File Information
File: 05-lr/acl_arc_1_sum/cleansed_text/xml_by_section/abstr/78/t78-1009_abstr.xml
Size: 45,037 bytes
Last Modified: 2025-10-06 13:45:49
<?xml version="1.0" standalone="yes"?> <Paper uid="T78-1009"> <Title>Subsequent Reference: Syntactic and Rhetorical Constraints</Title> <Section position="1" start_page="0" end_page="70" type="abstr"> <SectionTitle> Abstract </SectionTitle> <Paragraph position="0"> Once a_.nn ~ is introduced into a discourse, the form of subsequent references to it are strongly governed by convention. This paper discusses how those conventions can be represented for use by a generation facility. A multistage representation is used, allowing decisions to be made when and where the information is available. It is suggested that a specification of rhetorical structure of the intended message should be included with the present syntactic one, and the conventions eventually reformulated in terms of it.</Paragraph> <Paragraph position="1"> Introduction Whenever a speaker wants fo refer in text or speech to some object, action, state, etc., she must find phrase which will both provide an adequate description and fit the context.</Paragraph> <Paragraph position="2"> What governs her choice? One way to find out might be to look at the selected phrase afier the fact and try to develop a static characterization of the relation between it and its context. This is what most non-computational linguisfs do.</Paragraph> <Paragraph position="3"> However, relations derived fron~ finished texts are at best incomplete. They will not tell us how the choice was made or even guarentee tllat the relation(s) was apparent w.hen the choice had to be made.</Paragraph> <Paragraph position="4"> To get a dear picture of what people know about making references, we have to focus our attention of the process that they 8_,o through. It must involve making decisions on the basis of some contextual evidence. What is the evidence? How and when is it computed? How is it described? Is the decision of what phrase to use made all at once or as a gradual refinement? How is this process interleaved with the larger process of constructing the rest of the utterance? This report describes research done at the Artificial Intelligence Laboralory of the Massachusetts Institute of Technology. Support for the laboratory's artificial intellience research is provided in part by the Advanced Researc'h Projects Agenc:y of the Department of Defence under Office of Naval Research contract N00014-75-C-0643.</Paragraph> <Paragraph position="5"> We can narrow tile research problem by. distinguishing two kinds of references: initial and subsequent. This classification divides instances of reference by their position in a discourse. &quot;Initial&quot; references introduce new entities into the discourse, while &quot;subsequent&quot; references are another mention of one already introduced.</Paragraph> <Paragraph position="6"> An inilial reference must be an encompassing enough description of the new entity that the audence will be able to recognize it, This requires matchin 8 goals with evidence from a model of what the audience is likely to already know and how likely ttley are to understand various choices of wording (e.8. which of its properties should be emphasized? - why is it being introduced?). This is not easy. People talking or writin 8 about unfamiliar things or to unfamiliar audiences are not particularly good at it.</Paragraph> <Paragraph position="7"> Subsequent references are another matter. They are very highly grammalisized. Willie an initial reference may take almost any form: noun phrases with unrestricted numbers of adjectives and qualifying phrases, nominalized clauses, verb phrases (for actions), etc., subsequent references must use very specialized forms: personal, reflexive, and personal pronouns; special determiners like &quot;this&quot; or &quot;my&quot;; class nouns like &quot;thing&quot; or &quot;one&quot;; and so on. Here, grammatical convention dictates most decisions and leaves only some details to free choice.</Paragraph> <Paragraph position="8"> C/.= My observations in this paper are based on experiences with a program for generating English texts from the 8oal-oriented, internally represented messages of other programs. My program, and the state of the art in general, can deal much better with the representation of a grammar than with then representation of an audience model. Hence the focus here on subsequent references.</Paragraph> <Paragraph position="9"> The next section looks at the course of the whole generation process as my program models it, and fits the sub-process of finding phrases fol: references within it. Then the process of deciding whether or not to use a pronoun wig be examined in some detail. This will lead to the problem of accessing audience models and the idea that the relevant infor,~nlion should be computed oulside the linguistic conslruclion process per 5e. Thal idea is expanded to include &quot;rhelorical structures&quot; like the relation &quot;all of a set&quot; that leads to a phrases like &quot;...a square .... the other square&quot;. Finally, a design? for lhis rhelorical slruclure is sketched.</Paragraph> <Paragraph position="10"> Internal representation Suppose we had a logically minded program that wanted to n~ake the statemenl:</Paragraph> <Paragraph position="12"> People who have worked on language generation have almost un\,ersally factored oul all of lhe program's knowledge of langua~,e into a temporally and computationally distinct component. Once lhe resl of the program has compiled a description of what it wanls to say ~ like the formula above it passes it off to its &quot;linguistic generation component&quot; and lets it come up with the actual text.