Pragmatic sensitivity in NL interfaces 
and the structure of conversation 
Tom Wachtel 
Scicon Ltd, London 
and 
Research Unit for Information Science & AI, Hamburg University 
i. Introduction 
The work reported here is being conducted as 
part of the LOKI project (ESPRIT Project 
I07, "A legio oriented approach to knowledge 
and data bases supporting natural user 
interaction"). The goal of the NL part of 
the project is to build a pragmatically 
sensitive natural language interface to a 
knowledge base. By "pragmatically 
sensitive", we mean that the system should 
not only produce well-formed coherent and 
cohesive language (a minimum requirement of 
any NL system designed to handle discourse), 
but should also be sensitive to those 
aspects o~ user behaviour that humans are 
sensitive %o over and above simply providing 
a good response, including producing output 
that is appropriately decorated with those 
minor and semantically inconsequential 
elements of language that make the 
difference between natural language and 
natural natural language. 
This paper concentrates on the 
representation of the structure of 
conversation in our system. We will first 
outline ~he representation we use for 
dialogue moves, and then outline the nature 
of the definition of well-formed dialogue 
that we are operating with. Finally, we will 
note a few extensions to the representation 
mechanism. 
2. The HOVE frame 
We are assuming a seven-slot frame for the 
representation of moves within a dialogue, 
with the following slots: HOVE, USER, AGENT, 
TURN, ACT~ BASE, CONT. Every move in a 
conversation is represented by such a frame. 
The HOVE slot uniquely idenitifies a 
particular move in the conversation by an 
arbitrary integer. The USER slot identifies 
the oucrent user of the system. The AGENT 
slot specifies whether it i~ a user move o~' 
a system move. The TURN slot has the value 
OPEN n or CLOSE n, where n is a number that 
refers to a particular exchange. Typically, 
a move with a value OPEN n for the TURN slot 
might be a request, and one with a CLOSE n 
value the c~orresponding response. 
The ACT slot specifies what act is performed 
by the utterance. This will be either a 
speech act, or the value ACTION, since not 
all moves need be speech acts. The range of 
speech acts that the system will have to 
reoognise or' produce is clearly smaller than 
that which occurs in conversations between 
humans. Furthermore, certain speech acts 
will be of primary importance given the 
domain of application of the system, namely, 
as a front end to an expert system. We have 
therefore produced an initial hierarchy of 
potentially relevant speech acts 
(Waehtel 1985a), where the major 
classification is into requests, assertions 
and commentaries. Some of these are referred 
to below. Many of the speech acts we use go 
one level below what is traditionally viewed 
as a speech act (i.e. in the sense of Austin 
(~952), Searle (1969), etc.) and may be 
compared with distinctions that McKeown 
(1985: 9ff.), for example, discusses under 
the category of "rhetorical predicates", 
though they are by no means the same. The 
only speech acts discussed below a~e 
referred to by the following abbreviations: 
REQACT request-for-action 
REQAFF request-for-affipmation 
SUPPAFF supply-of-affirmation 
REQCONST request-for-constant 
SUPPCONST supply-of-constant 
REQCONF request-for-confirmation 
SUPPCONF supply-of-confirmation 
The BASE slot specifies the current topic, 
in the very restricted sense cf a pointer to 
the node in the ~emantic network that 
corresponds to the object what the current 
exchange is about. This simplistic view of 
topic is adopted here as a first step only, 
and serves to i~lustrate the points 
discussed below. 
The CONT slot specifies the semantic 
representation of the utterance, and we 
envisage using the same representation for 
semantics and for actions, so that all 
possible ACT types can be represented 
uniformly in the CONT slot. In particular, 
