloured blocks and 
pyraida, a box in- which they can be put, and an arm or crane khat can 
move che objects about. 
SHRDLU displays its replies to the operator by 
writing on the samq screen. 
The following is a discontinuous sample of 
the dialogue Winograd giws in his book. SHIIDLU1s replies are in the 
upper case r 
eick up the big red block, 
OK 
find a block which is taller than the one you are holding and 
put it into the box. 
BY IIT', I ASSUME: YOU MEAN TKE BLOCK WHICH IS TALfwER THRN Tm 
ONE I AM HOLDING 
what does the box contain 
THE BLUE PYMID RND THE BLUE BLOCK 
had you touched any pyramid before you put the green one on 
the Lkttle cube 
YES, TEE GREEN ONE 
when did you pick it up 
WEIILE.1 WAS STACKING tlP THE RED CUBE, A LARGE RED BLOCK AND A 
EARGE WEN CUBE. 
why 
TO GET RID OF IT. 
Thia, ingenious program was also ahle to accept new definitions.& words, 
such as steeple'; to make use of what it knew about the p~operties of the 
objects described, such as that a block could have its top cleared off, but 
a pyramid could not; and also ta remember what it had done before, as in the 
sample above. 
The syn-tactic analySis program was written in PR%RAMMAR, a procedural 
language related to PLANNER (see Hewitt '69). This means that a familia 
phase structure rule such as 
s+NP+w 
(to be interpreted: a sentence consists of a noun phrase followed by a verb 
phrase) would be expressed as: 
(PDEFIME SENTENCE 
((( PARSE NP) NIL FAIL) 
(( PAFSE VP) FAIL FAIL RETURN))) 
The details of the notation need not detairius at this point; what 
Ls important is that Winograd's gramuax 4s not tile cmnventirrnaL list of 
culas, but small sub-programs Like tha lines above, that actually xaysooant 
x-o~iiures for iulposing the desirad grstmalieA1 structure, 
The first leva1 of linguistic pm&ur~s in the system applies a 
systemic grammar' , dur to M.A. K. Mallidal* (1970) , which inapses a hierarch- 
ical structure of clauses on tihe input senterac&s\, which secb tc' b~ dram 
from a vocabulary of about 175 ims\ls. 
Winogradas parsing is top down, and depth first, with na automatic 
back up. The parsing progrim fur each griuxnatical catcq~r~~ is 
n functional 
definition in PRfXZWWR, which can be stated either as &VP, fcr SEWPEHCE, 
or as a flow-chart as below for VP: 
DEFIWJ pxqram VP 
REm failure 
Yes 
L 
Here is Winograd's own account of the start of this top-down parsing 
procedure for the sentence "Pick up a red block" 
(where the material in 
C 1 is added explanation and not Winogradas om) : 
"The CLRUSE program looks at the first wrd, to decide what writ the 
CLRUSE begins with. 
If it sees an adverb, it assumes the sentence begins 
with a single-word modifier tslowly, Jack lifted the book] ; 
iP it sres a 
preposition, it looks .for an initial PREP6 Con top of the hill stood a tree] 
If it sees a BINOBR, it calls the CLAUSE program to look for a BOUND CLAUSE 
C~efore you get there, we left]. 
In English (and possibly all languages) 
the firsb word of a construction often gives a very goad clue as to what that 
construction will be. fn this case, "pick" is a verb, and indicates that we 
may have an IHPERATIW CLAUSE. The program. starts the VO program witla the 
initial VG feature. list (VG IWER), looking for a VG of this type. This 
must either begin with some form of the verb "do" [Do not call me!] or with 
the main verb itself [Call me!]. Since the next word is not: "do" it checks 
the next word in the input (in U~is case still the first word) :o see whether 
it is the infinitive form of a verb. If SO, it is to be attached to the 
parsing tree, and given the additionql feature MVB (main verb). The current 
structure can be diagramad as: 
(CLAUSE MAJOR) 
(VG IWER) 
(VB MVB INF TRANS ,WRT -------------- pick 
TWS AND VPRT cmfw fran the definition of the word "pick" when we zalled 
the function PMSq for a word.4' 
Mter this syntactic parsing, a number of "semantic specidlists'' attach 
cwbantic structures to specific syntactic dnes. A semantic definition of an 
In the case of "a red cube", the follo~ing structure is built up by an 
NP "semantic specialist" 
(GOAL (IS ?X BLOCK)) 
(GOAL (COLOR ?X RED))_ 
(EQDIM ?x)-------------------~--- PLANNER description 
(BLOCK MANIP E%YSOB THING)---------- markers 
The first three lines willeventual~y form me bulk of a Micro-Planner 
progr- which, when evaluated will seek an object X that is a block, is 
equidimenoPona1 (EQDIM) and is red (where "red" itself has a definition, 
the system that restricts its application to objects with the feature PHYSOB) 
The last line of the ftgure is a set of 'semantic features" 
read off right to 
left from the following feature tree" 
The semantic structure of "the red kuheJ"ccan be used by C:?e deductive 
"&WING --- 
coapnent of the system, hefore eb*aluatfon resultAng in the actual picking 
up, to see if such an object 1s JE it wers IIL.~, (an '"~y~idinest- 
siannl pyramid1" would not be) the system souLd yo dncl try ta re-pitrse 
Nrn 
the sentcnco. 
The meaning of verbs in SHRDLU is mre mmplex. The seaantic c~wpnent 
has access to n definition fer "pick-up" just as it d~es for "tt5d1' a:~d "klcck" 
and this definition will enable SHRDLU to translate "pick-up tateaents" into 
Micro-planner in a mdnner analogous to that for noun phrases. 
These are two complications here. Firstly "pick-up", unlike "red", is 
PLACE 
PROPERTY -- - 
: 
defined in terms of other concepts in the system: in particular, in terms of 
GR?SP and RAISEHAND, which axe two of the three basic actiQns in the system. 
Secondly, there are two rrpes of verb definition, semantic and inferential 
Winograd does not give the semantic definition for "pick-up", but here is 
the one for "grasp" which is a closelb- related verb. 
(CMEANS (((MANI~TE)) (~#&wIPJ)) 
(#EVAL (WND ( (PRCXXIESSIVE) 
SWE: 
SIZE 
LOCATlcW 
\' corn 
MIbWTB ---------------------- 
Mtw 
(--------- 
C ' 
5m 
RED 
UC)f 
\NITS 
CaEM bTAC # 
PifiSoB-- ( 
'~~~S~~~~------------------------ rrg& 
,- IN 
(--I 
T~U FkW1Z.P 
'bm~p ---------- 
which says e~sentiallp that grasping is scmathinq dorle by an animate entity 
to a oanlpulabla one (flret line). 
More of the real content of such actions 
is found in their inferential definition. Here is the one fox '"pick-up": 
(CONSE TC - PICKUP 
IX) 
(PJCKUP xr 
(rn(WSP ?X) TiiEorn) 
(C.XXAL (RAISEHAND THEOREMS) 
TSlis definition allows the program to actually carry out the "pick-up" 
caamand if it is possible to do so in the simulated world, as it would not 
be, for example, if -re were already a block dn top of the red one.. 
PICKUP is being defiled in edzrms of a number of more primitive s&-actions, 
such as GRASP and RAISEHAND each of which must be carried out in order that 
sameming may indeed be picked up. There sub-actio~ themselves have in- 
fesential definitions: the one given for GRASP, for example, is somewhat 
differant from its "C1(&EANS1' definition given above, although the inferential 
iPefini,tiona are aim, in sane se-e, definitions of meaning as wall as pro- 
gra~as for actually carrying out the associated conmands. 
One reason for the enormous impdct of this work was that, prior to its 
appearance, A1 work was not very linguistically interesting, while the 
eystems of tho linguists had no place far the use of inference and real 
world knowledge. Thus a very limited union between the two techniques 
was able to breed considerable results. Before Winograd &ere were few 
pmgrams in A1 that could take a reasonable complex English sentace and 
ascribe any structure whatever to it. In early classics of 'ngtural 
language understanding' in AX, such as Bobrow's STUDENT (1968) problem 
solver for simple algebra, input sentences had to be short and of stereo- 
typed form, such as "what is the sum of .... ?" 
Conversely, in linguistics, there was, until very recently, little 
speculation on how we understand the reference of. pronouns in such eleqent- 
ary sentences as "The soldiers fired at the woslen.and I saw several fall", 
where it is clear that the answer is both definite, and that fhding it 
requires some inferential manipulation of genaralirrtiens dwut the world. 
3ha reader should ask himself at this jmint how he kwwe the nsrxact 
- 
refemnt of the pmnaun in that sentanca. 
3. $me Discussion of SWLU 
S~J -fax, the reaction ts Winugqad \s work has Lmtk wbSrSrla ~ineri t heal. 
What would crAitics find to attack if tthtzp M~SF 90 a9nde.I: Firstly, that 
~~inegrad's linguistic system is highly wnsr~~?atiw, and that UIQ distinct- 
ion between 'syntax' and 'semantics' my not Lw necessary at all. Sewniily 
#at his semantics is tied tu the shple referential wrld cf the blccks it? 
a way *.at muld make it fnextensihle, to any genexal, real tmrld, situatioh. 
Suppose 'block' were allowed mean 'an obstrxxctidnl and 'a nental ir,k,i*- 
ition', as well as 'a cubic object'. It is dauktful whether Winograd's 
features and rules could express the ambiguity, and, nore im~rtantly, 
whether the simple structues he manipulated could decide correctly between 
the alternative meanings in any given c~ntext of user Again, far more 
sophisticated and systematic case structures than those hg used might be 
needed to resolve the ambiguity of 'in1 in "He ran the mile in five minutes 
and Ire ran the milt. in a pawr kwg , as we11 as 'tllu ccmbination ~,lf case 
with wrd sense amhipity in 'Ho put tho key in the l~rk' (door lock1 and 
'Be threw the key in the luck1 (river leek). 
The blocks mrld is also strongly deduct-ive and lwical1y closed, Sf 
gravity were introduced into it, then anything supkwrted that war pushed in 
a certain way would have, logically have, to fall. But the cazmon sense 
- 
wlorld, of ordinary language, is not like that: in th~ 'waaen and soldiers' 
example given earlier, .the pronoun 'several1 can be said to be resolved 
using same generalisation such as 'things shot at and hurt tend to fall' 
There are no logical 'have to's1 there, even though the meaning of the ~ro- 
noun is perfectly definite. 
Indeed, it might be argued that, in a sense, and as r~afis its seman- 
tics, Winograd's system is not about natural language at all, but abut the 
- - 
technical question of how goals and sub-goals are to be crganised in a 
problem-solving system capable of mani~ulating simple physical ehjects. 
If n reeqber, for example, that tfre key problem that brought bwn the 
emrr#rur work on mchiae translation in the Fiftiea and Sixties, was that 
of the eensa diguity of nattWi.l. language wprds, then we will look in 
vain to SHRDLU Lor any help with that problem. There seem? to be only 
one dear exmaple of aur aLnbiguous mrd in the whole system, namely that of 
'curitairat as it appears in 'The box contains a red block' and rhe stack 
Again, if on@ glahces back at the definition of 'pick-up' quoted &ve, 
ana can see t)cdt it. ie in fact an e%pression rrE a prcrcedure f~r picking up 
an ob5ect in the SHR~LU .yet=. Nothing about it, for ekample, would help 
one, understand thep~rfe~tlv ordinary sant;ence 'I picked up my bags £tom the 
plstforn, and ran for the train', let alone any sentenco not &out a physical 
action performable by the hearer. One could put the point so: what wa are 
gFveR in the PLRNFtE3I code is.not a sense of 'pick up1 but an exardple of.its 
- 
use, just as 'John picked up the volunteer from the aueience by leaning over 
the edpeeog the stage and WWW her up by means of a rope clenched in his 
teeth1 is not so much a sense of ,the verb as a use of it. 
nose who like very general analogies may have.noticgd that Wittgen- 
stain (1953 para. 2ff) devated considerable space to the construction of an 
e1sentaz-y language of blocks, heaxus and slabs; one postulated on the 
as 
tipn that the words of language were basically, as is supposed in 
modal theory, the names of items. But, as he showed of the enterprise, 
.nd to the eatisfaction of aav readers, "That philosaphicat concer~t cf, 
meaning (i.e. af words as the unernbiyuous names uf physical ~bjects---W) 
has its place in a primitive idea of the way language funotions. 
But one 
ca~ aleo say that it is the idea of a lanyuaye more primitive than ougs". 
(my italics). 
To all this, it might be countered that -it has not been shown that 
the language facilities I have descrlb&d cmt be incorporated in the 
structures that SHRDLU manipulates. and-th%tt, even if they cwld not, 
the 
work muld still be significant in virtue of its orisinal control stzuctura 
and its demonstration that rpal world knovledge am bv uerged-with ling- 
uistic knowledge in a working Whole. Indead. a13mug.1 Winograd has apt 
tried, in any straightforward sense, tc extend 
SUEU~LU system one could 
say that an extension' of this -st is kmir~g stbaptd*$y 
(am43 wit5 
his 'Mliever Systwm' which is a hybrid system -t .hit 
beliefs that is, in the aanee nf saction 4 blow ''.+mad pouatlmt,, 
a base analyser Lrolln Bruce ' a ClUWWS amtem (1971) rhlch is e rl+zo r~rw 
---late first genesat~un---systPmp in km soaw wnvr & Wbtq~d*u. Otbch 
in the last catwry that should be- mtentAwm3 Blaavhw bmd fsmdgs'419'?2) 
e~p3sration of kb csnwpts of luustl ahd ,,cmi8dq kn r mt-ldl & 
tic-tac-to!&, and Joshils anfcnsion ob it (1973), kt all tbm ra~tp~lt 
am3 inPluentia2 wxk uf Oh.xx3rn (lQ72). 
