On Discourse relations, rhetorical relations and rhetoric 
Candace L. Sidner 
DEC-Cambridge Research Lab 
One Kendall Sq. Building 700 
Cambridge, MA 02139 
email: sidner@crl.dec.com 
Discourses are the collaborative activities of 
(human) agents who have purposes for commu- 
nicating. Discourse structure includes the pur- 
poses of those agents, which I take, following 
\[GroszSid86\], to be formally expressible as inten- 
tions and beliefs. 
While the theory of discourse structures has in- 
fluenced how many computational linguists think 
about discourse processing, it does not preclude 
careful consideration of rhetorical function in dis- 
courses. Nor does it settle the question of how 
intentions are conveyed by particular utterances 
in particular genres of discourse. 
In recent research I have been studying dis- 
courses that occur when people communicate 
about their collaboative activities. These people 
are collaborating not only to make the discourse 
happen, but to get something done together in the 
world. Following on the model of SharedPlans in 
\[GroszSid90, GroszKra93\], I have asked, how is 
it that agents use language to come to hold the 
beliefs and intentions specified by the SharedPlan 
model as necessary for successful collaboration? 
Using naturally occurring conversations of human 
agents collaborating, I have observed that their 
discourses cycle through a series of proposals, re- 
jections, assents, counters, modifications and re- 
tractions. 
To clarify this observation, I have devised an 
artificial language of negotiation \[Sidner92\] whose 
sentences are messages containing proposals of 
propositions, rejections of propositions, etc. The 
semantics of these messages is specified in terms 
of beliefs, especially mutual belief, and intentions 
that the discourse participants come to hold about 
the propositional content of the message. Along 
with the language is an "environment" for inter- 
pretation that keeps track of accepted, open and 
rejected proposals. Using this language I have cre- 
ated artificial conversations in which the beliefs 
and intentions of the participants are fully evi- 
dent. Such conversations have some of the rich- 
ness of naturally occurring ones, though they lack 
such attentional devices of human discourse as cue 
phrases. They also contain more redundancy than 
human discourse; in the artificial language indi- 
vidual utterances can not serve several functions 
at once, as is very common in natural human dis- 
course. 
I maintain as a working hypothesis that the 
negotiation language can model naturally occur- 
ing discourses as cycles of negotiations. Under 
this hypothesis, the recognition that an utterance 
serves as a proposal as opposed to a counterpro- 
posal, for example, is determined not by the re- 
lation of the utterance to previous utterances. It 
is determined by recognition of beliefs and inten- 
tions conveyed by the utterance and by the cur- 
rent discourse state with respect to beliefs and 
intentions (e.g. which beliefs are not yet mutually 
believed, which are, and which cannot be because 
one discourse participants holds that the belief is 
false); these together indicate how the beliefs and 
intentions of the current utterance operate as pro- 
posals, counterproposals, rejections and the like. 
As a model of human discourse, the negotiation 
language provides a fine-grained model of the be- 
liefs and intentions and relations among them that 
is conveyed in individual utterances. It does not 
eliminate the need for recognizing what role the 
particular beliefs and intentions conveyed play in 
the agents' plans, especially in their SharedPlans, 
and hence plan recognition is still critical. Re- 
cent work by Lochbaum \[Lochbaum93\] provides 
an outlook on plan recognition for collaborative 
activity. 
The negotiation language might appear to be 
similar to relations in RST and other theories be- 
cause terms such as proposing, counterproposing 
and rejection seem similar to, for example, Mann 
122 
and Thomson's evidence, antithesis and conces- 
sion relations. The distinctions may be clari- 
fied by first noting that the general term "dis- 
course structure relations" is ambiguous. Re- 
lations might be between utterances or utter- 
ances and segments (i.e. elements of the linguis- 
tic structure), between constructs of attentionai 
state or between those of the intentional struc- 
ture \[GroszSid86\]. lIST, Hobbs' theory and the 
McKeown schemas \[Manntho87, Hobbs79, McKe- 
own85\] are all relations among parts of linguistic 
structure. The dominance and satisfaction prece- 
dence of the Grosz and Sidner theory are rela- 
tions among constructs of intentional structure. 
In \[Moorepar89\] work, PaST is used to organize 
and enact the intentions of the speaker, as well as 
to maintain a model of how portions of the text 
are related to each other. Because the negotiation 
language concerns relations among belief and in- 
tentions, it is an example of relations among inten- 
tional structure. Both this language and the use 
of R.ST in Moore and Paris' work suggest that cer- 
tain aspects of rhetorical relations are captured in 
the beliefs and intentions conveyed in utterances 
in combination with the state of the discourse. 
The negotiation language viewpoint however 
does not critically address the issue of rhetori- 
cal function in part because it is not clear what 
aspects of discourse behavior one wants to claim 
must be addressed by rhetorical function. What is 
the role of rhetorical function or rhetorical knowl- 
edge in discourse? What aspects of discourse must 
be accounted for by rhetorical function? While 
rhetorical relations like those of RST have been 
useful in the generation systems of McKeown and 
the ISI systems, no one has claimed that the recog- 
nition of these relations is essential for the inter- 
pretation of discourse; many researchers do accept 
the view, originally propounded by Austin, Searle 
and Grice, that intentions and beliefs conveyed in 
utterances are intended to be recognized. 
Do rhetorical relations or other textual relations 
concern rhetorical knowledge? Or are they mis- 
named, so that the term linguistic structure rela- 
tions is more apt? Rhetorical function concerns a 
different aspect of communication than the recog- 
nition of intention, namely the affective one. By 
this I mean the role of an utterance in evoking in 
the hearer or reader some change of state (includ- 
ing an emotional one) that the hearer or reader 
does not necessarily recognize; often affect is less 
than successful if the hearer is aware of it. In 
classical tradition, which extends back to Aris- 
totle's view of rhetoric, rhetorical function con- 
cerns the art of persuasion; in more recent times, 
rhetoric is the art of social control and motivation 
through communication. Hovy's Ph.D. \[Hovy89\] 
work can be seen as an experiment in rhetorical 
function. His PAULINE system can present an 
event from several different points of view, de- 
pending on, among other things, the goals for in- 
fluencing hearer's opinions; Hovy's system is not 
concerned with the hearer recognizing what is go- 
ing on. Research by Cahn \[Cahng0\], addressesing 
the automatic synthesis of utterances with affec- 
tive mood (e.g. utterances that sound happy or 
sad or angry), demonstrates that affect may be 
carried at the most fine grained level of communi- 
cation. 
Both rhetorical theory and intentional theories 
deal with a discourse participant coming to hold 
a belief on the basis of utterances from another 
participant. Modern rhetoric (especially in adver- 
tising) concerns itself with causing the participant 
to do something (such as buy a certain product), 
a concern not entirely unakin to intending that 
another perform an action \[GroszKra93\]. It is 
only rhetorical theories that address the means 
of achieving these ends by affect on the hearer, 
either with or without the hearer recognizing it. 
It is unclear to me whether Hobbs, McKeown or 
Mann and Thompson intended their relations to 
operate rhetorically in the sense described above. 
If the relations were not so intended, then they 
may continue to provide the kind of organizing 
framework they have played in generation sys- 
tems without having a parallel role in interpreta- 
tion systems. And if they were not, then rhetori- 
cal function is a matter computational linguistics 
might still need to address. Because rhetorical 
function is one of affect on the hearer, it may be 
valuable to generation systems, which must plan 
for the affect of utterances on discourse partici- 
pants, the force of utterances in persuasive activ- 
ity, and perhaps social aspects of discourse partic- 
ipants. Rhetorical function may also be useful to 
the interpretation of discourse. One might want 
to consider how to build systems that are sen- 
sitive to the affect of utterances (or perhaps not, 
since it might be easier to have computational con- 
versational partners that do not respond to such 
matters). Rhetorical function does not yet seem 
critical to many researchers in computational lin- 
guistics, but a better understanding of its role in 
discourse may clarify issues of this workshop. 