we will define an exchange as a pair of 
utterances with the same value for the CONT 
slot, for the time being. This is of course 
too strict. Other functions specifying 
35 
"local coherence" in the sense of Hobbs 
(1982: 227) are also relevant here. The 
particular illooutionary force of an 
utterance will be a function of the value of 
the ACT slot and the CONT slot. Subdialogues 
that are not in the mainstream of the 
conversation will be identified by 
particular relationship of values for the 
TURN slot between adjacent moves, enhanced 
by the values of the ACT slots for the 
moves. 
Some examples of the use of this frame to 
represent sequences of utterances in 
conversations can be found in Waohtel 
(1985b, 1985o), including its use to 
identify shifts of topic, subdialogues and 
relevance, as well as the contextual 
disambiguation of speech acts, which is the 
main topic of these working papers. 
3. The structure of conversation 
We assume that it is possible to define the 
structure of a possible conversation by 
rule. Actual human-human conversations may 
defy such analysis, as illustrated by, for 
example, the work of Sachs, Schegloff & 
Jefferson (1974). However, the possible 
ways in which the conversations we are 
dealing with may go are severely limited by 
three factors: (a) this is an interface to 
an expert system (or some similarly specific 
software), which delimits the possible range 
of topics; (b) one of the participants in 
the dialogue is a machine, which means that 
it will not suddenly want to indicate that, 
for example, Albert's niece is a friend from 
school, but this fact has no bearing on the 
supportive things being said about her; and 
(o) the other participant knows that his 
interlocutor is a machine, and will behave 
accordingly. Therefore, what we need to 
model is not a typically natural open human 
conversation, but a restricted type of 
conversation that also occurs between humans 
in certain well-circumscribed contexts. For 
example, a conversation between a would-be 
passenger and a ticket clerk at a railway 
station is closer to what we need to model, 
and in such oases it is possible to define 
what is or is not a well-formed conversation 
by rules of an abstract nature that may well 
be inadequate for other naturally occurring 
converations. 
We therefore propose three rules that define 
the notion of well-formed conversation in 
the present context, making the following 
assumptions. The structure of a conversation 
can be represented as a tree structure. The 
wellformedness of such trees can be defined 
by rewrite rules. The maximal number of 
levels of embedding in such trees is six 
(see below). In particular, subdialogues can 
be embedded within dialogues, but there can 
be no embedding within subdialogues. The 
last restriction conflicts with what people 
do. It is one of the restrictions we 
consider necessary, and which can be handled 
in such a way that the user will not notice 
36 
that any such restriction exists. 
We assume that the following four categories 
are sufficient for the representation of the 
structure of conversation. The symbols used 
serve as mnemonics for their approximate 
counterparts in English, but they should not 
be strictly equated with them: CONV 
(conversation), DIAL (dialogue), EXCH 
(exchange) and MOVE (as discussed above). 
To formulate in informal terms the general 
style and atmosphere of the rules that we 
will propose more formally below, let us say 
that a CONV may consist of one or more 
DIALs, a DIAL may consist of one or more 
EXCHs, and an EXCH consists of two MOVEs, 
with each of these MOVEs followed by an 
optional DIAL. 
A major point about conversations that must 
be handled in a grammar of this type is the 
fact that although MOVEs are the only 
terminal nodes, and are therefore the nodes 
that correspond to the utterances that are 
actually produced, with all other nodes 
representing more abstract elements, certain 