This wrk, mot recsz~thy apylYd to a r&cm-world d ltme~ SOCBt mm, 
is not discussed in the detail it deserves in this papex. '%be 
bwd 
on an augwnted state transition nebork gs-, is udmabtmdly of 't;ba 
rxaeast mbust in actual use, in that it is less s,ensiUve to 9.4hRTICmS&t 
input guestions it encounters thdn its rivals. 'Thq reasam fir 
tmdtbg 
it in depth is that bath Was and Wimq~ad 'nave an~u.ed 3n print tht thsLs 
twlo systas are essentially eqiivaLent [Wisrsgrad 1971) 19731, ad so, 
if they are right, there is no need Its dise:ss bth, and Wixmgxwil's is, 
within the WI camiaunity at least, the better known of the two, 
Their ec&ivalenc,e arguments are proLdly mrxect: bth ur gr- 
based deductive systems, operating within a guestim-anmriqq b~~i-f 
in a highly limited daain uf disccurse. Wixqsad'3 syst- QX h$aw aa hou 
to psoceed, within his P-PM gramas, is, as he hhsehf +pints mt, 
fomallj. equivalent t~ an augmented state transition network, M in prtit 
vlar tc~ the ordering of cbictes at ndes in PIJodsl system, 
There is a significant diffexencfe 2n theis mtaphysicaf -, 
presuppositions about meaning which, howevex, has m  inf flu err ace ca the aamL 
operation of their respective systea~. This diffeme is disguised by 
the allegiance both givd ta a 'prolcedwal view of meaaiq' T'k difft!zeace 
is that Molods takes a much more logico-sanantic intqretatiua of that slogan 
than does Winoqrad. In partisular, fbr Ws the meaniq of an Lnp~t utter- 
ance to his system is the procedures within the system that raJ+ipulata tfr 
truth conditions of the utterancfe and estgblish its truth value. 
To put the mttex crudely, for Moods an assertion has xi meanhq if hie. 
system cannot etabligh its tnth or falsity. Wbuqxad has mrtabdy 
camitted himself to my such extreme~positiom. 
It is interesting 'to notice that Woods' is, in virtue of his strong 
position an truth conditions, probably the only piece of work in the ofi~ld 
of A1 and natural language to satiefy Hayes' (1974) recent demand* that to 
be 'Lntellectually respectable' a knowledge syptem must have natural model 
thwretic semantics, in Tarski's senso. Since no-one has over given prec3se 
tzuth conditions for any interesting piece of discourse, such as, say, Woods1 
arm papers, one might claim that his theoretical presupposittons necessarily 
limit his work to the analysis of micro-worlds (as distinct from everyday 
language) . However, if Woods ' ' internal ' interpretation of tho 'meanings 
are procedurest slogah has certain drawbacks, so too does Winograd's, or 
what one might call the 'external' interpretation. By Ghat I mean Winograd'g 
concentration on actions, like picking up, that are in fact real world pro- 
cedures, and ir) acway that tl~e meanings of 'concentrate', 'call', 'have', 
'intwpret1, etc, are - not self-evidently rep1 world procedures that we could 
Set out in PLANNER for a robt. Of course, Ninograd 4s free to concentrate 
on any micro-world he wishes, and all I am drawing attention to here is thd 
danger of assuming that natural language is nomaiky about real world pro- 
cedures and, worse still, the implicit making bf the assumption that we can- 
not understand discourse about a procedure unless we can do it ourselves. I 
aa not saying that Winograd is making this evidently false assumption, only 
that the rhetoric surrounding the application 05 the !meanings are procedures1 
sloglsln tx~ his system my cause the unwary to do so. 
There is quite a different and low-level problem about the equivalence 
of Woods' and Winograd's systems, if we consider what we might call the 
received co-n-sense view of their work, Consider the following three 
assertions: 
(1) s system is an implementation of a transformational grammar 
(2) 
Winograd's work has shown the irrelevance of transformational 
grammar for language analysis - a'view widely held by reviewers 
of his work. 
* a view modified in Hayes (1975) where it now seems that programs/pro- 
cdures would serve as a 'semantics' instead (a quite different, and 
more reasonable, position, of course). 
(3) Woods' and Winograd's systems are formally equivalent - a view 
held by both of them. 
There is clearly swathing of an inconsistent triad anronyst thosr 
three widely held breliaFs. T31a txouble probably centxus Gn the r~xact 
sense which Woods1 nark is formally equivalent to a transf~mational~ 
graaraslar - not a question that ned detain us here, but one worth plntfng 
out in passing 
4. Scwe More General Uckgraund IasurfL 
Winograd's hvrk is a central rrxcmplr? of the 'Artificial fnl~lligr?nc*c 
paradigm of h.ngu&ge', using '~aradicp' in Kuhn's (10701 sense of a 1arqe 
scale revision in systematic thinking, where the,pa.radigru revise is ,the 
'generati- paradigm1 of the Chmskyan linguists fChomsky 1957). Fra 
the A1 pintof view, the generative linguistic tmrk of the last fifteen 
years has three principal defects. Firstly, the generation of sentences, 
with whatever attached structures, is not in anv interesting sense a dem- 
onstration of human understanding, nor is the separation of khe well-formed 
from the ill-fomed, by such methods- for understanding requires, at the 
very least, bth the generation & sentences as parts of coherent discourse 
and some attampt to interpret, rather than qer5ly zeject, what seen to be 
ill-farmed utterances. Neither the transformational grammarians following 
Chomsky, nor their successors the generative semanticists (Lak-off 1971), 
have ever-eSplicitAy rknounced thd generative paradigm. 
Secondly, Chmsky's distinction between pexfomance and competence 
models, and his advocacy of the latter, have isolated modern generative 
linguistics from any effecti- - test of the systems of ruhes it proposes. 
Whether or not me distinction was intended to hdve this effect, it has 
meant that ay test sxtuation necessarily involves performance, which is 
wnaLdered vutsfde the province of serious linguistic stugy. 
And any 
embdiment of a svstein of rules in a computer, and assessment of its out 
put, would be perf~rmance. AI, too, is much concerned with the structure 
of linguistic processes, independent of any particular implementation,** 
** Vide: "Artificial Intellige~ce is the s.tudy of intellectual mechanisms 
apart from applications and apart fra how such mechanisms are realised 
in the human or in animals. '' (McCarthy 1974) 
but implementation is never excluded, as it is from competence models, but 
rather encouraged. 
Thirdly, as f mentioned before, there was 'mtil recently rio place in 
the generative paradigm for inferences from facts and inductive generalis- 
atlona, even though vex;y simple examples demonstrate the need for it. 
This last point, ab~ut the shortcomings of conventional linguistics 
is not at all new, and in A1 is at least as old as Minsky's (1968,p.22) 
obawvation that in 'He put the box on the table. Because it wasn't level, 
it slid off', the last 'itt can only be referred correctly to the box, 
rqther than the t&le, on the basis of some knowledge quite oth#r than 
that in a conventional, and implausible, linguistic solution smh as the 
creation of a class of 'level nouns' sb that a box would not be considered 
as being or not being level. 
These points would be generally conceded by those who believe there 
isam AX paradigm of language understanding, but there wdlrld be Ear less 
agreement over the psfkive content of the paradigm, The txouble begins 
with the definition of 'understanding' as applied to a computer. At one 
extreme are those who say the word can only rqfer to the performance of a 
machine: to its ability to, say, sustaih dome farm of dialogue long enough 
arad sensbly enough for a hwn interrogator to be unsure whether what he 
is conversing with is a machine or not. On the other hand, there are 
=my, ahst certainly a majority, who argue that more is required, in that 
the msthde and representations of knowledge by which the pexformance is 
achieved must be of the right formal sort, and that mere performance based 
- 
on ad hoc methods does not demonstrate understanding. 
This issue is closely related to that of the role of dqduction in 
natural language understanding, simply because deduction is often the 
structure mant when 'right methods' are mentioned. The dispute between 
those who argue for, or, like Winograd, use deductive methods, and those 
who dvocate othex inferential systms closer to cammon sense reasoning, 
is in my ways a pseudo-issue because it is so difficult t~ define cltarly 
what a mn-deductive system is, (if by that is meant a system that cannot 
in principle be lnodellea oy a deductive system) since almost any set of 
forrpal'procedures, including 'invalid inferences1, can be so displayed. 
The heart of the matter concdrns the most appropriate kom on an infsrsnce 
system, rather #an how thss~ infercncas may be &xim~tisFd, and it may 
well turn out that the most appmpriatc fom for plausLbla rrao~ning in 
order to understand is indocd non-deductive. 
Tl~is sum insight has 
largely defused anot2at.r tlu&med issue: wha ther tl~n app~v~rlate re&xressnt- 
stions sl~ould be proer;.dwes or d@claxntions. Winoymdts w~rk was wE the 
former type, as was shown by his definitions of *urJs like 'pickup' as 
procedures fur actually pickirry thinys up in U\F Blecks ~~sld. HQWQV~?~, 
simple pr~xcddral rcprcmntati~nu usually hnvo the disadvantage that, if 
YOU are QO~IKJ to indicate, Ess every ' it=' of knswldge, how it is tc k5;?.c 
- 
used, then, if you may use it on a number of kinds uE ocsssi&n, 'y~u will 
have to store it that numb.es of times. So, if y~u want ta change it 
later, you will also have to remeinher to ohange it in all the different 
places you have put it. There is the additional disadvantage of lack of 
perspicuity: anyone reading the pr~cedural version of (he Winograd grammar 
rule I gave earlier, will almost certainly find the c.onventilc?nal9, declar- 
ative, version easier to understand, 
So then, the fa&hion far all things procedural has to some extent 
abated (see Winograd 1974). There is general agreement that any system 
should show, as it were how it is actually to be applied to langua~e, but 
that is not the s-e as demanding that it should be written in a ~r~c~dura3 
language,line PLANNER. I shall return to this last pifit later. 
5. Second Generation Svstems 
To und'ewstand what was meant when Winograd contrasted his own with 
what he called second generation systems, we have to remember, as always 
in this suject, that the generations are of fashion, not chronology or 
inheritance uf i3eas. He dedcribed the work of Simmons, Schank and myself 
among others in his s-ey of new approaches, even though the foundations 
and terminology of those approaches were set out in print in 1966, 1968 and 
1967 respectiyely, What those approaches, and others have in mmon is 
the belie. thak understanding systems must be able to manipulate very 
complex linguistic ohjects, or semantic structures, and that no simplistic 
approaches to understanding language with computers will wrk. 
In a very influential recent paper, Minsky (1974) has drawn together 
strands in the work of Charniak (1972) and the authors above using a 
teminolagy of 'frames': 
tvA frame is a data-structure for representing a stereotype situation, 
like a certain kind of living room, or going to a children's birthday 
party, 
Attached tea each frasne are several kinds of information. Sbme 
of thia is information about how to use the frame, Somc is about what 
cne can expct to happen next, Some is about what to do if those ax- 
pectatione are not confimed. 
We can think of a frame as a network of nodes and relations. The 
top levels of a frame are fixed and represent things that are always true 
about the supposed situation. The lower levels have many terminals --- 
'slots1 that must be filled by specific instarices or data. Each terminal 
can specify conditions its assignments must meet .... Simple conditions 
are specifia by markers that might require a terminal assignment to be a 
person, an object of sufficient value, etc..,, II 
The key point about, such stxuotures is that they attempt to specify 
in advance what is going to be said, and how the world encountered is 
goihg to be structured. The structures, and the inference rules that 
apply to them, ate also expressions of 'partial information' (in MKarthyts 
phrase) that are not present in first generation systems. As I showed 
aarliar, with the 'women and soldiers' example, such loose inductive inform- 
ation, seeking confirmation Erom the surrounding context, is required for 
very shple sentences. In psychological and visual terms, frame approaches 
~nvisage cnn undezstander as at ieast as much a looker a? a seer. 
Thus, we might, very tentatively, begin by identifyiq what Winograd 
called 'second generation' approaches with 
those making use 05 very 
general notions akin to what Minsky called 'frames'. But this is no more 
than a temporary device, for convenient initial classification of the field, 
because later we shall have reason to question the first-second generation 
distinction, and, as noted earlier, Minsky's notion of 'frame' is itself a 
highly fhid one in the process of definition and refinemgnt. 
Let us now turn briefly to five approaches that might be called 
sewnd generation. 
Charniak 
The new work which owes most to Mirrsky Is advocac,y is Ckarnink s . 
Hea studied what: sorts uf inforezitiizl infomation Charnlak 7 '73, ''741 
would be needed to rrasulm pronoun Wiyui ties in ciai3dren l a s torjCr::, 
and AJ% that sehso tu understirrail t.htxu. Orla of his ex,mgic, ' otouicls ' is: 
'Jane was invited tu Jack's birtl~day party. She wnderd if he wuld 
like a kite. A friend tcld June that Jack already had a kite, an3 that 
ha would mku her take it back 
it refers to the first kits uasrti~ned c?r tha se~wnd. Charniakts analysis 
begins by pirating out that a great deal cf what is required to understand 
that story is implicit: Iun~ilrledge aLwut the giving of p~esents, knoililedge 
that if one possesses one of a certain sort of thing then one may well not 
want another, and *so on, 
Charniak's system does not actually run as a preyram, but is a theoset- 
ical structure of rules called 'demcnsl khat correspond roughly to what 
Minsky later called frames. A demon for this exanple would be, If we sop 
that a person might not like a present S, then lock Pclr S being returned to 
the store where it was bought. Zf we st?e that hngfening, or even being 
suggested, zssert that thp rcasor why is tht P docs not like S1. 
The imprtant wards these are 'lt-k fey', which suggest that t31r>r~ may 
well bo confirming hints to be found in the :=tory and, if t4lerc are, than 
this tentative, partial, inference is cursect, and we have a definite and 
correct answer. "I'his approach, of using partial {not necessarily true) 
inferences, in order to assext a definite answer, is highly characteristic 
of 'second generation' systems. 
The demons are, as with Winoyraa's work, expressed in a procedural 
language which, on running, will seek for a succession of inter-related 
'goals'. 
Here, for example, is a demon concerned with another story, about a 
child's piggy bank (PB) and a child shaking it, looking fcr money but hear- 
ing no sound. The demon, PB-OUT-OF, is fomalised as: 
[DEMM PB-CUT-QF 
(Horn PB PERsW M N) 
{?N Ollfi-OUM 7PB) 
EWAL (7 IS ?PB PIGGY-BANK)) 
(GOAL (3 IS 324 KNEY) qDEDWE) 
(GOIIL (?NOID SW ?PERSON 3PB) $TRUE) 
(ASSERT (? HAVE: ?PERSON ?M) 
(ASSERT ('3 RESULT ?N WOLD) ) ) 
Again, it is not necessary to explain the notation in detail. to see 
that conditions are being stated for the contents of a piggy bank having 
ken emptied. 
The pattern being sought by the demon in operation is tire 
third line. TE a chin of demons can 'reacht one of the passiblo xafer- 
ente in a story then there is a suct+ass registered and the ambiguity of 
the corresponding pronoun is resolved. 
