00100	PROBLEMS OF NATURAL LANGUAGE UNDERSTANDING IN TELETYPED INTERVIEW DIALOGUES.
00200	
00300	
00400	     By `natural language` I shall mean everyday American English
00500	such as is used by readers of this book in ordinary conversations.
00600	It is still difficult to be explicit about the processes which
00700	enable hummans to interpret and respond to natural language.
00800	Philosophers, linguists and psychologists have speculated about
00900	and investigated natural language with various purposes and few
01000	useful results.  Now attempts are being made in artificial intelligence to write        
01100	algorithims which `understand' what is being expressed in natural
01200	language utterances.
01300	     During the 1960's when machine processing of natural language
01400	was dominated by syntactic considerations, it became clear that
01500	this approach was insufficient.  The current view is that to unDerstand
01600	what utterances say, knowledGe about linguistic syntax and semantics
01700	must be combined with knowledge about an underlying conceptual
01800	structure containing a world-model and an ability to draw inferences.
01900	How to achieve this combination efficiently represents a huge task for
02000	both theory and implementation.
02100	     Since the behavior  being simulated by  our paranoid model is the
02200	linguistic-conceptual behavior of paranoid patients in a psychiatric
02300	interview, the model must have some  ability to process and respond to
02400	natural language input in a manner indicating the underlying pathological
02500	
02600	to develop a method for understanding everyday Englisg sufficient
02700	for the model to behave conversationally in a paranoid way in a
02800	circumscribed situation.  What is said in this situation is far
02900	icher than what is said in conversations with a block-stacking
03000	i2900
03100	robot but its requirements for constructing an interpretation
03200	of an input are not as complex as trying to understand anything
03300	said in English BY anybody in any dialogue situation.
03400	We took a pragmatic approach which considered "understanding"
03500	to represent "getting the message" of an utterance by
03600	gleaning some {not all} of the relations between them.
03700	this straightforward approach to a complex problem has its
03800	drawbacks, as will be shown, but we were striving for a
03900	sufficiency to demonstrate paranoia rather than complete
04000	comprehension of English.
04100	     Linguistic approaches cite traditional problems with
04200	ambiguity, as illustrated in the following example from
04300	Wilks { }.  Suppose I walked up to you, a stranger, on
04400	the street on Sunday morning and said
04500	     {1} He fell while getting to the ball'
04600	Admittedly this is a strange scene and in this situation
04700	you would think me to be crazy, hungover and maybe still
04800	drunk, but the example is no more weird than the isolated
04900	examples discussed in the linguistics literature.  Suppose
05000	further that in your personal `dictionary' the word 'ball'
05100	has at least two senses, {A} a spherical physical object
05200	used in a game, and {B} a formal dance.  {It probably has
05300	also a third sense as a verb but we will ignore this more
05400	or less recent example of semantic shift}.  Having no
05500	further information in this situation and attempting to
05600	construct an interpretation of my utterance, you would bbe
05700	puzzled as to whether I was referring to a ball game or a
05800	dance.  If we then continued on our respective ways, saying
05900	nothing else, your puzzlement would continue and even increase
06000	--I don't know what he was referring to nor why he even said
06100	that to me.
06200	
06300	     The ambiguity arises because of the two word senses for
06400	ball, each of which would give the utterance a meaningful
06500	interpretation.  But the example is extremely forced and
06600	artificial.  Such isolated utterances cannot bbe disambiguated
06700	`uniqueated is a better term' but this is no handicap for
06800	ordinary human convversations in which ambiguities hardly arise
06900	at all.  Besides the utterance itself, extra information is
07000	usually available in the form of contextual and situational
07100	knowledge, even bbetter, one can always ask.  If I had said
07200	only utterance {1} to you, you could simply ask:
07300	
07400	            {2} `What do you mean?'
07500	
07600	and my reply would indicate something about a game or a
07700	dance or who `he' was.
07800	     Utterances occur in conversations which take place in
07900	sociopsychological situation.  The communicants have roles
08000	and intentions towards one another.  If the situation is that
08100	of a medical or psychiatric interview between doctor and
08200	patient and the doctor asks:
08210	
08300	     {3} `How much do you drink?'
08400	We know from the nature of the situation that drink means
08500	`drink alcohol' and does not refer to a total fluid intake.
08600	
08700	     Dialogues represent connected discourse in which all
08800	the utterances, except perhaps for opening greetings, are
08900	connectable to previous utterances, contexts and sub
09000	contexts, topics and subtopics surround any givven utterance
09100	and activate relevant word senses such that alternative
09200	senses do not arise in the comprehension process.  In
09300	spoken dialogues intonations and word emphases are further
09400	means for avoiding ambbiguities, but the connected discourse
09500	of dialogues brings problems of its own to the algorithmist
09600	whose program must keep track of what is going on and what
09700	has been said before.  Foremost is the problem of anaphoric
09800	reference.
13200	
13300	Fragments
13400	
13500	     Another major problem for algorithms which attempt to understand
13600	discourse consists of the fact that many of the input expressions
13700	are not well-formed.  All sorts of fragments and ellipses appear
13800	which must somehow be connected to conceptualizations under discussion.
13900	For example, consider the following exchange:
14000	
14100	    {10} Dr. - How do you like the hospital?
14200	
14300	    {11} Pt. - I shouldn't be here.
14400	
14500	    {12} Dr. - Why not?
14600	
14700	The question {12} is an elliptical expression for the full conceptueliza
14800	tion
14900	
15000	    `Why should you not be in the hospital?'
15100	
15200	     Junk words {`well now'} {`tell me more'} and go ahead signals
15300	must be responded to by continuation of a topic.
15400	
15500	For example:
15600	
15700	    {13} Pt. - I went to the track last week.
15800	
15900	    {14} Dr. - Really?
16000	
16100	Such expressions as {14} stand in a meta-relation to the topic and
16200	serve to keep the conversation going.  
16300	
16400	Rejoinders
16500	
16600	     Sometimes the input expression from the interviewer is a rejoinder
16700	, a reply to a reply by the patient.  For instance:
16800	
16900	     {15} Dr. - Who are you afraid of?
17000	
17100	     {16} Pt. - The Mafia is out to get me.
17200	
17300	     {17} Dr. - I would be afraid of them also.
17400	
17500	in which {17} is a rejoinder.  Such expressions are not requests for
17600	information but provide information for the patient's model of the
17700	interviewer.
17800	
17900	Interviewer-interviewee Relations
18000	
18100	
18200	     It is characteristic of psychiatric interviewing that the
18300	participants from time to time do not simply talk about the
18400	patient.  Two situations exist concurrently in an interview,
18500	one being talked about and one the participants are in.  At
18600	times the second situation becomes the first.  When the partici
18700	pants discuss one another and their relation, the dialogue
18800	expressions contain intentional verbs which in English fit the
18900	pattern `I X you' or `you X me'.The comprehension process must
18950	
19000	distinguish clearly between subject and object in the case of some
20000	of these verbs.  For example in
20100	
20200	     {18} I like you
20300	
20400	the speaker `I' experiences the liking but in 
20500	
20600	     {19} Do I please you?
20700	
20800	the `you' experiences the pleasure as a consequence of something
20900	`I' does.