features of conversation need to be 
associated with these abstract nodes. For 
example, although each MOVE is specified for 
who the current user of the system is and 
each MOVE also has a particular topic, as 
discussed above, these notions properly 
belong to more abstract levels of 
conversational structure. Who the user is 
can be defined at the CONV level (i.e. we 
define a CONV as a conversation with one 
user). The topic of an utterance can be 
defined at the DIAL level (i.e. a CONV can 
consist of one or more dialogues, each on a 
single topic). Furthermore, a DIAL can 
consist of one or more EXCHs, and it is at 
this point that the content of the 
utterances that form part of that EXCH is 
defined. 
Let us now be more precise. We assume that 
some of the slots mentioned above in the 
MOVE frame are represented as features on 
the nodes in the trees representing the 
structure of the conversation of which the 
moves described by the MOVE frames are part. 
This association of features with nodes, 
plus the assumption that all features 
trickle down, with a few exceptions 
discussed below, provides for trees of the 
general form shown in Table i. The lower 
case letters are constants. Note that the 
values of the BASE feature on the 
subdialogue nodes have not been specified. 
We return to this point below. Table I 
represents a goal: the sort of structures we 
want the rules to produce. The following 
three rules generate trees of this type. 
Kleene Plus notation is used. 
The notation should be interpreted as 
follows. Roman letters as feature values are 
constants. Greek letters are variables 
ranging over possible feature values, and 
are to be interpreted consistently within a 
rule~ but not necessarily between rules. 
They are used to ensure that the correct 
MOVE F:il 
ASE : b 
ONT : 
URN : 
Table I 
I D IAL 
ASlE:_J 
I EXCIt 
SE~ it\] 
ASE \[ 
\[ 
DIAL 
B SER 
EXCH 
ASE :b 
ON~ : 
CONV 
1 EXCH 
ASE : \] 
ONe: ,~1 \] 
MOVE MOVE MOVE MOVE 
asE:l I nAsE: I nasE: I BASE: l I ~ASE:I I BASE 
O~T:S I ICOm~: ICO~'r: ICOm'-m I ICOm~:q ICOm' 
r DIAL 
A~E : 
EXCH ~ 
s~.. ~\] 
ASE : | kCO~r : 
nS 
MOVE MOVE HOVE 
\[BASE : 
\[CONT: 
\[~URN : 
DIAL 
UBSER : AsIE: ~ 
EXCIt 
SER:iN ASH : 
ONLY: 
F ...... MOVE MOVE 
ASE:Pl pASE: o~T.~ I Ices,: 
\[TURN:o_\] \[jUURN: 
CONV 
3 
EXC}~ 
BASE:~ / co~T:~ / 
2 
-~ DJ:AI.,d+ DI~L d .--) EXCHj L 
ABE :b \[ pass: BASl!: :?\[ 
~D:- \] ~u~D : suBD: r I 
_ . ~om:o d 
--> MOVE n\[ 
BASE : ~ | 
ICON'.e: 6 | 
\[~ul~N : OeE~J 
<(DIALd)> MOVE n ((DIALdd I) 
\[~URN : CLOSI? 
feature values triokle down in the right 
oases. Node subsoripts distinguish between 
different instanoe~ of the same node. Note 
that Greek letters are also used a~ 
variables for node subsoripts (rule (3)). 
Round braoket~ indioa~e optionality in the 
usual way. Angle braokets (rule (3)) are 
used in the same way as used by e.g. Labor 
(1972: oh. 8) in the study of 
~ooiolinguistio variation. They indioate a 
relationship between elements on the left 
and on the right of the rule. The expansion 
on the ~ight is only possible if the feature 
on the l~!ft of the rule has the value 
speoified, if both are enalosed in angle 
brackets. In the present ease, they are used 
to prevent the expansion ~f a subdialegue as 
a further subdialogue. The feature ESUBD=-3 
is introduoed by the rule that expands CONV. 
The rule e;¢panding DIAL oopies this feature 
with this value. The rule expanding EXCH 
allows an expansion of EXCH tQ include 
(optionally) one or two DIALs, but if the 
DIALs appear, then they oarry the feature 
\[SUBD:+\]. The expansion of such a DIAL by 
rule (2) oopies this feature with this 
value, as before, when the DIAL is expanded 
to one or more EXCHs. However, sinoe the 
EXCHs so generat, ed oarry the feature 
\[GUBD:+3, the rule that expands EXCH will 
not allow the possibility of further DIALs, 
beoause any suoh e~pansion is oonditional 
upon the EXCH having the feature \[SUBD:-3, 
as speoified in rule (3). 