It can be seen that the information encoded in the system is of a 
highly specific sort - in the present case it is not about containers as 
such, and how to get their contents out, but about Piggy Banks in particular, 
and everything relies on that partfcular knowledge having been put in. Not 
all the knowledge is of this general sort: in a recent paper (Charniak '74) 
whws tha 'kite' stary is reconsidered there are rules ~f considerable gan- 
rrrsuty snd interest. One such is that Charniak calis a R+SSA rule: 
'XE the .tory give8 information which would make it plausible to infer 
mt PERSON is favourably inclined towards action A, and PERSON does SI a 
signif icmt subaction (SSA) of A, then f nfer that PERSON is doing A 
An important azsumption of Charniakls is what I shall call his 
'decoupling assunaption', namely that this work on the knowledge-based 
detemahation of reference can be effectively decoupled from any partichlar 
syntactic or semantic representation, or of its apgdication, arid can be 
explored Fn isolation. Thus, the apparently English words in the PB-OUT-OF 
d-n above do not have any particular status ower than that of English 
words that happen ta occur in the stories being examined. I shall return 
to this assumption later. 
Corny has (Colby et a1 '71), (Enea and Colby '73), (Colby and Parkison, 
'74) developed over a pezfod of several years an on-line dialogue system 
thatsimilatss a paranoid patient called PARRY. A masuxa of its syrucea~s 
is that f* is perhapa the arost used A.I. praqsam in cr~istencsr 
usbit, mat 
La, by those. outside ths rle~earch psojact that developed it, Herd is n 
discontlnuouar sati~pla of its output, wain with ma. rryskeia2a mspnoao in 
the upper case: 
Ban you been hospitalised before3 
SWIS IS W FIRST TXblS. 
How long ham you bssn there? 
ABanlWQpltE;~. 
&my headachara? 
NEI llEALT"H IS FINE* 
Are you having; any difficulty with your ~tressllosy? 
m. 
Then perhaps you can tell me who is the President of the United States? 
NIXON IS PRESIDENT. 
What day is it today? 
mMY IS THURSDAY. 
What season is it? 
LE;TS GET ON WITH THE ZNTSEIVZGW. 
Colby's stm was to produce a systtm that was not fragile' in the way 
that most A.I. systems are: one that did not break dawn, at give up, if 
We input was not exactly what it expected; but me that carried en scam- 
haw in a11 circumstances, in the way that conversing humans do. 
Fragility is avoided by having m conventional syntax analyser, and 
by xiot even attempting to take account of all tihe mrds in the input. This 
is a considerable aid, since any parsex that begins to parse a more #an 
usually polite request such as 'Would you be so kind as to ...*' is going 
to be in trouble. British English speakers arriving in the UiS. quickly 
learn to delete such phrases, since they cause great confusion to human 
listeners in stores. 
The input text is segmented by a heuristic that breaks it at any 
occurrence of a range of key words. Patterns are then matched with each 
segment. There are at present about 1700 pattesns on a list (Colby and. 
Parkison, in pxess) that is stored and matched, not against any syntactic 
or semantic repfesentations of words but against the 'input ~mrd *string 
directr and by a process of sequential deletion. 
So, for example, "What 
is your main problemr' has a root verb "BE' substituted to became 
WHAT BE YOU WIN PTtOBLBH, 
ft is then matched awcessively in the following farms after successive 
deletion6 : 
BE YOU MAIN PROBW 
WHAT YOU WIN PROl3LW 
WHhT BE MAIN PROBLEM 
WHAT EIE: YOU PROBLEM 
WHAT BE XKl WIN 
ond only We ppulthate line exists as one of the stored patterns, and so 
i8 wrtchd, Stored in the same famat as the patterns are rules expressing 
the conrepuenc3a for the 'patient1 of detecting aggression and over-friend- 
Liness in the intanrlewer's questions and remarks. 
The matched patterns 
Pound be then tied directly, or via these inference rules, 
to response 
patterns which are generated. 
Enormous inyenyity has gone into the heuristics of this system, as its 
popularity testifies. The system has also changed considerably: it is now 
calltad PARRY2 and contains the above pattern-aratchinq, rather uan earlier 
key Wrkt heuriatica. It has the partialt or what scme would call 'prag- 
mtf~~, rule& about wpctation and intention, 9ndvthese alone might qualify 
it as 'swmn8 genarqtion' on some interpretations of the phrase. A genexa- 
tor i+ alro being instaXLd to avoid the production of only *lcannedl re- 
mponsas . 
Colby and his associates have put considerable energy into actually 
wing to find out whether or not psychiatrists can distinguish PARRY'S 
re8ponaes fran those of a patient (Colby and Hilf '73). This is probably 
the first attempt actually to apply Turing's test og machine-person disting- 
ulshbility. There are statistical difficulties about interpreting the 
results but, by and laxye, the result is that the sample questioned cannot 
distinguish the two, Whether or not this will influence those who still, 
on principle, bel~eve that PARRY is not a simulation because it 'does not 
understand', rains to be seen. It might be argued that they are in 
danger of falling into a form of Fapext's 'human-superhuman fallacy1 of 
attacking machine shulations Mause *Aoy d 
not perfom s~pmk-n talkse 
like trcnslate mtxy, taakr that arcma p~pla c@rbhniy can - d.cr but #1i7 
anajority cannot. Whdn such aceptlcr say Ult PARRY dws mt und~tstad 
they hava in mind e lave1 of uderstsndLng that is mrtalnky high - cna 
could extd their case iyonLcaJCly by pointing out that my EQN px?pl 
Warstad the content af oantences in the daptn am detafl that an and,~cic 
philosophar does, and a vszy gd thing toe. But tPI~ce can be +&t 
#at Paany p~gla on many omasian% !XI oaem to Wrrxstand in ti:@ way that 
PMY does. 
S mns 
The remaining three systms differ fs\# the t:w in Uaa&r attempt 
to provide soma repressntationrtl structure quite different frc~a L!it of the 
English input, This mans the use of cases, and of cxazpl~x structures 
that allow inferences to be &am from the attsibution of case in ways Z 
shall axplain, There as also, in the remaining syst=sr same attwzpt ta 
construct a primitive, or reduced, .-c&ulaxy irito which the lampage rep- 
resented is squeezed. 
Simmons1 wxk is often thought of as a 'r~eaory Wed', though he dees 
in fact wy tsbore attention to wrd sense &iguitla, and ts actual recog- 
nition in text than do many other authors. For !:in the Eunhcntal ncscian 
is that of a 'soarantic networkq, defined aussntialfy bp the sratxmnt of 
relational triples qf f~mr aRb, where R is the name ut a relatlou and s and 
b are the names of nodes in the network. Shmorts' wrk with this general 
formalism goes back to at least (Shams et al, '66) but, in its never fern 
with case foxmalisn, it has been reported since 1973 (Shamans '?Obi, (Shaons 
and Bruce 1 , (Simmns and S&ocum '72) , (Sicmons '73) , ar,d (Hexdxix et a1 
'73) may reasonably be considered a further implementation of Simmns' 
methods. 
Simmons considexs the example sentence 'John broke +the window with a 
hamer'. This is analysed into a network of nodes C1, C2, C3, Cd corres- 
ponding to the appropriate senses of 'John1, 'Bread', 'Windcv' and 'Hammer' 
respectively. The linkages between the nodes are labelled by one of the 
following 'deep case relations ' : CAUSAL-ACWUtT (a. , CA2) , 'EENS, =US, 
S03JRC6 and GOAL. Case relations-are specifications oT thd way dependent 
parts of a sentencer or concepts corrtesponding to parts of a sentence, 
depend on the main action. SO, ih this example, John is the first causal 
actant (CAI) of the breaking, the hammer is consideted the second causal 
actant (mi?) of that breaking, and the window is the theme of the breaking. 
Thuss the heaxt of the analysis could ba repzesented by a diagram as followd: 
' John C2 
OF by a set of relational triples: 
(Cl CAS C2) (Cl CAZ C4I CC~ l?HE&E. C3) 
Huwwer, thisis not the full representation, and my addition of the word 
1-1s to the diagram is misleading, since the nodes me intended to be 
nar~ea of senses of wozds, related ta the actual occurrence of the corxes- 
porufing wad in a text by tho relation TOK (for token), In an inrplemnt- 
atfon, a node would have an arbitrary name, such as L97, which would then 
rumit a stared sense definition. %, for a sense of 'apple Shmanrr suggests 
an ao~otiated set of featwes: NBR-singular (S), SHAPE-spherical, COLOR-red, 
PRINTTHAGS-apple, THEME-eat, etc. If the name of the node tied to this s~t 
of features was iweed L97, then that We might becane, say, 65 on being 
brought into saa sentence representation during parsing. Thus the diagram 
1 gave must be thought of supplemented by othez relational ties fram the 
nodes; so that the.ful1 sentence about John would be represented by the 
larger set of triples: 
(Cl TOK break1 (C1 CAl C2) (Cl TEIEf3E C3) (Cl -2 C4) 
(C2 TOK Joh) (C2 DET Pef) (C2 NBR S) 
(C3 'ToK Window) (C3 DET Def) (C3 NBR S; 
(C4 TOK Bamer) (CC DET Indef) (C4. NBR S) (C4 PREP With) 
Wxd eense ambiguity i~i taken account of in that the node for one sense 
of 'hamaex' would be different fram that corresponding to some other sense of 
the same wzd, such as that meqaing Mwam3, 
slightly strained alternatiw for this ssntenca, 
The network above is slro o represantrrtion aC t)U Collouing rsnt,nger 
which can bb .Ihouoht of as surface vaqlmta of p shqle 'uI*ll~tlyLq~~ S~NG 
twe: 
John broke the wind~w with a hakmmr 
John broke the whnaow 
The hammer br~ke the widow 
Thw window broke, 
kt all parts of t;harknetwrk will be sat up 
each QP these sentences, ~i 
caurse, but tha need fex same item tO fill an appmpriate s! t can 3Ye infer- 
~'dj i,e. of the first c~us~~cW~ [John) in the last tw sentences, The 
sentences ah~ve are recognised by mans of the 'ergative paradigm2 of orderec 
matching patterns, of which the Eollowing list is a part: 
(CAI. 'lxaxls CA21 
(CAl "rHEME) 
(cA2 -1 
m.'=w 
These sequences will each match, as left-rigw ordered itarns, one sf the 
dwve sentenceq. It will b2.s clear that Simmons' method of ascribing a node 
to each word-sense is mt in any way n prhltive sy~t~~ by which tmean a 
system of classifiess into which all word sanses,are mapped. 
Shmns is, however, cansidexing a system of paraphrase rules that 
wlould map from one network to another j31 a way that he claims is equiwlent 
to a system of primitives. Thus in (Simmons '733 he considers the sentence: 
John bought the boat from Mary 
Mazy sold the boat to. Job 
which would noracally be considered approximate paraphrases of each other. 
He then gives 'natural' representations, in his system, as fallews in the 
same order as the sentences: 
* Shons' normal example of word sense ambiguity does not apply to the 
sentence above: he distinguishes 'pitcherl', a pouring containerr froea 
'pltcher2 ' , in the U .S . sense of 'one who howls a! ball ' . 
Ci TOK buy, SOURCE (Wsq), GQRt \John), (ha$], 
cl TOK e;okl, ScTmCe tllary) ? COAL (John), TM (hat) , 
and also the bLngla ,gapreselltation for both sentences, as below, using a 
prlnitfve action ' tranatsr' 9sae description of Schank's work in next sec- 
tion) p5 Eollow8: 
a 
ToK ~d, Ugs C2# CJ 
ca Toft txmsfor, SOURCE [John) ; GOCUl (1 (money) 
C3 1DK wansfcr, SWRCX (Nary) , GOAL (John) , THE B (boat) 
SL~wna opts for the first .€om of representation, given Ule poalib- 
ility of a transfer rule gohg Ptopl either clT the shalkower representations 
tb Ihc other, while in (Hendrix et a1 l73), the ather apprdach is adopted, 
wing a primitive action B&CI.fANGG inetead of 'transfer'. 
ThIe implementation under c~nstruction is a front-end ,oarsex of the 
Woodat augmented transition network type (see Woods '701, and a ganefation 
system going gram the sea~tic networks to surface strings described8in 
detail in (SWns and S1ocu.m '72). SimPons has also given considerable 
tb (SFrPPJons and Bruce '7 1) to the auloPPatic ttanslation of the networks 
into a cmxrespontling Efrst-order predicate calnilus format of the sort 
developed by Sandenall. (1971). This last is particularLy valuable because, 
LZ penatalirablr, lt rhwr that any linguistic di,ng in network Ecm -- can 
b translated in- some form of the predicate calcults, if that Formalism 
and it# crssvclated proof kachnigurs oan be shorn to be app?!!priate for car- 
bin p#~~blaa$ La the area of natural language analysis. 
Sehank 
SchanScqa is a rich system of semantic representation, developed aver 
a psiad of six yeaxsf with the collaboration af a number of talented stu- 
dents. Its graph system of notation has influenced psychologists like 
&belson (1973) , amony others. Schankls contribution has been the notational 
syste'~ representing the structure of natural lancruage sentences, and this 
has &ern progr-ed by various collaborators over #e years. In its present 
version, caJled WGfE (schank et a1 '73) it has an ana'lyser of I";nal&h t%~- 
to Zdesbeck (19741 s seiixmtic memory Ewpnent due to RiegW (1974) , and 
t genetatox of English due t;o GoLban (1974). MaRGIE produces cxutput in 
two modes, demonstrating the sort of wnceptual FnShrencfng that goes on at 
-the Bevel s'f the stmmUc repkesenbUwB: Tb Pm md th 
I- amtifa. Samples of 'input wd outwt tm rad ho t& ba rPdw 
em h shm thus: 
(- -) 
EWW: ;Balm told that 'Bsiik 4L, 
mw, W Wk but uwt, 
N4lq bw rtirisc sku wmts a kiodt. 
8511 wmts to OWM CQ t~w a m. 
BAAL Moats saawsle to ~~~Q W haw 198, book, 
B'ihl wmts %aEZ ram3 a book, 
OUWIPP: JQhn s~a.nqled,~ary. 