</Paragraph> <Paragraph position="13"> 13ul before moving on to that component, let us look closer at this formula. I am presuming lhal the speaker's primary (non-linguislic) represenlalion, be il predicate logic, semanlic net~, or whatever, uses a lotally unambiguous style of represenlalion - son~elhing equivalent Io always referin8 to an ol)jecl, elc. by its unique name. For example, the three &quot;x&quot;'s in the formula all denote lhe same object (albeit local). The two predicates, the quantifier and the irnplication sign all denote different ol)jecls.</Paragraph> <Paragraph position="14"> We usually think of objects - noun phrases - as being the only lhings lhal mighl be refered to more lhan once, but thal is nol the case. Consider the formula mortal(Romeo) ^ mortal(Juliet). Thal could' be rendered in any of several ways including: &quot;Pomeo is mortal and so is Jufief&quot;. Here lhe second instance of mortal() was realized by a special, highly restricted grarm,~atic device - exaclly lhe characteristics of a &quot;subsequent reterenC/e&quot;. From lhe point of view of the language generation componenl, lhe imporlanl lhing will be lhe repetition of some nan~e l'rom lhe input formula not, at first glance at leasl, the kind of object lhal name denotes. (&quot;The set of descriptive formula~ supplied to the linguislics component is called the pro\[~ram's &quot;message&quot;. Subformulas or terms within a message are called &quot;elet,ents&quot; or &quot;msg-elmls&quot;.) The internal objects lhal appear in a speaker's descriplions will have defining and incidenlal properlies associaled wilh them which are accessible through their names.</Paragraph> <Paragraph position="15"> This will include a property (aclually a packet of properlies and procedures) which records what the program knows about realizing the object as an English phrase. \] refer to this prop~,rty as the object's &quot;entry&quot; - as in an entry in a h'anslatin~, diclionary. ,An enlry specifies what are the set of possihle English phrases that could be used for the object, and includes a set of conlexl sensitive tests that will indicate wl~ich phrase to choose. Breaking down the speaker's &quot;how to say il&quot; knowledge inlo such small chunks facililates the use of a ~eneral recursive process for turning messages into texts by following the compositional structure of the formula(s) from top to bollom.</Paragraph> <Paragraph position="16"> Besides pointing Io permanent properties, a objecl's name will also be the reposilory of more or less temporary annotalions. In parlicular, when the generation component realizes an instance of an object as phrase, it can add an annotation to it markin~ what kind of phrase was selected, where in lhe text this occured, whal the immediately cJominaling clause was at the time, and so on. The next lime there is an instance of that same object the annotation can be found and used Io help decide whal kind of subsequent reference should be made.</Paragraph> <Paragraph position="17"> Before the linguistic processing is begun, is it possible to exmnine the input formula and delermine what subsequent references it will educe? The bound variable x appears three tirnes, once with the quantifier and once with each predicate.</Paragraph> <Paragraph position="18"> it would he a. candidate for some subsequent references ifpin facl, the formula was rendered into English literally.</Paragraph> <Paragraph position="19"> &quot;For any thinE. , if that thing is a man, then it is mortal.&quot; Rut other, more fluent, renderings of that formula will not give the x's a separate status: &quot;E~cinF. a man implies beinE, mortal&quot; &quot;All nlen are mortal&quot; in shorl, it is not possible 1o predict which objects will be e~plicilly refered to and which not jusl on the basis of a formula in the inlernal representation language. You would have to know (1) how lhe terms that dominate the object in the formula are going to be renclered; and (2) whether the object was rnenlioned earlier in lhe discourse and how it was described there. Then you would still have to, in effect, duplicate lhe reasoning process that the generation component would 8o lhrough ilself.</Paragraph> <Paragraph position="20"> A ~, we will see later, lhe generation component will often need &quot;advice&quot; as to whether or nol the audience would understand certain phrasings. &quot;The audience model which makes these decisions will presumably prefer to work from pre-calculated observations so as to avoid delay. The implication ol the tact that you cannot whelher that there will be a subsequent reference to a parlicular object until it actually happens is thai you cannot make special preparations for it. The audience model, or any other effected part of the program, will have to be generally prepared for whatever objects might be asked about.</Paragraph> <Paragraph position="21"> The possibility of three different renderings for the same formula implies that the formula per se does not contain enough specification to pick out just one of them. If you consider the three sentences for a moment, you will appreciate that what distinguishes them are differences in rhetorical emphasis and in how to interpret Vx. These are things that Frege deliberately omitted from the predicate calculus. To direct the generation component so as to arrive at a particular one of those sentences, more formulas would have to be added to the message or else found in the larger context (e.g. the formula mighf be part of a proof), and the entries for quanlifiers, implication, etc. would have to. be augmented to notice ther,~.</Paragraph> <Paragraph position="22"> Upgrading the predicate calculus enough to motivate the use of fluent English is a facinating problem, but one which 1 will ~loss over in this paper. See McDonald \[1978a\] for more details. For now, l will assume that the decisions made by the various entries come out 'so as to give the literal version of the formula with the explicit references just so that we can use it for an example.