The value oi the fe~ture TURN is either OPEN 
or CLOSE plus a oonstant that refers to the 
relevant EXCH. Note the use of the 6reek 
37 
Table 2 
' I MOVE I \] 
SER: Max | I~ SE: IJCAI | ~SER: Max 
NT: CI | IBASE: EXCH 
RN: OPEN I ~UBD: + 
ENT:USER | I T: REQCONST~ 
I ' EXCH 2 
~SER: Max q 
|SUBD: 
LC_0NT: C2 _J /___ 
f \] 
MOVE 2 
OVE: 2 
SER: Max 
ASE: EXCH I 
ONT: C2 
URN: OPEN 2 
GENT:SYSTEM 
T~QCON~ 
CONV I 
~SER: Max~ 
f 
DIAL I \] 
ASE : IJCA_~ UBD : 
- 
f EXCH I 
FSE~: Max q 
IBASE : IJCAI I ISUBD : 
CmONT: cI 3 
l 
J MOVE 6 
IOVE : 6 q SER: Max | DIAL3 
ASE: IJCAI | ~SER: Max \] 
ONT: CI | IBASE: EXCH 
URN: CLOSE I | ~SUBD: + 
GENT:SYSTEM | I CT : SUPPCONST~ 
J EXCH3 I EXCH4 
FsER: Max -1 r-~ FSER, Mox \] IBASE: Excel I \[s3) lEASE: EXCH 
|suED: + / "~ Isu sD: + ~ONT \[ c3 
__1 ...... LC0NT i C4 
I I I I __ __ MOVE 3 __ __ MOVE 4 _ __ MOVE 5 __ MOVE 7 __ __ MOVE 8 
ussa: Max I USER: Max lUSER: Max //USER: Max \]/US~R: Max | 
BASE: EXCH 1 I BASE: EXCU 1 lEASE: EXCH 1 //BASE: EXCH ~ //EASE: EXCH 1 | 
CONT: C2 I CONT: C3 /CONT: C3 //CONT: C4 ' TURN: CSOSE 2 / TURN: OPEN 3 /TURN: CLOSE 3 / /TURN: OPEN 4 / /c°NT: / C4 / /TURN: CLOSE 4 / 
/AGENT:USER / IAGENT:SYSTEM /AGENT: USER / F GENT:usER / / AGENT=SYSTEM / 
variable. The same constant is used as the 
value of the feature BASE in subdialogues. 
What this amounts to is a stipulation that 
the topic of a subdialogue is the EXCH that 
it is part of, which seems to be about right 
intuitively. This is what makes them 
metalinguistio in character. Furthermore, 
note that this is a case where a 
feature/value pair does not trickle down. 
This is tantamount to stipulating that DIAL 
is a BASE-bounding node: it creates 
"islands" with BASEs that do not extend 
upwards to the main dialogue, but without 
overwriting the BASE of the current main 
dialogue. Again, this seems intuitively 
correct. 
Let us now provide a concrete example of the 
structure that these rules assign to a 
dialogue such as (4). 
38 
4 Ui When is the next JICAI meeting? 
Si I presume you mean "IJCAI" 
U2 Yes 
B2 Do you mean the next conference 
or the next conveners' meeting? 
U3 Conference 
$3 12 August 
U4 19857 
$4 Yes 
The structure ie given as Table 2. The 
values for the feature CONT are given as 
constants rather than as full semantic 
representations, and the constants rather 
than as full semantic representations, and 
the constant IJCAI is used for the BASE, 
which is the actual conference due to take 
place on 12 August 1985. This value has been 
given in all relevant oases, thus glossing 
over the fact that the BASE could not be 
identified immediately, which is what 
triggeeed the subdialogues. We add, 
however, neetain features that wece 
discussed earliee, such as MOVE, AGENT and 
ACT, to olaeify how the final focm of the 
frame eepresenting each MOVE is deeived. 
This is a oonveesation in which there is 
only oFie main dialogue arid only one maid 
exchange within that dialogue. I hope that 
it is clear how these additional elements 
would be incoeporated into the structure, 
and how the appropriate values foc BASE, 
CON? and SUBD would be iaaintained or 
changed. 
It is inteeesting to note that the nodes iri 
conveesation trees of this sect have a 
conceptual validityl in that dJ.~feceet node 
types (Jo~'eespond to diffeeent aspects of a 
~enve~°satierio Thus a CONY node eoc~'esponds 
to "this (Iollve~'sation with this usec", a 
DIAL \[:SUBD :-3 node eoccespends to "this 
topic"~ an EXCH \[SUBD: --3 node corresponds to 
"this point" ~ a DIAl \[BUBD ~-~'\] node 
eoreesponds to "a point that needed 
olai'ifieation", arld an EXCH ESUBD:÷\] iiede 
ooe~;'espends to "what was unuleac", Each HOVE 
ill\]de 12eprl~sel\]t5 ~311 uttee~Jiil\]e , (11 > \[~oLll,~e. 
The seA; of HOVE nodes dominated by EXC'.H 
\[UI.IBO:"LI eoreespends to "what was said; t',he 
gelrf~l,a! l iln-~ of the OCilVecsation", alld tile 
set ot HOVE nodes dol,iiriated by EXCFI \['31l\[)1):+3 
corresponds t(i "the !iubdialogees". t.J. kewiso~ 