Joksn choW Wxy and she died because &e c=add mt kmae%aaa, 
hsy did because she was unable t~ i-le air azla she 
was u&Ls to inhale sme air because John grahkd her DIF& 
The ah of Schadc's aystem has ahways hen txa pmvida a --Urn 
of meaning in terns of which these aLsdl ether tasks, such sa &i,m 
indeprsdent of any pasticullax language, and of syntax, /ityq fS'sbrca, Oe all 
surface structure whatever. 
The fcml structure of Schank's grans is that of 
(Bays '64), ad the items in gsaw axg pf f~ur typesq ar cmt- 
egories. 
They are symblisd as PP, Am, PA asld M, vhfdr am mzzuqms, ht 
which correspond closely (for the purpose of um3e.r~- th.ix feam=tkd tb 
those of a noun, verb, adjective and adverb, respctidy.e+ T'Ik basic 
- 
- 
* Schank distinguishes 'ccnceptuall and 'searnantic' zepesematia&~ im rw 
that is important fox hh within his own syttep. Bowever, Z obrll tmm 
the terms indiffexently since, in this brief ad stprfichl W-, 
nothing hangs upon the distinction. 
**This is a considerable overs~plifica~~n~ in cx&w to gim r 
4 self com.taine3 ,descrSigrion. ;Butl in fact, aany Ex@ km - 
represented as Am's: chair, pen+ honesty, am3 'trwItfcm, 
structtare is called a conceptualiaation, and is normally intrbduced with 
a etraightfomard dependency structure such as, for the sentence 'The man 
teok a book': 
 an & take + book 
Here 'pf 
itldicatea past, and is the aepndendy symbol liking a PP to We 
ACT ('take') which is the hub of the conceptualization, as with Simon& 
?'he '0' indicates the objective case, marking the dependence of the object 
PP on the central ACT. There is a carefully constructed syntax of linkages 
between the conceptual categories* that will be describpd only in part in 
what follows. 
The next stage of the notation involves an extended case notation and 
a set of primitive ACTS, as well as a nqer of it:ems suoh as PHYSWNT 
which indicate ather stqtes, and items of a fairly simplified psychological 
theory (the dictionary entry for 'advise', for example, contains a subgraph 
telling us that Y 'will benefit' as part of the meaning of 'X advises Y' 
[Schank '73). There Axe four cases in the system, and their subgraphs are 
as follows: 
Objective case: ACT '0 PP 
Recipient case: Am' 
Instrumental case: Am 
4 
Directive case: 
PP 
'Phere are at present fourteen* basic actions forming the nubs of the graphs, 
as well as a default action DO. They are: PROPEL, .MOVE, INGEST, EXPEL, 
GRMP, PTRANS, MTRANS. ATRANS, SMELL, SPEAK, LOOK-AT, LISTEN-TOI COW and 
MBUZLD. The notions of case and primitive act are related by rules in the 
develOpment of conceptualizations. So, for example, the primitive act 
INGEST has as its instrument the act PTRANS. 
mere are also other infer- 
--- -- 
* Since the publicabion of (Schank 73a) their number has been reduced to 
ezeven (plus DO) by the elimination of SHELL, LISTENID, IXK)KAT and COQC, 
and the adation of ATTEND, 
ances fram any ACT classified as an INGEST action, such as that the thing 
ingested changes its fomt that M tAe UA~G Awp&ac3 is&LUe kb In 
gestet becomes lmrs nourishodl stem (oao Scbnk '73, pp. 38tf .I. 
This 
will all kcam clsaxar if we consider tho trmsitl~n Zrcm a dietiwary 
entry Pox asr action to a filled-in mnceptuahirati~n. Hem Is tthe d~cc- 
ionary entry for the action 'shwt' : 
can consider this entzy als an active 'frAxte-like~ object seeking filler 
itms in any context In which it is activated. Thus, in the sentence 'John 
sho the girl with h riflet, the variables will be filled in frcm context and 
the case inference will be made fm the main act PROPEL, which is that its 
hstruuent is lkSOVEI GRASP or PFtOPRL, and so we will arrive at the whole con- 
ceatualieation: 
John PROPEL 4- bullet <- 
bullet 
===PKYSccxrr 
PROPEL 
girl 
rifLe girl 
This case inference muSF b~ made, according to Schank, in order to achieve 
an admate zepresentation. There is, in the last diag~am, a cextain re- 
dundancy of expression, but as we shall see tn the next section this often 
happens with deeper semantic notations. 
More recently, Schank, together with Rieger, has developed a new class 
of causal inferences which deepen the diagrams still further. So, in the 
analysis of 'John's cold improvPQ1 because I gave him an vplel (Lrt Scfrank 
'74a) the extended diagram contains at Ih~t four yet lower levels of 
causal =rowing, including one corresponding L.ht the notion of Juh can- 
s+Ncting the idea (WBUTLD) that he wants to ea% an apple. 
So we can see 
that the undexlying explication of mean* here is not only in the serlso of 
Iinpulistlc prLmltLws, but in tern of a theory of mental acts as well. 
Now Ulsra ate a number of genuine ~positi6na]. difficulties here for 
the euml&tator faced with a epstm of this complexity, 
One aspect of 
thi~ is the atages of developnt pf the ~ystam itself, which can bc seen 
ae a consimtcntpmcesa of produrlng what was argued for in advance. 
For 
ekampla, Schank claimed early on to be a constructing system of semantic 
mtructures undatlyirrp the 'surface of natural language', alehaugh initially 
them were no primitives at all, and qa late as (Schank et a1 '70) there 
was only a single primitive TRANS, and most of the entries in the dictionary 
conmisted of the Bnylish wards coded, together with subscripts. Since than 
the primitive system has b&ossomed and &ere are now twelve primitives tor 
hCTS including three Ebr the original TRANS itself. Each axposition of the 
system recounts its preceding phrases, from the original primitive-free one, 
throuqh to the present causal inference form; rather as each human foetus 
is said to relive in the womb all the evolutionqy stages of the human race. 
The only trouble with this, fxm an outsider's point of view, is khat at 
each stage the representation has been claimed, to be the correct one, while 
at the same ti- Schd admits, in moments of candor (Schank '731, that 
there is no ad to the conceptual diagrrVbraing oE a sentence. This diffi- 
culty my well reflect genuine problems in language itself, and, in its 
acuteat form concerns a three-way confusion between an attractive notation 
for displaying the 'meanings of wordsv, the course of events in the real 
world, ad, finally, iibtual procedures for analysis to be based on the 
diagrams, 
This raises the, to me, inrportant question of the application of a 
semantkc system, that I shall touch on again later. Schank, for example, 
dues mention in passing the questions of wd-sense ambiguity, 
and the awful 
ambiguity of English prepositions, but there are in no way central for him, 
and he assumes that with the availability of 'the correct repxesentationWt 
his sysh when UnpleIm?nted must inevitably soive th- traditional and vex- 
ing questions. M procedures are hinted at along with the graphs as to 
how tnrs is to be done. A distinction cof importance may be becoming ap- 
parent here batween Schank s work and Riegerls: in Riagar's thesis (RLqer 
'74) the rules of inference appear to craatg clclparata and new rubprrphr 
wnicn may swd in an lnfersntial celatlon to each other so as tsl produce 
cloncluaiona &but: ~~~~~a of, gayt pronoun rabr~ence, etc. But in 
Schmk's cormsponUng papers the s- ihfctrsncss urn not applid ke 
actual problems (Schank '74a) but only be- to amplaxity th. conceptual 
graphs yet further. 
Closely connected witla this raattex is the quaation af the survival of 
the mlvface sr'tructure in tho diagrams. Until very recently p~~h,itiuis- 
ation applied only to verbs, tht of nouns being Left to Mehr [Wekwr 272) 
Most recently, though, noun wds have been disappearf ng from dfagraps and 
been replaced by.categorfes such as +PZIYS0=* But At is cleax that the 
swface is only slowly disappearing, rathex than having been abhorred all 
along. 
In a mra recent publication CSchank '74b) there are signs that this. 
trend of infinitely proliferating diagrams (for indivihal sentences) is 
feversing. In it Schank considsrs the application of his approach to the 
repraqentation of text, and concl :des, correctly in my tP4etq, that the rep- 
resentations of parts of the text must be interconnected. by causal arrows, 
and that, inlordm to present@ 1rv.cidity, the conceptual diagrams for indi- 
vidoal sentences and their partvi must be abbreviatedr as by triples such as 
POEPLE PplWS PEOPLE.  her^ indeed, the surface simply has to surviw in 
- 
the representation un1esF one is prepared to camit oneself to the axeme 
view that the ordering OF sentences in a text is a purely superficial and 
arbitrary matter. The Fensein wnich this is a welcome reversal of a trend 
should be clear, because in the 'causation inference' development, mentioned 
earlier, all the consequences and effects oE a conceptualization had to be 
- 
drawn within itself. Thus, in the extreme case, each sentence of a text 
7 
should have been represented by a diagram containing most or all of We 
text of which it was a part. Thus- the representation of a text would haye 
been impossible on such prihciples. 
Pay own system constructs a semantic representation for small natural 
language texts: the basic representation is applied directly to the text 
and can then be 'massaged' by various forms of inference to became as deep 
as is necessary for well defined tasks demonstrating understanding. 
It 
is a uniform representation, in that information that might convenionall~ 
be considerea as syntactic, s-ntic, factual ox rnrerencial LS weu ax- 
pressed within a single type of struwra. The fundamental unit in the 
mnatructioe of th2s beaning representation is the template, which is 
intmded to correspond to an intuitive notion of a basic message of 
agent-action-object fom. 
Templates are rigid format networks of more 
basic butldlnp blocks called fomulas, which correspond to senscln of 
individual worde. In order to cohskruet a cctnplete text representation 
templates ate bound byethat by two kinds of higher level structures 
called paplates and inference rules. The templates themselves are 
built up as the construction of the representation proceeds, but the. 
formulas, paraplates and jlnference rules are all present in the system,at 
the outset and each of these three types of pre-stored structure is ult- 
irpately constructed frm an inventory of eighty semantic primitive elements, 
and from functions and predicates ranging over those elements. 
The system runs on-line as a package of LXSP, k&ISP and MLISP2 pro- 
gram, Wing as input small paragraphs of English, that can -be made up by 
the uber from a vocabulary of about 6QO word senses, and prduzfng a good 
French t:ransL&tion as output. This environment provides a pretty clear 
teat of lmguage undarstding, bcauaa E'rench translations for everyday. 
pmse are either right or wmng, and can be seen' to be 910, while at the same 
titPe, the mfot difficulttee of understanding ptogtams - word sense ambig- 
ratty, case anbigufty, difficult pronoun reference, etc. - can all be rep- 
resented within a machine translation environment by, for example, choosing 
the words of Lhe input sentence containing a pronoun reference difficulty 
so th&E the potsible alternative references have different genders in French. 
In that way the French output mdkes quite clear whether or not the program 
has made the correct inferences in order to understand what it is trans- 
la_ting. 
The program is reasonably robust in agtual prformance, and will 
even tolerate a certain amount ob bad grammar in the input, since it does 
not pzfbm a syrkax a~LysI;s &=%he sense, hut snnkn message 
forms representable &XI the semantic smctures employed. 
vpical input would ble a sentence such as 'John lives out: QE tQtm hi 
&inks his wine out of a bottle, Mo than throws the httlas out uf Uae 
for each of tke thraa occurrences of 'out oft, since it raslisarrs that they 
diffexenco must be reflected in the Fwonch, A sentonce such as, *Give Use 
monkeys b;mands although they are not ripe because they ay~ very I~wQry' 
produces a translation with different equivalontd fur t)ra tm eccurrmwr 
of lUaey1, bocause the syslm oorr@ctlp realiasst iraQlSI wlrat 4 shall describe 
below at preference considerations, that tlae most sensible intct~retaticn 
is one in which the first they' refers to the bananas and the second tc 
the monkeys, +and bananas and monkeys~have different genders in French. 
These two exmph are dealt with in: the 'basic de' of the system. 
(Wilks 73a) Inmany cases itcmotxesolve pronoun ambiguities by the 
sort of straightforward 'preference considerations1 used in the last exaaple, 
where, roughly speaking, 'ripeness' prefers to &-predicated of plant-like 
things, and hunger of animate things, Even in a sentence as sbple as 
'John drank the wine on the table and it was gdtt such considerations 
aye inadequate to resolve the anbigtlity of 'it' between wine and table, 
since both my be good things. In such cases, 02 inability to ras~lve 
within its basic moder the program deepens the xepresentatio~ of the text 
so as to tq and set up chains of inference that will reach, and su prefer, 
only one of the possible referents. I will return to these pzocesses in 
a nment, but first I shall give sane brief description of the basic repre- 
sentation set up for English. 
For each sense of a word in its dictionqxy the program sees a fohula. 
This is a tree structure of semantic primitives, and is to be interpreted 
formally using dependency relations. The main element in any fonnula is 
the rightmost, called its head, and that is the fundamental category to 
which the fonnula belongs, In the formulas for actions, for example, 
the head will always be one of the primitives PICK, CAUSE, CHANGE, FEEL, 
HAVE, PIXME, PAIRl SENSE, USE, ,WANT, TELL, BE, 5X), FQRCE, W, 
- 
THINk, FLOW, W, DROP, STRZK, FUNC or HAPN. 
Here 18 tnts eLee stxuctufe for the. action of drinking: 
(mu PART) 
Qace again, it is n~t necessary to explain the formalism in any detail, 
to see that this sense of Idrink* is being expressed as a causing to mve 
a liqyid object (F'WH m) by an animate agent, into that saine agent (con- 
tainment case indicated by IN, and formula syntax identifies SELF with thB 
+gent) and via (direction case) an aperture (TLIRU PART) of the agent. 
Template structures, which actually represent sentences and their 
parts are built up as netwcrks of formulas like the one above. Templates 
always consiat of an agent nude, and action node and an object node, and 
other: nodes ttat laay depend on these. Sot in building a template for 
'John drinks,wine', the whole of the above tree-formula for 'drinks' would 
be piaced at the central action node, another tree structure for 'John' at 
the agent node and so on. The complexity of the system comes from the way 
in which the formulas, considered as active entities, dictate how other 
places hn the same template should be filled. 