References
\[Cahn90\] J.E. Cahn. Generating Expresion by 
Synthesized Speech. M.S. Thesis. MIT. Cam- 
bridge, MA, 1990. 

\[GroszSid86\] B.J. Grosz and C.L. Sidner. At- 
tention, intentions, and the structure of discourse. 
Computational Linguistics, 12(3), 1986. 

\[GroszSidg0\] B.J. Grosz and C.L. Sidner. Plans 
for discourse. In P.I~. Cohen, J.L. Morgan, and 
M.E. Pollack (eds.) Intentions in Communication. 
MIT Press, 1990. 

\[GroszKra93\] B.J. Grosz and S. Kraus. Collab- 
orative Plans for Group Activities. submitted to 
IJCAI93. 

\[Hobbs79\] J. Hobbs. Coherence and Co- 
reference. Cognitive Science. 1:67-82, 1979. 

\[Hovy89\] E.H. Hovy. Pragmatics and Natural 
Language Generation. Artificial Intelligence. Fall 
1989. 

\[Lochbaum93\] K.E. Lochbaum. A Collabora- 
tive Planning Approach to understanding Subdi- 
alogues in Conversation. Submitted to IJCAI-93. 

\[Manntho87\] W.C. Mann and S.A. Thompson. 
Rhetorical Structure Theory: A Theory of Text 
Organization. in L. Polanyi (ed.) The Structure 
of Discourse. Ablex Pub. Corp, 1987. 

\[McKeown85\] K. 1~. McKeown. Text Genera- 
tion. Cambridge Univ. Press, 1985. 

\[Moorepar89\] J.D. Moore and C.L. Paris. Plan- 
ning Text for Advisory Dialogues. Proceedings of 
the 27th Annual ACL meeting, 1989, pp. 211. 

\[Sidner92\] C.L. Sidner. Using Discourse to Ne- 
gotiate in Collaborative Activity: An Artificial 
Language. AAAI Workshop on Heterogeneous 
Agents, 1992. 