£H~'I; ~1 \[if tit tic>r il o d (,~ ~ ClOl2ices pontl i;o o51iel? 
hclladec ~lollients el 6~ OCliVe~'satiorl= The set 
07 C()NV nod(.~>s oor'~'eilds ttl "all the di\]ltJ~-erlt 
~lerivi!IcfJ{~\];ierl~ )\[ licit ill thi~,~ se%sioll with 
d.i.~t~rerit tlsol,'s", the set ill 1)i~%1. \[BUBD.'-'J 
7iod{-#~5 (ltl!. eR~pondt; to "tli~! to~\] il:;f7 (i(.iv()l~ed ,i i 
tli~,~ set of F;XCH FBUBD'-\] ned~:q~ ~ei:,i.,espsnd+~ 
tu "the lJoin~s discussed", and +Je mi. By 
takin(t J. ntn account oenf iUu~'ai, iolts o~ 
I eatue~ ~It liodes ~ one oaii isolate, 
th~:~'efo~e, such elements a~ "the last but 
cne topi¢~ discussed by tl~o previous user" or 
"the fleet point i~i this ooeve~'saticm that 
needed olaril i{lation". 
Let us now turn to two e)(tensions o~ the 
above system~ hypebhetieal moves arid 
anticipatocy moves, ~'equired by certain 
dialogue phenomena. 
4. Hypothetical moves 
"rheee are appaeently innocuous COilVepsatiens 
suoh as (5) which may cause ti~oob i e on 
formal grounds. 
U: Can you print the minutes Of 
the last meeting? 
S: Yes. Do you want to see them? 
U: Yes 
S: (p~ints) 
This is a five-move conversation (the 
system's "Yes" counts as a sepacate move). 
The g~ammac would assign the steuotuee shown 
informally as (6) to the first four moves. 
MOVE ii USER~ OPEN 1, REQAFF 
MOVE 2: SYS'FEM, CLOSE i, SUPPAFF 
MOVE 3: SYSTEM, OPEN 2, REQAFF 
MOVE 4: USER, CLOSE 2, SUPPAFF 
On formal grounds, the oonversation is 
closed after the fourth.move (U: Yes), with 
all OPENed moves having been CLOSEd. What, 
then, trigger's the system's printing of the 
eequieed text (MOVE 5) ~ and what happens 
after that, Since an odd numbec of moves 
~annot constitute a well-formed conversation 
aeoecding to the grammar peesented above? It 
is oleae that it is the meaning of MOVE 3 
that is the key. To handle this fo~mally, we 
pcopose the use of the notion of 
"hypothetical move" and the cepresentation 
speech aot.~ net as atomic elements Hilt as 
struotuces. Thus we wi I \] ue present a 
supp I y -o~-a~ f i~mation in response to o 
ceqoest-loc--af~irmation as SUPPAFF(REgAFF)o 
A hypothetiual move is a move that does not 
a~tually oeeur ilr the oeilversation $ but 
which the ~iystem oosstcuuts on lille basis o~ 
very specific clues, and whic:h allow it to 
(~ontinue the eo~iw.~rsat ion appcopi~ia~ie i y ° 
They ooz, cespeYid in some way to a 
~q~pcesentation c~ Geiee'~ (19/5) llotien o~ 
implioature. Foe ,E,~xample~ a more detailed 
analysis o:~ (5) reveals that (6) omits 
several important details. Tile first iilOVE! is 
abtual ly alailigtAous betwei:)n a ~'equost-:foc- 
affirmation and a ceqoe!~t-foz'-acM~ioli~ What 
we would like) the systelii to do is te supp).y 
bbe a f f il'iilatiori te the r'equest-~ f or ,-~ 
allil~'mati(3n part,j arid to retlu~st alfiPiliation 
conct~cilifig the eequest--lel.-:aetion pact. Th~ 
important point is that a p\[<epeP analy.qiB of 
"Oo you ~#ant to see the!m?" should r'epPesent 
the J\[aet tl'iat this is response to the 
potential ~'equest.- f or~aotion int, ez'p\['et at ion 
of "Can you print the minutes of the last 
meeting?"0 The upshot of tliis is that a 
more pL~ecise ~ep~'eseritation of the ~i\['st 
lout moves ef (5) is (7), cathez' than (6),. 
MOVE i: U, ()PEN i, REQAFF/REQACT 
HOVE 2: S, CLOSE i~ ~UPPAFF(REQAFF) 
MOVE 3: B, OPEN 21 REQAFF(REQACT) 
MOVE 4: U, CLOSE 2~ SUPPAFF(RESAFF(~E@ACT) 
We new have a way of amcountillg fo~ the 
system' s eext more (pminting), and fec 
explaining why anything at all happens. 
MOVE 4 is a SUPPAFF'(REQAFF(REQACT)), i.e° a 
supply of affirmation in response to a 
request foc affirmation in response to a 
request foe aotion. It seems quite gloat 
intuitively that this complex structure is 
equivalent "to a REQACT, and we propose that 
this type of reduction should take place by 
rule. 
39 
However, this rule must not over-write the 
original interpretation of the illooutionacy 
force of the move, which must be retained 
foc the dialogue to be well-formed with 