Thus, the 'drink1 formula above can be thought of as an entity that 
fits at a template action node, and seeks a liquid object, that is ~ say 
a f~rmula with (FLOW STUFF) as its right-most bzanch, to put at the object 
noda of the same template. This seeking is preferential, in that formulas 
not satisfying that requirement will be accepted. but only if nothing 
misf actan ca lXZ'-fotUEa. TIie -€Elliplate Uif ly esWIisned Tm 3 Trag- 
ment of text is the one in which the most formulas hive their preferences 
satisfied. There is a general principle at work here, that the right 
interpretation 'says the least1 in inforreation-carrying terns, T)rh 
wry simple device is able to do much of the work of a syntax and wxd- 
ysnse wzibigukty resa1vi;tap pxagraa Pnar cusq~e, LZ the a,mteme kd 
been 'John drank s whole pitcher1, the fomulr tor th. 'pitcher of klquidb 
wuld hawe hen pr.rsEerreCI to that for thar human, sfm the subf~mS;a 
(FLOW STUFF) could be apprtopriateAy located uithirr it. 
A tonsidarable tamwnt af squeezing af this sbapl~ eansnkcal Lorn of 
template is necessary to We it fit tha mmplexfty of language: 
texts 
have to bt Eraymented initfalLy? then. in fragments which am. say, gra- 
positional phrases there is a daaay agent Lapasad, and the prepsitions1 
phrases thexe is a dummy agent imposed, and the gremsiticmai LomuLa 
functions as a pseuda-action. There are special 'less preferred1 oaliers 
to deal with fragments not in agent-acti~n-object order, and so on. 
men the local inferences have been done that set up the agest-action 
object templates for fragments of input text, Shd system attempts tm tie 
these templates together so as to provide an overall initial structure fox 
the input. One form of this is the anaph,oxa tie, o-f the sort discussed fog 
the monkeys and bananas example above, but the =re general £om is the case 
tie. Assignment of these would result in the template far the last clause 
of 'He ran the mile in a paper bag' being tid to the action &e of the 
template for the first clause ('He ran the mile'), and the tie king l~~~ed 
CONTaiment. These case ties are made with the aid of-another class of 
ordered stxuctues, essentially equivalen* to FMlrPore s case f ruses, called 
praplates and which are attahea t~ the formulas for English prepositions8. 
SO, for 'outof', for =aaple, there h-ould be at Least six ordered paraplates, 
each of which Is a string of functions that seek inside templates for inform- 
ation. In general, paraplates range across two, nat necessarily contiguous, 
templates. So, in analysing 'He put the nuhr he thought of in the table', 
the successfully matching paxaplatz would pin down the dependence OP the 
template for the last of the three clauses as DIREctior., by Wing as amp- 
ment only that particular template for the last clause that contained the 
formula for 'a numerical table', (and - not a template repxesenting a kitchen 
table) and at would do that because of a function in that paraplate seeking 
a similarity, of head (SIGN in this case) between the tt~m appropriate objecr, 
ConqularJ for ~numbarl and 'tabla'. The other template cumtaining the 
tfurnftuzsq formula for 'table* would naturally not satisfy the function 
brcaure SIGN would niok ba the kesa of this amme foxmula for %able9, 
The structure of mtuailly cc~nnected templatars that has hen put to- 
gsthax thua fu conetitutau a 'atmiantic blockg, and, if it can h con- 
&txucted, then ar far as the mystrtm is concerned all osmsntic and refer- 
ential ambiguity has hen reaolvd an8 it will begin to generate French 
by unwrapping the bldck again. ?"ha generation arrpects of this work have 
hen dracriW in (Hor~akovitr 73 . One aspect of the general notion of 
preference is that the aystan should never construct a deeper or mre 
elaborate oqmattc rraprssantation than is necessary. fox the task in hand 
and, FE the initial block can be constructed and a generation of F- ;rich 
&one, rto 'deepening* of the representation will, be attempted, 
HOW~V~X, wmy exmples cannot be resolved by the methods of this 
'baeic mode' and, in particular, if a ward sense arPbiguity, or pronoun 
reference, i~ still unresolved, then a unique semantic block of templates 
canrnot be constructed and the 'extended mode' will be entered." In this 
&a, new template-like forms are extracted fran existing ones, and then 
added to Me template pool ftom which further inferences can be made. 
So, 
in Ula tm~lata derived earlier for 'John drinks wine', the system enters 
the Loarula for 'drinks', and draws inferences corresponding to coach case 
sub-Eorrmula. In this t~xtmple it will derive template-like forms equivalent 
to, in omJf~ry English, 'The wine is in Jobt, 'The wine entered John via 
an aperture' and so on. 
The extracted templates express information al- 
ready implicitly preser.t in the text, wen though many of them are partial 
inferences: anes that may not necessaxily, be true. 
-n-sense inference rules are then brought down, which attempt, by 
a s-fe strertegy, ta construct the shortest possible chain of rule-linked 
tmmplate fo-8 from one containing an ambiguous pronoun, say, 50 one c2n- 
tainhg one of its ~ssible referents. Such a chain then constitutes a 
solution ta the ambiguity problem, and the preference approach assumes that 
the shartest chain is always [the right one. 
So, Yn the case of 'Jahn drank 
tha wine /on the table/ and it was good', (in three temprate-matching frag- 
menb as shewn) the camact chain t~ 'wine' uses the two rules 
* Wibo '73b, and @n preera) 
. (C*AN~ 1) CCSW LHI CWVE c~us~)) t+m 2r r + tr testaw;) 2) 
om, in Cswi-EngPfah 
[mhta-1 cauaa-ko-mov~-in-sel: -object-21 +* il *)*r 211 
r 2. (I m (GoWKZMQ)~ RI+ iCLAkOl 2) WWT 1, 
BXt again 8 
C1 is g&l * [anate-2 umtr 11 
Th.5~ ru1.0 uc ~nLy ptha&, that kr cu sky, tlwy corrraFnd 4wly 
to wht wa may xeao~rmbPy Iwk out tor in a gkvrn rttutkon, net? to ubt 
WSP happn. Tha hypotl,.sir irere btrt wderrtahl&np can only trkr 
plracs oh the baefs of .akpptble rufoo that: are mafixred by the eunlext af 
ap~lication. In this axample the chain constructed uy ba expressed as 
(w8srinq the &ova sguam bracket rmtaatio~~ to cont&bn nut a representation, 
but sisxxply an indiedtion, in BngldsA, of the template contents): 
~30hn drank the-wine] -Bate J, 
I [JQM wants 
backwards 
lvine is 
inf 
The assmption here: is mat tw ehain ushq ather inference niles wttl,d have 
reached the ' t&1q1 solution by using less ~.aa two sules, 
The chief drawback sf this sp!irm is that dings consisting entirely 
of primitives have a considerable amount of bo'eh vagueness and redundancy 
For example, ns reasonable coding in terms of structured primitives could 
be expected to distinguish, say, 'hmerl and 'mallet'. That my net 
matter provided the cdings can distinquish iapostantly differe~': 
of 
words. Again, a template for the sentente s he sheperd tended his flock' 
would contain considerable repetition, each node sf the template trying, 
as it were, to tell, the whola story by itself, again, the ~refasence 
cziteria are not in any weighted, which might seegn a dxahcack, and 
the prefexential chad LET@I criteria for hference chains miqht v~ff 
seem too crude. Whether or not such a, system can remain s-le with a 
WrutderabLe vecabulary. of say several thousand words, has yet to be 
trrtd. 
ft will ba ovidrnt tso any reader that Zha laat twa systems described, 
Bch.nktm ud my moun, share a great deal in cccpmon. IWsn tha apparent 
Qtff*rence In notation is reduced if one see$ the topological similarity 
mat rorults from mnrlderfng the head of a formula as functioning rather 
lLko a Schwk bait action. If one thinks of khe dependencies of the case 
eubprte of a fornula, rot &ranged 1 lneargy along the. .bottom of a tree, but 
radiating out Ex- the head in the centre, then the two diagtsms actually 
have identical topologies under interpretation. A difference vises in 
that the 'filled-in entity' for Schgnk is the conceptualization centred 
on the basic action, though for me it is the network oE formulas placed in 
relation La a t~lopLate, whexe there is indeed a basic action, the he& of 
the action formula, but there is also a basic entity in the agent formula 
and SO on. OX, to put FL another way, both what-is and what-is-expected 
are represented in the templates: the agent formula represents the agent, 
Pox exampla, but the left-hand pact of the action formula alsp represent3 
what atgrant was expected or sought, as in the (*ANT SUM) sub-formula of 
the *&inkt formula, 
A~thou~h developed in isolation initially, these twlo systems have 
also influenced each other in more recent years, probably unconsciously. 
For eatample, conceptual dependency now emphasises the agent-action-object 
far~rcrt -re than befoxe, and is less iverb-cent.red' and t~heless while, 
ronvez-sely, rrty own system now Wes much more overt uuc= of ~les of wt- 
fa1 LnfcanaaUun than in its earlier versions. Again, b~th systems have 
intellectual conneotions that go back before either generation of A1 sys- 
team. In my view, both these systems have roots in the better parts of 
the Computational Linguistics movement of the Fifties: in the case of 
Scfrank's systm, cane may think of the earlier systems of (Hays '64) and 
(Lasrb '661, and the arkow-structured primitive system of (Farradene '66) 
~~EB&e~~OLa3s-~~~prcceaents.Fnthp .Parkex- 
&odes '61) system of classiffc&ion awl the early seamtic structures of 
(Richens '61) and (Casrsterman '61). In 1961 the last author was arguing 
that 'what is needed is a disoiplina that will study suantlc nsolrge 
camaction in a, way malogous to that in which r&nrba#omatfes now rtudiro 
~~thmtLcal connaetion, and to that in which ~Ulm~tLcal Ilngulstic~ 
AQW studla8 SPUC~~C CWU3acti08l1 * (LUd. , p. 31 
This historical pint x&fsrso s final bns that is, I feel, of prgsing 
interest. Then seem t~ bs two rsscarch styles in this field: one is 
what sight b9 callled the 'fully finished style1, is whish ma wxA exists 
only in one ccmphte fow, and is not issued in iaerly ar dove1 vets iodns, 
The best example of this io Winoptad's wrk. The other type, examplified 
by all the other authots di8scussad hate, to same extent, is the det-eloying 
style: work which appears in a n-r of vlersiens over tke years, one 
bps with gxadual hprovt?ments, perkraps in attmpts ta tackle a wider 
range of lfncpistic or other inferential phenomena. There are &vat- 
ages to both styles, but even in the latter one hws that any proposed 
stxuctura ox system will, in the end, be found wanting! in Lhe balances of 
language, so it can only be a question of when one will have to abandon ~t. 
- 
The interesting question, and one to which no answer could possibly h 
given here, is just how far is it worth pushing any given structural ap- 
proach before starting again fram scratch? 
6, Sane Cormpisans~, CVkd,. -,l'qn-$r-ass 
In this sactivn X shall -para and co~~trast, under some nine inter- 
connected headings, the projects ae.;cribed in be My of the papex, 
This is not easy to do, particularly when, the pxesent author is among the 
writers discussed, though that is easily mrdied by be reader's Wing 
an appropriate discount. A more serious problem is thb , at this stage 
of research in artificial intelligence and r:ztural language, the most at- 
Ctractive #istinctions dissolve on more ds~ailed scrutiny, laxgely because 
of the lack of any p~ecise theoretical statement in =st, if not a11,'tha 
major prn jects. There are those who think that it therefore follows that 
this is not me lzrwrent for any form of critical camprison in this field, 
and that no more is needed than a 'psitive attitudey towards all possible 
pxwjeeb. OrtZythsewho feel tht,.-wt theemkrary, any kbe is asgod 
@Len arms at2 u~ @puo *Xqoa ayr7 aaoqa - puey am a- m @a-1 
TB~~~PU xo,; uo~~~uasexdax 30 TaheT aawj~dcmdd~ ay? surojum iimpmxdd~ 
uo~qarauab puoaaii ay7 B?mm zcpdqg 7na=rxnr, p vt 
up~3o3-a-w 60 p-"z 
-sn.lrwlm a3=Tpla;rd 
u? passardxa msXs s , auo axaw qua;EPdstrea aq pvcm q~a3 aqq 
p anbv 
-yaaq bu~~ozd-asxoaqq pzapu~qs Xxa~ awzs 73123 q axaw sanljm- wtfazapq 
s,euo qew zea3 am aq pTn= 'aldmoxa ro3 &uossaz peq B :asam azo~dbm a 
eaqd am qcm sdeqrad araq put? uo~qqolu prams e bqp~oha xoz stmmaz 
PW ~ltl~ P6 tn~ am *SPP~F~ a3e3~~33d ~aha lo (EL, fl-~ 
LD ax-) sap= tmoTasnpcud tq passaxdxa eren smq9Xs sqq  yo ;I~T 
xaysaa qanm aq X~xwl3'.p~na~ &pd s~w 30 3s- aqq 316511 &XPB 03 SF 1- 
.pssnasTp siayrm yamem ftm 49 pasn smzbalp pua rpuopqou aulsla33fp so 
qa~ew 
s~ 3apzw-q s2swxauo~ gua suomrrodans wyqe0~130.)38,03 raqqoyy 
'pax.dB03 aq 03 suarcud atp Xluo pup naantm tp~yrr 
Am! 30 qasqno am qle #nap S'J qj 0s tsaq3euzdd~ ~to~~?riruo6 5~2~3 saw0 UP 
TTarJI sta "yrm UMO s,Pz)Z~~~U~ ran- X~upqxa;r pTnm qupkl pumas oy7 *raho 
-arw -7nq qndu~ am u~ X~q~q'ldxa quasard qw us~~wo3u~ qqm uraauoa 
TTe pawaqasa re3 os seq aq log Jpuo3as ar(;) ~TM swtriqs xou 4auydI asx~y 
en WTn Aqlq) zo ye~lrr~w xanru qw mnon, lpooxdd~ 
,n11~j# w 30 
uo~qdyrasap a ~szauab os uam *7mq r)ndu~ am u~ quasaxd i~~s~~dbte aw 
ST q~qq a6pa~n~t.q pix- Teaq plro ~snqdaaucm bu~quasoz8ez ormqs~r awm-6~~3 
U'flpqUUJ (t) PUP 'r)ndu~ 30 ,aXnXlru78 ejQJm8, ow -8 3*@IaJJTP X~2-3 
-?g~uB?s em 7- qxaq 30 uayq~uasexdsz am 303 8W?Q3Ic$S snasrs xqa 
-ma uTtzquoa ( '~3314~ smqsXa aaoy7 se qsns 'aazaq ~orauw -an awm uf 
(m5~pwqe! ~y am trTqqTn aknbuP~ Tsrnqou 30 Lpnaa am u~) BQP~~BX* mTV2 
-auob puaaoo au~3ap aq que~ +o~dwpx* 303 *?qb~m ,wT~P;L~u~& qs3t~j, 
s,ppxbotq~ lo as* ~7s apnloxe pw 48.q~xamap sqaag~td am TTW apn~~u~ 
*aaea s~m uy 'p~nm qm~ iruo :suoT-J.yuljlep 33f-a XUP XQ pwaJaP 
20UU93 ~WSP~ 3UBqYa 4 ~0~330~e8 am yaj~.~o rfimwAn WTW~ 
-a45 pax- f"qszt3 uponaaq uo~qau~aun? a, WX-TH WTT 'qroqs pesew 
  ST^ sqaaf.wd 30"~01"33b~a~ am 3q AWMB F27T-m W 3snm 31 
*uer plnoyla 4ssazfWd 
30 adoq %w UT TOWhJOTTOwT SP UOTSSWSTP OW law0 XW 
holds that his staactsues =a f&pess&ent d ury pu%kcmbw 
Qi(l qp 
resentatfm, er rather, that they whd a#r xrtrlilard at a 8c at &ma& 
of magrssentaths~, d~pendimg on th mbjer=t area. khm &a 
bubt a86 the r.egg~scntathw in terns M -isriatam tBm% bm 
im 'B$s 
~lrk mar,$ to 31e Ln we-tow cxxrorpwdbam vlsh ropLM m. 