respect to the grammar. We propose that the 
e~feot of this type of rule (an implioature 
redundancy rule) is t~ create a hypothetical 
move immediately following it of the 
appropriate type. Its effect is to alter the 
structure of the conversation in exactly the 
same way as if the user (in this case) had 
actually uttered something like "I request 
you to p~int the minutes now", except for 
the fact that it is noted that this is a 
hypothetical move. We now have a formal 
entity that can trigger the printino of the 
required text, since this is a CLOSure of 
the hypothetical move. If no printing took 
place, then the dialogue would be ill- 
formed, since it would contain one OPEN that 
had not been CLOSEd. This, the system is 
behaving as if the use~ had made a 
particular move that did not actually occur. 
(The notion 'as if' is central to 
Vaihinger's (1935) theory of fictions= It is 
al~o cruoial to 6rioean implicature.) 
The result is that (4) is now analysed as a 
six-move dialogue, with the structure shown 
a~ (8). 
MOVE i: U, OPEN I, REQAFFIREQACT 
MOVE 2: S, CLOSE I, SUPPAFF(REQAFF) 
HOVE 3: S, OPEN 2, REQAFF(RE~ACT) 
MOVE 4: U, CLOSE 2, SUPPAFF(REQAFF(REQACT)) 
MOVE 5: U, OPEN 3, RE~ACT, hypothetical 
HOVE &: S, CLOSE 3, ACTION 
5. Anticipatory moves 
Another type of ir=ealis move is an 
anticipatory move, where on the basis of 
specific clues the system anticipates what 
the user's next move will be. The 
difference between these and hypothetical 
moves is that no action is taken by the 
system until there has been a reaction from 
the user that either confirms or disoonfirms 
the correctness of the move that has been 
anticipated. The use of such moves will be 
of assistance in the interpretation of 
cryptic follow-.ups, as in (9). 
u: Can you provide progress reports on LOKI 
subprojeots? 
S: Yes. Do you want to see them? 
U: LOKA 
S: (prints) 
The user's second utterance must be 
interpreted as a request-for-action, which 
is difficult on formal grounds. Without 
going into too much detail, we propose that 
in such oases ths system should have 
formulated an anticipation of a following 
40 
request~for-action before the user'~ next 
utterance. \]'his could either be an e;¢plicit 
request=for-action ("Please print the LOKA 
progress report"), or ~imply "Yes" (i.e. a 
SUPPAFF(REQAFF(REgACT))), which would 
trigger a system request for clarification, 
perhaps, or anything else at all tha~ can 
serve to identify the BASE of the 
anticipated request-for-aCtion. This is the 
important point about the anticipatien~ 
Anything. at all that can fill in the 
unspecified ~Iots in the BASE of the 
anticipated request-for-action will confirm 
that this utterance is intended as a REQACT. 
For this reason~ the bare name LOKA i~ 
enough to get the report printed. Any other 
sufficiently identifying description of the 
relevant subprcjeot would have achieved the 
same, such as any of the following <as 
appropriate): the one based in Hamburg, 
Hamburg, NL, Max'~ projeot~ most ceeent~ 
etc. 
6. Conclusions 
The processes and formalisms outlined above 
are all tentative in nature, and represent 
part of an approach to the problem of 
pragmatic sensitivity, rather than purported 
solutions to the problem. We envisage then 
as being part of a system that uses a 
multi-level parsing technique, with mutual 
assistance between different subcomponents 
of the parser, so that pragmatic information 
can immediately be used to assist par~ing i 
for syntax, and so on. We also see that 
par~ing will involve not only ~entence 
parsing, but also conversation parsing, in 
that the appropriate structure of a 
conversation must be built up at each step. 
This is simply one further part of the 
general parsing process~ but one that we 
envisage as being of assistance to other 
parser suboomponents, as well as fulfilling 
its primary function of making sure that the 
system is something of a conversationalist, 
rather than just being a communicative 
plodder. 