The slsaqest how-kewl appmach fs -y ht ollrcm;t$J dm 
that this dispute is ultimateby one oE degree, simx no aae clnilr 
that every lccution recognized by an $nltelligaat rryl- art br i.Qpd 
hto a 'deep' representation. To taka an extmme auab amy -tam tikt 
uag@ 'Gxd W8rninqT into a deep sewm%hc represemgltkm 
that the carsect sespsns8 was also rGcad &arnhxjt wauld $Ch & seirfms 
thesretical mistake. 
Hawever, themst serious arqument fa ira mn-tqpar%fshr$ -tmUm 
Ss mt in kerns 09 the av~Hdaqam of ammbm~ d%g%%dUw, & 
closely tied to the defence of se&anthc pahb2hwm %EI m, u&%& Ps a 
large subject not to be unde~taken here. Cbe a% the tmxUes & 
tic prh,itivqs is that they are open ka - bad &e%eaces, ihumua z;cW 
than increase their plausibility. For -e, users a;JF fur 
linguistic representation have declared them to hve scme 
d -WU 
existence and have implied that there is a 'right sett ~Wwes bpq 
to ernpiriqal discovery. On that view the essentially hqd.sUc 
of structures sf prbitives is lost, because %t is an usmwkLd fe&are af 
a language that we can ch-e its vocabuhry as function ui& dLt&matf.a 
vocabularies. But if there is a zight set of prLmiUwm, utmt~ mk~~% 
are the awes of brain-items, then that essential SF=- uxald km h&t- 
What is the 
is that there is a considerable amount of psychologicill 
evidence that Geople a2e able to recall. the content of uhat they hear and 
understand without being able to recall either the actual words or the 
syntactic structure used, Thare is large literature on this subject, from 
which two sample references would be [Wettler '73) and (Johnson-Laird '74) . 
Thesc results are, of course, 
no proof df the existence of semantic 
primitives, but they are undoubtedly supportkng evidence of their plausi- 
bility, ao is, on a different plane, the remlt from the encoding of the 
whole Weboter's Third International Dictionary at Systmv Develagmefit Corp- 
oration, where it was found that a rank-ordered frequency count of the words 
usad to define other words in that vast dictionary was a list (omitting 'the1 
and a which corresponded almost item-for-item to a plausible list of 
ssmantic primitives, derived q ptioxi, by those actualhy concerned to.codel 
the structure of wmd md sentence meanings. 
Zt is important to distineish the dispute Ibout level from the, 
- 
closely connected, topic that I shall call the centrality of khe #nowledge 
required by a language understanding system. 
Centrality 
What X aria calling the centrality of certain kinds of information con- 
cerns not its level of representation but its non-specifidty: again a 
contrast can be dram between the sorts of infomiltion required by Charniakls 
s~st~, 0x1 
on@ hand, and that required bySchankls* and my om on the 
obhar. Charniak's examples suggest that .the fundemental form of information 
is highly spacific** to particular situations, Like parties and the giving of 
presents, while the sorts a£ information central to Schank's and my own 
systems are general partial hssertions abut human wants, expectations, and 
scr on, my of which' are so general as to be almost vacuous which, one misht 
argue, is why their zple in understanding has been ignored for so long. 
- 
* Though as noted earlier, Schank in 1975 has adopted Rbelson9s (1973) 
notion of 'script', as a largar-scale 'frame1, in such a way as to in- 
corporate much less 'central1 knowledge. 
**In a recent paper (1974), Charniak gives much more general-rules, such 
as his 'rule of significant sub-action', mentioned earliw. 
If I were a reasanably Eluent spaker of, say, G8man, 1 might we13 
not understand a Gem conversation about birthday presents unless Z had 
tietailed 8factuaS. information &but: hw Gens~~~ns organixa the giving of! 
presents, which Plight be considerably different the way we do it, 
Converselys aP course, 3 migl.rt umiarstd much og a twkmlcal artLcle abut 
a subject in which I was an expert, even th~~rgh 1 knew wry Ifttka af the 
language in which it was written, These az'e certainky wnrL3exatians that 
tall Lox Charniak's approach, and it La perhaps a paradox that the s~rt of 
r~aturrl language understalridler that wuld tend to COJIP~~ his apswp,t tons 
~muld be one concerned with disooursa &L.r;)ut, say, the details aL reyapking 
a t$Otor CU, where factual. infsmathon is what is centsalt yetr imnically, 
Charniak has concehtrated on something as general as childtents stories, 
with their need of deep assumptions about hurwn desires and khaviour. 
In the end 'this difference may again turn out to be one of enphasisj 
and of what is most appropriate to diSSerent subject areas', though there 
niay be a vexy general issue lurkiw somewhere here. It seems to me not a 
fuolish question to ask whether much of what appears to be about natural 
language in A.I. research is in fact about language at all, Even if it 
is nbt that may in no way detract fran its value. Newell (blolore, Newoll 
q73) has argued that A.1. work is in fact 'theoretical psychology', in 
which case it ceul8 hardly be research - on natural language, When describ- 
ing Winograd's work earlier in the paper, Z raised this question in a weak 
farm by asking whether his definition of Ipickup1 had anything to da with 
the natural language use of the word, or whether it was rather a description 
of how his system picked samething up, a quite different matter. 
Suppose we generalize this query samewhat, by asking the apparentky 
absurd question of what would be wrong with calling, say, Charniakls work 
an essay on the 'Socio-Economic Behaviour of American Children Under Stress? 
In the case of Charniak's work this is a facetious question, asked only in 
order to make a point, but with an increasing number of systems in A.I. 
being designed not essentially to do research on natural language, but in 
order to have a natural language 'front end' to a systm that is essentially 
intended to predict chemical spectra, or play snakes and ladders or whatever 
the question becomes a serious one. It seems to me a good time to ask 
whether we ahould expect advance in understanding natural language from 
those tackling the problems head on, or those coroncerned to build a 'fr8nt 
andv. It i~ cLtt,xly the case that - anpiece coulL 
bp esrcntial to the understanding of sane story. 
The question is, does 
it follow that the epehifict.tion, organieation and formalization of that 
knowldge la &a studf oP l:.aga, because if it is then all human enquiry 
ftm physics and history to medicine is a linguistic enterprise. 
And, of 
cowrr, that poaskbility has actually been entertained within certain strains 
of darn philosophy. 
itowaver, I am not wing hefa, to breathe fresh life into a philosophical 
distinction, batween being aLuut lmpunge and - not being about language, but 
tather introducing a practical distinction, (which is also a consideration 
in favour of optiqg, a3 I have, to work on very general and central areas 
of howledge) between specific knowledge, and central knowledge without 
which a syartem could not be said to unilexsttind the language at all. 
For 
1 
example, I might know nothing of the arrangement of American birthday 
parties, but could not be accused of not understanding English even though I 
failed understand sme pazticular 'children's story. Yet, if I did not 
have available acme very general partial inference such as the ane people 
bainq hurt an8 fallingr or one about people e*avouring to possess things 
that they want, then it quite possible that my lack of understanding of 
quits airtple aentencee would cause observers to think that I did not under- 
rW Englbsh. An interesting and difficult question that then arises is 
whether those who concentrate on central and less central areas of discouse 
could, in principle, weld their bodies of inferences together in such a :gay 
as to create a wider system: whether, to put the matter another way, 
natural language is a whole that can be built up fxm parts? 
Pken-noloqica level 
Another distinction that can be confused with the central-specific 
one is that of the lphencmenological levels1 of inferences in an under- 
standing system. I mean nothing daunting by the phrase: consider the 
action eating which is, as smatter of matmica1 fact, quite often an 
act of bringing the bones of my ulna and radius (in my arm) close to that 
of my lower mandible (my jaw). Yet clearly, any syatQIP OP CCEPgeK).n sense 
inferences that considered such a truth when reasoning about eating would 
be making a mistake. One might say Ulat the phenoeenolqtcrl lrvrL of 
the anraly_sis was mng even thourgh all the InF'amznces it: !!ad8 ware Uue 
ones, The stme wuld be true of any W.I. system that wade everyday 
inferences about physical objects by mnsiQaring their quantum structure. 
Schank's analysis of eating rontaias the inf'matian &st it la done 
by uovirsg the hands to the mukh, and it might be argued that yven ulis is 
goisrg too far ftom the '@aaningl of eating, whataver that my bar towsrds 
generally true information about ma act which, if always inferred &ut 
aU acts of qating, will carry the systesrs nruamageably fax. 
Therq is no denying that this sort of infomatioar might be useEul to 
have around somewhere; Wt, in Minsky's terms, the 'default1 value of the 
instrument for eating is the hand brought to the mouth, so that, if we have 
no contrary infomation, then that is the way to assue that any gfvm act 
of eating was performed. Nonetheless, there clearly is a danger, and that 
is all X am drawing attention to here, of taking inferences to a phenolnencw 
ldgical level beyond that of uammn sense. A clearer case, in my view, 
would be Schank's analysis (1974a) of mental. activity in which all actions, 
such as kicking a ball, say, are preceded by a rsrenta9 action af conc~iving 
or deciding to kick a ball. This is clearly a level of analysis untrue to 
caumn sense, and which can have only harmful effects in a systea intended 
to mimic corxlaPon sense reasoning and understanding. 
Demupling 
Another general issue in dispute concerns what I shall call demupling, 
which is whethex ox not the actual parsing of text or dialogue into an 'under- 
standing system.' is essential. Charniak and Minsky believe that this in- 
itial 'parsing1 can be effectively decoupled from the interesting inferential 
work and simply Qssumed. But, in my view, that is not so, because many of 
the later inferences would actually have to be done already, in order to have 
achieved the initial parsing. For example, in analysing 'He shot her with a 
colt', we cannot ascribe any structure at all until we'can make the infexences 
that guns rather than horses are instruments for shooting, and so such a 
sentence cannot be represented by an 'inference-but-no-parsing' structure, 
without aremi- that language doas not have one of its esgential char- 
aeteristlca, namely ayptemrrtie ambiguity. 
The essence of decoupling is 
allowing roprersntational etructures to have significance quite indtlpend- 
ant of theirapplication, and that may lead one to a eituatMh lot 
essentially ditfstont frm that of the logician who simply asserts that 
ouch-and-much ie the 'right structuxel of sme sentence. 
The inferences required to resolve word aense ambiguities, and those 
ad tb reaolva pronoun reference pxobletast are not of different typos1 
oftan the two pmblaas occur in a eingle sentence and must be resolved to- 
gether. But Chatniak's decoupling has the effect of completely separating 
these two closely related liniguistic phenomena in what seems to me an un- 
raallstic aanner. His system does inferencing to resolve pronoun ambig2 
uttfes, while sense ambiguity is presumably to be done in the future by 
sapre other, ulti.mately remupled, syste'~.* 
Wodulari ty 
Madularity concerns the deccwposability af a firogran or system into 
(interacting) parts, and fhe nature of the relationship between t+e parts. 
Winograd's program, as we saw, contains syntactic, semantic and deductive 
BegmentJ which interact in a way he describes as 'heterarchicl (as oppo$ed 
to 'hierarchic8) which means that different wents can be in controlaat 
dif foreht tiswc . 
Qn the other hand, ScW and Wilks have argued that it is not nec- 
esaaty ta absarve efther the syntactic-semantic, 
or the semantic-deductive, 
dlatfnctlon in an understanding program. On that view there 0 no par- 
t;icular,virtue in integrating syntax and semantic rbutlnes, since +here was 
no need tm separate them. 
Charniak, h~~verr wbld argue that, in same sensg, one should makq 
a syntax-setplantics distinction here if one c+n. 
This would be consisterit 
with his view on decoupling, and for him it wuld be convenient to de- 
couple at a module, as it were, such as syntactic analysis. 
But decoup- 
* Although Chaxniak would aque that sense ambiguity could be introduced 
into his system in its present fona. 
and s-ng modularity are not the same thing, Wineqrsldi1s progru, for 
example, is madulak but not at all ddcouplecl kropp SUX~~C?! trxt, 
Ava&lability of suxEaee at.ruct:ura 
An issue close ho that of the spproprlcrtp level of repreaer\letlun in 
a system i$ that aP the availabflity of! Qa surface sbuctum FP the 
language mcnlysedt or, to put it more crutlely, Ute availability during 
subsequent analysis of tho actual words &wing antlkysed, Tt~ee~s axe thtrerty 
available in ~olby, and ar~ indirectly availabh in S ns7, Nkrxq~ad'~~ 
and my awn system* but Schank mkos a pulrat uf Uaa iiqwrtance af their nm- 
availability, on the grounds that an ided r-epresentalhcn skmuld be totally 
independent of the. input surface structuxta and wrds, There axe Sxrth 
theoretical and pxactf cal aspects to aims claim sf ScbcEk %: f r. the lhf t , 
the osder of the sentences of a text is part a£ its surface structure, and 
pres\rm&ly it is not intended ta &andon this 'superficial inf~rmaticn' 
In one of his recent papers 91974bI Schank sems to have accepted sme 
limitation on the abandonment Of surface structuse. 
The other, practical, pint concerns the form of representation em- 
ployed: in the (1973) hnplementation of Schank's systffi using an analyser 
of input text, a matwry and a generator of responses, it was intandd that 
nothing should ha transferred fxan the input program to the eufyut pr~yriuw 
-cept a rapresentatian ded in the structures sf primitives discu:::dl 
earlitlr,* The question that arises is, can #at structure specify and 
disting~ ish word-senses adequately without tuansf erring inf~m~ticn spci- 
fically associated^ with the input word? Schank clearly believes the 
answer to this question is yes, but that cannot be considered established 
by the scale of cmputations yet described in print. 
A suitable envir-ent in which to consider tke question is that of 
translation from one language to another: suppose we are analyging a 
sentence containing the word 'nail1 meaning a physical object. It is 
clear that the translation of that word into ~rench should not be the same 
* '~nis point is to some extent hypothetical since, as we saw, Schankls 
conceptualizations still do ccntain, cr aspear t~ c~ztain, 3aF.y surface 
items; in particular nouns, adjectives an3 adverbs. Iizwever, tLis is 
a transitional'natter and Lley are in the course of r'epkace.zezt, as 
noted, by non-superficial items. 
as the translation for 'screw or 'peg1. Yet is it plausible that any 
dascription of the function of these three entities entirely in terms of 
arawmtf~ prWtima1 ma without any explicit mention of the wrb name and 
its connection to its French equivalent, will be sufffcienG t43 ensure that 
only the right match is made? 
Blication 
'Shis pint ia a ganeralioation of the last Lwp, and concerns tho way 
in which differant ryutaa8 display, in the etzructures they manipulate, the 
actuel. Ipracdltres of application of those structures ta input text or dia- 
logue, 
'Thiri is a matter dlEferent from computer implementation of the 
aystm. Xn the case of Colby's patterns, for example, the form of their 
application to the input English is clear, even theugh the @a&hing in- 
volved could be achieved by many different implementation algorithms. 
Xn 
the case of my awn system, I hold the same tio Be true of the template 
stzructurres, even though the time the input has reached the canonical 
template form it is considerably different from the input surface structure. 
The system at We extxeme end of any scale of perspicuity of application is 
Wincgradls wheke the procedural notation, by its nature, tries to make clear 
the way FR which the structures are applied. At the other end are the 
sys- 
~QSS of Schank end Charniak, whaxe no application is specified, which means 
that tha regrslrrentatfono are not only cmpatible with many hapiementation 
aLporitba, which doers mtmtter, but axe also compatible with many syste~ls 
of: Ilnguiskic NILS, W~IOO~ specification is an essential piece of inquiry, 
and whose subsequent production may cause the basic system to be fuhda- 
mentally dFf Perent. 
Application is thus different fram decoupling, 
for SChankls system 
is clearly coupled to language text by Riesbeck'sqarser, though his 
stzuctures do mt express their own =lication to language text. 
English pxepusitions will serve as an example: 
in Schaxk's case 
notation there is no indication of how the case discriminations are 
actually to be applied to English prepositions in text. 
So, for example, 
the preposition *in1 can correspond to the containment case, time location, 
and spatial loeatioqw amow others. As wa saw earlier, tiha B1serhinatian 
rnvolved in actual analysis is a matter of apciEying wry delioat. srm- 
tic rulss ranging ovex the basic atatahtic otxvctursw 
the structures iLlEd case aytltem thmseL~as B~BLP~ to mh to bg leoaantlally 
dependent on the nature and apphicabiUlty olP such EU~~S~ and as this 
application of tlae sy8tem should have an obvious place in the ~Ve~aLli 
structuxas, It is nat sawthing to be delegated to ta mra ' impl9s~ent- 
ation' It epugh of the linguistic intractablasfi of English analysis 
we= to be delegated out of this segmtlentatiun, &.I, muld be uffexlny no 
more to the analysis of nature1 language than the hgiciarts tllho pmEEer the 
predicate calculus as a p]rausibLe strircture for English. 
In sane of his -re recent writing's 'Minograd has begun to develop a 
view that is considerably stronger khan this 'application1 one: in his 
view the control structure of an undkrstanding progran is itself of theo- 
retical significance, for only in that way, he believes, can natural la- 
Forward inference 
great 
outstanding dispute 
perspicuous. 
whether one should make massive 
forward inferences as one goes through a text, keeping all one's expect- 
ations intact, as Charniak and Schank hold, 0s whether, as I hold,, one 
should adopt some 'laziness hypothesis1 &ut understanding, and generate 
deeper inferences only when the system is unable to salve, say a referential 
problem by mre superEicia1 methods. Of, in other terns, should an under- 
standing system be ~roblern-, or data-, driven. 
* This is not meant to be just bland assertion. I have written at same 
length on the relations between application and the theoretical status 
of linguistic theories in (Wilks '74). 
**The differences between Minsky's (19741 notion of 'default value' and 
what I have called 'prefexence' can be pointed up in terms of application. 
MhsQ suggests 'gunt as the default value of the instrument of %he action 
of shooting, but I would claim that, 
in an example like the earlier 'He 
shot her with a colt', we heed to be able to see in the structure assigned 
whether or not what is offered as the apparent instrument is in fact an 
instrument and whether it 'is the default or riot. In other words, we need 
sufficient structure of application to see not only that 'shcotlng1 pre- 
fers an instrument &at is a gun, but also why it will chaose the sense 
of 'colt1 thatcis a gun rather than the one which is a horse. 
ATtlx>ugh Schank sametinee writes of a system making 'all possible1 
inferences a8 it p10ceBd8 though a textt this ie not in fact the heart 
ot tho dispute, since no one would want ta defend my atmng definittior 
oL the tom 'all poesibla infetences'. 
Chacniakqs argument 4s that, un- 
less certain fornard inferences we made during an analysis ofr say, a 
e-ry - forward inferencest that is, that are not problem-driven; not 
made in rerrpcnss ta any particular problem of analy.ysia then known to the 
ayrtsm - than, ar a matter of empirical fact, the system will not in 
general be able to solva srPbiguity or rofetence ptoblems that arise later, 
because it will never in fact be possible to locata (while looking back- 
wards at the text, as it were) the points Ohere those forward inferences 
ought to have been made. This isr in very crude summary, Charniak's case 
against a purely ptoblw-driven inferencer in a natural language under- 
stander , 
A ditficulty with this.argument is the location of an axample of text 
that c~nffrms the pofnt in a ncn-contentious manner. Chatniak has found 
an excerpt ftcm a book describing the life of apes in which it is indeed 
hard to locate the reference of a particular pronoun in a given passagQ. 
Chamiak's case is that it is only possible to do so if one has made eert- 
aln inon-prublm occasioned) inferances earliez in the story. But a 
nuabet QE readers find it quite hard tb refer that particuXe pronoun any- 
wayl which might sweet that, the text was simply badly written. 
Another difficulty 16 that it is not always clear whether the argument 
is about what pple are thought to do when they understand, or about how 
one should mnstruct an wdexstandLng system. 
This is a difficult matter 
about which to be precise: it would be possible, for example, to agree with 
Charniakts argurnentmd still construct a 3urely problem-driven inferencer 
on the ground that, at the mment, this is the onlv way one can cope with the 
vast majority of inferences for understanding, since any system of inferences 
made Fn response to no particular problem in me text is too hard to control 
in practice. Indeed, it is noticeable that the mst recent papers of Schank 
(1974a and 1974b) and Charniak (1974) have been considerably less forward- 
inference oriented than earlier ones. 
This Bispute fs prhaps mly one of degree;&nb about tha posalbil- 
ity of befining a degree af forward inf~rlene~e that alds the adutisn of 
later semantic problem without going Lntta wwe~srry depth. This right 
be area where paychelogicab invastrigatloras wukd be eE F~'IO.~US hdp It9 
'The,justflication of systems 
-= 
Finally, one might useZuLly, WwpA bslaf?Ly, curntxast ths Shffarent 
des of JustiPicathan iolplieftly appealed ta by the syst:.~~~s deucxikd 
earlier hn this paper. These seem to FIM? to &u:e to EOW t 
(i) Tn terns of the pwex of the inferentiak syskea enpisyPd. 
This fama of j.ustifhcation has underlain the- earLy predicate caXculus- 
based language programs, and is behind Hayesr (1974) recent deaand that 
any foxmalism for natural language analysis should admit of a set thecttetic 
s~tics, in the Tarskfan sense, so as to gain 'Intellectuai respect- 
ability1, as he puts it. The same general type of justificatim is 
appealed to in sane degree. by systems8 with BLMNER-type f~xtmlikas. 
(ii) 
In terms of the provision and formalisation, in any terms in- 
cluding Elqglish, of We sorts of knowledge recpirea LO understand areas 
oe ~~SWUS~. 
(iii) In terns af #e actual performance of a s):st~m, i~plementd on 
a ckmguter, at a task agreed tu demonstrate understanding. 
(iv) 
In terns of the lfnquistic and or psychclcgfca~ plausibility of 
the proffered system of representation. 
Oversimplifying considerablyr one might say that Charniakls system akpeals 
mostly to (ii) and somewhat to (i) and (iv); Winogr3S1s to {iii) and scme- 
what to the other three categories; Colbyls (as regads its natural lan- 
guage, rather than psychiatric, aspects) appeals almost entirely to (iii); 
Simmons largely to (iv) , and Sthank's and my own to dif f ereng mixtures of 
(ii), (iii) and (iv) . 
In the end, of course, only (iii) counts for enpiricistsu but there 
is considerable difficulty in getting all parties to agree to the terns of 
a test.* A cynic might say Chat, in the end, all these systems analyse 
tho setltenres atit they analwe orl 
to put the same point a little more 
Wwtetically, these 
is a sense in which systerms, those described here and 
tho st^ elsewhereb each define a natllcleal, languaqe, namely the one to which 
it applies. The difficult question is the extent to'which those mnv and 
mall natural lacpages resemble Engli~h. 
7. Cdnclueiqn 
The Last section ,atreased areas of cuzrsnt disagreement, but there 
w~u18, if vote& mse Menr be tmnsiderable agreement atmt~g A.X. workers 
on natwdl, language about where the large problems of the immediate future 
a: tt,e need for a go4 memory mdel has been stressoa by Schank (197-la) , 
and my would add the need for an extended procedufbl theory of texts, 
rather of individual example sentences, and'far a more sophisticated 
theory of reasons, causes, and motAFhs for use in a thwry of understanding. 
Many Ptight also be pezsuaded to agree on the need to steer between the 
ScylLa of trivial first generation Fmplementatfons and the Charybdis of 
utterly fantastic ones. By the lattet, f mean projectfi that have oeen 
sericuly dfscussed, but never implemented for obvious reasons, that would, 
ray, enable a dialogue program to discuss whether or not a participant fn 
ufvlul o-ty '$%kt qllilt~', end if 80 why. 
nie last disease has socpatbes had as a lrajor syrpptoCll an extensive use 
t -f the wrd 'praqmat-cs' (though this ern also indicate quite benign con- 
df tioas in other cases) , along wdth the implicit claim that lsemant ics has 
been salved, t~) we should get on with the pragmatics'. It still needs 
repeat- that there bs rn sense whatever in which the semantics of natural 
language has been solved. It is still the enoxmaus barrier it has always 
been, even if a feu dents in its surface are beginning to appear here and 
there, Even if we stick to the simplest examples, that present no diffi- 
- 
* Though an interesting, potentially revolutionary, distinctlon seems 
to have bean introduced by a recant reviewer of many of the systems dis- 
cmsed here, heteen the functionirig of a program and la 'program in itself1 : 
'Only Winograd describas a program that is sufficiently impressive in itsell 
tc force us to Me his ideas seriously. The t6chniques of Uki others havc 
ta get by an whatever Fatuitive appeal they can muster1. 
(Isud '74) 
culllty to the human padsr - anb it must h ad$sittad that tc 
bdan M+ 
of th. praiakrnt faults of tho A.I. paradigm oC lmgupa that it h.r vprnt 
too much t.ha M puzs1es UIIP~~~~S - thrm an rtLU gnat bi~~lculths 
both ayst:-tfc axle3 linq~I$tI~. 
An example of the fomr wwld be UH devq10pmnL OL a 
=yak- of undarstandictg texts or storias'that had ,my cdpaclty to rwrcr 
after having its expactations satisttad ah then, subsequently. Xructrrtul, 
At prssent no systtm QC the BQZ~ dascrhbed, uhethor of 9 
ox whatever, has any such oapeity to rcrovsr, The sitrwrtiian is quite dig- 
ferent fmp that in a dialogue, as in Winograd's o)rsta~, where, on Being 
given each new piece of inEcmtlon, the syste~l checks it against uhat it 
~WS~ to see if it is baing contradicted, and then behaves in an appro- 
priately puzkled way if it is. In fraroe or lexpectationl systems it is 
a11 too easy to mnstruct apparently trick, but LxesicaEliy plausible, ex- 
amples that satisfy what was king lmkd for & then overturn it. That 
pssibility is already built into the notation oE frm or expectatian. 
An example of Phil Hayes against my om system will same: mnsider "The 
hunter licked his gun all over, and the stock tasted especially gwd" 
What is maant by 'stock1 is clearly the stock piece of the gun, but any 
preference system like mine that considers we two sansss of ?stockt, and 
sees that an edible, soup, sans@ of 'stock1 is the preferred object of the 
action 'taste, will infallibly opt for the wnsng sense, Any £game or 
expectation systm is pmaa to the same general kid df countex-exmphe, 
In particular cases like this it is easy to suggest what might be 
done: here we might suggest a preference attached to the formula for any; 
thing that was essentially pareof aslother thing (stock = 'part of gun' 
in @is casej, so that a local search was made whenevex the 'part-of1 
entity was mentioned, and the satisfaction of - mt search wuld always 
be the overriding pxeference. Gut that is mt the same as a general 
solution to thq problem, which used to be called that of 'topic' in the 
cmputational semantics of the Fifties. There are no solutions to L1i$ 
problem available here and haw, though some suggestions have been made by 
Abelson 91974) and M~Demo'tt (1974) . 
nay 30 qe~ sp mepcpord 
'a~cpaoreauf XTT- Iw ' WeTw x~aao'l;3 
W =he a T@Q*@O&*~CB~ eginwc~kh@S, OX &kS&#@tfte. * 
a 
t2mwsis and dl!i?%J~~. But M* I 2-1 .MI (p.ICL*I d -. 
ant2 it should bi psb.L* to ow %at -8 9YlulPosrrPsSyw -- 
me aplptcme2.l an my y%m qimmtdarm Jks ~!let mid 
-I. Ea 
mu$d be niaa hf WLs md be tm by a 
mothax chm~e oE Ser&ahn. 