REFERENCES

Cole, P. & J. L, Morgan (eds.) 1975. Syntax 
& Semantios~ volume 3: Speeoh aots. New 
Yock= Aoademio Press 

Findle~ N. V. (ed.) 1979. Assooiative 
networks: representation and use of 
knowledge by oomputers". New York: Aoademio 
Press 

Given, To (#d.) 1979. SyntaH & Semantios~ 
volume 12: Oisoeuvse and syntax. New York: 
Aoademio Pcess 

Gcioe, H. P. 1975 "Loglo and oonversation" 
In: Cole & Reagan (eds.), 1979,~41-58 

Hobbs, 3. R. 1982. "TowacdB an understanding 
el ooherenoe in disoouvse". In: Lehnert & 
Ringle (eds.), 1982, 223-243 

Labov~ N. I772o Sooiolin~uistlo patterns. 
Philadelphia: University of Pennsylvania 
Press 

Lehne='t~ |~. & M. H. Ringle (ed=.) 1982. 
Strategies foF natural language prooessing. 
London= Erlbaum 

MoKeown, I(. R. 1985. "Discourse strategies 
for generating natural-language text". In: 
Artifioial Zntelligenoe~27~ I-/,I 

Vaihinger, H. 1935. The philosophy of 'As 
if' -- a system of the theoretioal~ 
praotioal and religious fiotions of mankind. 
London: Routledge & Kegan Paul 

Waohtel~ T. 1985a. "Disoourse stcuotuce". 
LOKI Report NLI-I.I~ University of Hamburg 

Waohtel~ T. 1985b. "Guided speeoh aot 
assignment in 'oan you' utteranoes" 
Unpublished LOKI working paper TW-II, 
University of Hamburg 

Waohtel~ T. 1985o. "Contextual faotocs in 
speeoh aot assignment". Unpublished LOKI 
working paper TW-13, University of Hamburg 