References 
(AibeLsora '73) 
Abelson, R.P., The Structure of Belief Systems, in MOD. 
(Abelson '75) 
Abelsvra, R.P., Discourse Beaders, in Bobfow and Col3ins (eds.), 
~epresentation and Understanding 
(Academic Press,, N.Y.) . 
(Balzer et a1 '74) 
Balzer, R. et. alj Domain-Independent Automatic Programming, Inform- 
ation Sciences Iwtitute, Marina del Pey, Ca. 
(Bobrow '68) 
Bobrow, D.b., Natural Language Input a Computer ?robhB~-solving 
system, in lainsky (ed. ) , ~e~ntic xhforpwtion ~roceosing, (NIT Press, 
Cambridge, Hass , 1968) . 
Ibwn '74) 
Brown, G., The' Believer Svstem, in ACE, 
(Bruce '72) 
Bmce, B., A Pldel EQ~ Temporal References and hh Appbi~dktio~ in B 
~uestion Answering Program, in &hmce 3 
(Bruqst Scbidt '74) 
Brucer B., Schmidt, C.F., Episode Understanding md Belief Guided 
Paxsingt in Am4 
(Chaxniak ' 7 2) 
Charniisk, E., Towards a Model of ChiZd3m1s Story Caprehensi,on, 
NITAT-TR 266. 
(Charniak '7 3) 
Charniak, Emr Jack and Janet in Search of a Theozy of Knowledge in 
AIJC3. 
(Charniak ' 74) 
Charniak, E., "He will make you take it back": A Study in the Pragd 
matics of Language, US?: No. 5. 
(Chomsky ' 5 7 ) 
Ch=skyr N., Synkqctic Skuctu;res, (bieuton, The Hague, L957). 
fColbyr Parkinson '74) 
Colby, K.M., Parkinson, R.Cw, Pattern-Matchifig Rules for the Recog- 
nition of Natural Language Dialogue Expressions, in A3neric%n Journal 
of Cdmputational Linguistics; Vol. 1, No. 1. 
(Colby , Hilf 7 3) 
Colby , K.M. , Hilf, F .D., Mtfltidimensional Analysis in Evaluat ingv a 
Shulation of Pavanoid Thought, in SUAXH-194. 
(Colby et a1 ' 71) 
Colby, K.M., et al, Artificial' Paranoia, Artificial Intelligence 2. 
(Coles "72) 
Coles, L-S., Techniques cos Information Retrieval Usin g an Xnferen- 
tial Questian-Answering System. with Natural Language Input, SRITN. 1932. 
(Davidson ' 6 3 ) 
Davidson, D., Actions, Reasons and Causal Laws, Journal of Philosophx. 
(Davics, Isard2) 
Davfas, D.J.M., karef, S.D., Utterances as Programs, presented at the 
7th International Machine Intelligence Workshop, Edinburgh, June 1972. 
(Enea , Colby ' 7 3) 
Enoo, H., Colby, K.M., Idiolectia Language-Analysis for Understanding 
Doctor-patient Dialogues, AIJC3. 
(Farradens ' 66) 
Farradcne, B., Research on Information Retrieval by Relational Indqing, 
Dept. of Information Sciences, City University, London. 
(Fillmure '74) 
Fillmore, C., Summer School lectures, University of Pisa, Italy. 
(Goldman '74) 
Gc-Idman, N.M., Computer Generation sf Natural Language from a Decp Con- 
centual Bast?, CAST No. 2. 
(Halliday '70) 
Halliday, M.A Kt in Foundations of Language. 
(Hayes '74) 
Hayes, P.J. Some Problems and Non-Problems in Representation Theory, in 
AISB. 
Hays, D., Dependency Theory: A Formalism and Sone Observations, Language, 
Vol. 43. 
Ii~idorn, G.E., English as a Very High Level Language for Simulation Pro- 
gramming, in'Proc. Symposium on Very High Level Languagqs, Santa Monica, 
ca. 1974. 
(Hendrix et a1 '73) 
Hendrix, G.G., ek al, Language Processing via Canonical Verbs and 
Semadtic Models, in AIJC3, 
(Herskovits ' 73) 
Berskavits, A., The generation of French from a semantic representation, 
SUAIM-2' 2. 
(Hewitt ' 69) 
Hewitt, C., in Proc. Second International Jo-int Conference on Artificial 
Intelligence, (Bedford, Mass., Mitre Gorp., 1969:. 
+ 
(Bockett '62) 
Rockett, C.F., Grammar for the Hearer, in Vol. XI1 of the Symposia in 
=lied Mathematics, American Mathematical Society. 
[I-sud I74) 
Isard, S . , review of MOD, Scicnct~, VL>~. f klb. 
(Johqson-Laird '74) 
..r y ? 
Jol~nsan-I,;.ii.rd , P . , blu~~ory for t.w~d?;, Na)ttirt* , '-1 . . 3- . 
(Josl~i, FQcischcdcl' ' 73) 
Josl>i, A. K. , Weischedel , R . M . , SQUL~ Frills fcr t hc bLd.%l TI .:-T.IC-TL-~I 
of Davies and Issxd: Scnlant ics of Fredic.~tc CQrq>$crncnt Construct icn::, 
in AIJC3. 
Kuk~rl, 1'. S . , The Struct urt~ of Scie~~t if iu Rr.vc?lutiuns, (t'tlivcr:: i tjm ~x 
Chieag~> Press, Chicago, 193~3 2nd ran. . 
(Lakof E '71) 
MkoEf, G, , in Steinberg and Jak~b~vits (eds, 1 , Semantics, (C.U.F., 
Cambridge , 197 1) . 
(Lamb '66) 
Lmb, S., in Outline of qtratificational Grammar, (Ge~rget~71li~ University 
Press, Washington, D.C. 1 . 
(Lighthill ' 73) 
Lighthill, J. -, in Artificial Intelligence : a Paper Sp~p~siuu~, (Szicncc 
Research C~unci'l, 1973) . 
(blcCarthy, Hayes, '69) 
b!cCarth>*, J., Elayt.s, F.J., i11 ~!cltzi-r a11~1 $!i~:t~ic (t-1~1s.)~ kI;~chi~~~ 111tclli- 
qcnce 4, (Edinburgh Ilnivcrsi ty Press, E~iinburyl\! . 
(PlcCas thy, 7 4 ) 
blcL'nrthy, J. , Rcvielt~~ of (Lighthill '73) , in Artificial Intt~lligp~lcc.. 
(FlcDemo tt ' 7 4 1 
blcDermott, D.V., Assimilation of New Information by a Nataal, hnsuase 
Understanding System, MITAI, Tr-291, 
(Mas terman ' 61) 
Masterman, M., Samantiq Message Detection fr?r Machine Translation, in 
TEDD . 
(Minsky ' 68) 
Minsky, ILL.. , Editor's Introduction to Semantic Information Processing, 
(MIT Press, Cambridge, blass . ) . 
(Minsky '74) 
Flinsky, M. , Frahe systems, circulated bSS ,, from blassachusetts Institute 
of Technology, and in, Winston (ed.) Visual Information Processing ills7751 . 
(Moore, Newell '7 3) 
Moore, J., Newell, h. , How ccn Plerlin Understand?, in L. Gregg (ed. , 
l$nowledqe and Cof~dition, (L. :Srlbaum Associatiori, Potomac, Md., 1973) . 
(Parker-Rhodes. '61) 
Parker-Rhodes, A.F., A New Model of Syntactic ~escri~bion, in TEUD. 
(Richcns '61) 
Richens, R.H., Tigris and Euphrates, in TEDD. 
(Hiager '74) 
Rlegt~r, C. J., Conceptual Memory, Stanford Univr!rriity Ph.U. 'J'llonia. 
(Riesbeck '74) 
Riesbcck, C.K., Computational Understanding: Analysis of SantQnccs 
and Context, CAST No. 4. 
(Rulifson, at a1 '72) 
Rulifson, J .A., et a1 QA4: A Procedural Calculus for Inductive 
Reasoning, SRITN '73 ., 
Sanhwall, E., Representing Natural Language Information in Predicate 
Calculus, in Machine Intelligence 6, Meltzer and blichie (ads.), 
(Edinburgh University Press, Edinburgh, 1971) . 
[Sandewall '72) 
Sandcwall, E., An Approach to the Frame Problem, and its Implementation, 
in Machine Intelligence 7, Mcltzer and blic3ai e (&s. 1 , (Edinburgh Uni- 
vc%r::i ty Pred"', Edinburgh, 1972) . 
(Sandewall '721 
~andawall, E-, PCF-2, A First-Order Calculus for Exprassiny C~nceptunl 
fnformati~n, Uppsala Univcfsity, Deparbcnt r;E Ctmputer Science. 
(Scna* '68) 
Schank, R.C., Semantic Categories, Tracor Doc No. 68-551-0. 
(Schank ' 73a) 
Schank, R.C., The Fourteen Primitive Actions and Their Inferences, 
SUAIM-183. 
(Schank '73b) 
Schank, R.C., Identification of Conceptualizations ~nderlyi- Natural 
Language, in KID, 
(Schank '74al 
I 
Schank, R.C., Causality and Reasoning, CAST No. 1. 
XSchank '74b) 
Schank, R.C., Understanding Paragraphs,, CAST No. 6. 
(Schaak et a1 '70) 
Schank, R.C., et aL, SPINOSA II: Concoptun1 Casa-Bnsc3d Natural 
Language Analysis, SUAIM-109. 
(Schank et a1 '72) 
Schnnk, R.C.? Primitiv~ Concepts Underlying Verbs OS Thought? SL%I#-kb3. 
(Schank, Rieqer ' 73) 
Schank, R.C., Rieger, C.JOt Inference =d the Computer Undexstanding of 
Natural Language SUAIbl-197, ahd in A~tificial ,Xntelligencle, 193.5. 
Schgh)w, R .C., et a1 bMGIE : blcmory , Analysis, Response Generation srld 
Infere~~ce on English, in AIJC3, ;in13 in Journal ok the A.L",N. 1975. 
(Simmons '70a) 
Simuons, R.F., Natual Language Question-m&ilc.ering-Systms: 1969, Cam. 
ACH, Vol. 13. 
(Simmons ' 70b) 
Si~l;wns, R.F., Sane Swantic Structures for Representing English bleqn- 
ings,.Tech, Report Nb. NL-1, University of Texas, Austin, 1970. 
(Simons '73) 
Simmons, R.F., Sehantic Networks: Their,Computatioh and Use for Under- 
standing English Senten~es, in bOD. 
(Shimon=, et a1 "66) 
Simmons, R.F., et al, An Approach Toward Junewr?rirrg English Qucsti~.ns 
frern Text, in IFIPS Conf. Pmc., FJCC Vwl, 2% 19bt.. 
(Simns, Bruce '71) 
Simtuons, R.F., Bruce, B ,C . , Swe Relations Betwaar~ Predicate Calculus 
and Semantic Net Re~resentations of Disc.t;3uswe, in Pr~c. Second Inter- 
L 
national Conference on Artificial Intelligence, 1971. 
(Simmons, Slocum '72) 
Simmons, R.F., Slocw, J., Generating English Discourse from Semantic 
Networks, in Com. ACM;Vol. 15. 
(Sussman '74)' 
Sussman, G. J. , The VirLua,us Na%ue of Bugs, in- ASSB. 
[Milks ' 67) 
Wilks, Y.A., Semant$c Consistency in Text -an Experiment and sac 
Suggestions, Systems Develbpent Corp, , Santa blonich, Ca. , SP-2758. 
(Wilks '72) 
Wilks, Y.A., Grammar, Meaning and the Machine Malysis of Language, 
(Routledge & Ksgan Paul Ltd. , ~os'ton and London, 1972) . 
[Wilks ' 738) 
WIUP, Y:A., Preference Sewurtics, SUAIM-206, and in Keenan (ed.) 
F~xajal Sthantics of Natural Language, [Cambridge University Prass.1975) 
h?llks T3b) 
lius. Y.A.., An Artificial Intelligence Approach to Machine Translat- 
ion, in 8400. 
[Wilks '74) 
#ilks, Y,A., One Small 
Head - Model9 and Theories in Linguistics, in 
Fowdstiohs of Innpuage, Vol. 11, 
(WiLtka ' 75) 
Hilks, Y.A., A Preferential, Pattern Seeking, Semantics for Natural 
Language Inference, Artificial Intelligence. 
(Weber ' 7 2) 
Weber S., Semantic Categories of Nominals for Conceptual Dependency 
Analysis of Natural Language, SURIM-172. 
(Wettler $73) 
Wettler, M., Zur spefcherung syntaktischer Merkmale im Langzeitge- 
dachbis, Rericht CLber den 28. Konress der Deutschen Gesellschaf*- E. 
Psyehologie, 
(Winograd '71) 
Winograd, T.# Procedures as a Representation for Data in a Computer 
Program for Understanding Natural Language, MIT Ph-D. Thesis. 
Winograd, Tmr - Understanding Natural Language, (Academic Press, Inc., 
New York, 1972) , 
Winograd, T,, A Survey ,Lecture on Natural mquage, Third International 
Joint Conference on Artificial Intelligenke, Stanford, Ca. 1973. 
(Winograd '74a) 
Winograd, T., Frame Representation and the ~eclarative/~roced~ral 
Con-~ve~syr in Bobrow and Collins (eds.), Representation and Understwding 
(Academic Press, N , Y, 1. 
(WinagrzYd '74b) 
Whograd, T., Five Lectures on Artificial Intelligence, SUAIM-246, 
(Hittgenstein ' 53) 
Wittgenstein, L., Philosophical Investigations, (Blackwell, Oxford, 1923). 
(wooas ' 70) 
Waxis, W., Transition Network Grammars far Natural Language Analysis, 
Ccan. ACM, Vol. 13. 
Wds, W., Meaning and Machines in [ed. Zamp~lli)~, Proc. of khe Intor- 
national Conference an CamputationaZ Linguistics, Pis&, 3,973. 
(Woods, at a1 '72) 
Ms, W., at al, The Lunar Sci~ncas Natural Language Infr);)matien 
System, BEN Report 2378, 1972. 