</Paragraph> <Section position="1" start_page="64" end_page="70" type="sub_section"> <SectionTitle> Syntactic Context </SectionTitle> <Paragraph position="0"> Below is my program's representation of the situation just as it is about to choose a phrase for the third instance of x in the formula. The point of showing this constituent structure is to demonstrate that while the program has a great deal of data to bring to bear on the choice, it also has a great deal of data which is utterly irrelevant to it. The packaging of the data the size of the search space - is at least as important as having the data available in the first place.</Paragraph> <Paragraph position="1"> clause1 \[int ro\] \[clause\] clause 4 \[prep\]\[obj\] \[intro\] \[clause\] for rip__3 I- coord. &quot;if&quot; I- coord. &quot;then&quot; ...f~ --,, clause5 clauseg.</Paragraph> <Paragraph position="2"> \[(:let \]\[head\] _~ .... ~ / -~&quot; any thin E \[subj\] \[pred\] \[subj\] \[pred\] vC/9_7_._, x mortal() \[det\]\[head\] \[vg\]\[pred-nom\] that timing be n p_8 \[det \]\[head\] a man in lime diagram, the names of grammatical categories: clausei, pp, etc., denote the syntactic nodes of an annotated surface structure. Each node has a set of immediate constituents, organized by a list of named constituent slots. A slot can be empty, hold another node, hold a word or idiom, or hold an element of the input formula which has yet to be processe~, e.g. x, or mortal(). The words at the leaves of the tree are given in their root form. A morphology subroutine specializes them for number, lense, etc. when they are spoken (printed on the console).</Paragraph> <Paragraph position="3"> The choice of what syntactic categories, descriptive features and constituent slots to maintain is tied up with the choice of actions associated with them by the linguistics component. The \[intro\] constituent, for example, will act to insure lhat any introductory clause is realized as a participle. There are many trade-offs involved in the design of this grammar, and I will again gloss over them for this paper. The choice of refering phrase for a subsequent reference is determined largely by the syntactic relationship between the current instance and the previous instance to the same object. |n a static, after the fact analysis, we would determine this relationship by examining their positions in a tree like the one above. This is a simple enough operation for a person using her eyes, but it is an awkward mark and sweep style search for a computer program.</Paragraph> <Paragraph position="4"> My program uses a much more efficient, and |would say more perspicuous approach based on recording potentially relevant facts at the time they are first noticed by the linguistics component The wording of the heuristics that are used for the decisions are similar to the wordings used in static analysis. (They almost have to be, given that that is how the bulk of linguistic research has been done to date.) But the data for the heuristics is acquired in a more natural manner. Before discussing lhe program actual pronominalization heuristics, I will first digress (o describe the workings of the generation process which collects (and creates) the data. Tile tree in the previous column was developed incremenlally. Clausel is the result of realizing the conceptually topmost part of the input formula - the quantification, its argument - the implication - was then positioned in the new syntactic structure but not yet realized itself. This is what the constituent tree looked like at that point.</Paragraph> <Paragraph position="5"> clause! \[intro\] \[clause\] 1--~PE'~g man(x) ~ mortal(x) for x All of the generation components actual knowledge is spread about many small, local routines: dictionary entries for the object that will appear in input formulas; &quot;realization strategies&quot; - the construction routines that those entries execute to implement their decisions; or &quot;grammar routines&quot; - null associated with the names of categories or constituents and in charge of effecting conventional details not involved in conveying rneanin 8. These routines are all activated and organized by a simple controller.</Paragraph> <Paragraph position="6"> The controller works by walking the constituent tree, top down through the syntactic nodes and from left to right at each level of constituents, The process begins with the top node of the tree just after it is built by the entry for the the topmost element of the input formula.</Paragraph> <Paragraph position="7"> Outline of the Controller Examine-nocJe (l) call tlme grammar routine for this category node (2) rebind the node recursive state variables (3) call Examine-constiluenls Examine -constituents - For each consliluenl slots of the current node in order do: (i) call the grammar routine for thai slot name (2) call Exaraine-slol-conlents Examine-slot -conlents - Cases:</Paragraph> <Paragraph position="9"> call the morphology subroutine with the word print lhe result conlenls = <node> call E~amine-node conlenls = <msg-elmt> use the dictionary entry for the element to find a phrase for the element; replace the element wilh that phrase as the contents of the slot; loop lhrough the cases again.</Paragraph> <Paragraph position="10"> So, having generated clause2, in effect by starting the controller on the last case of Examine-slot-contents, the conlroller will loop around. Time contents will now be clause2; the lhird case will be taken and the clause &quot;entered&quot;. Its first constituent conlains another node; lhe controller recursively re-enters Examine-node and enters time prepositional phrase. Ils first constituent contains time word &quot;for&quot;, which is immediatedty printed out wilh no changes from the morphology subroutine; the second contains the first instance of x which is processed with the dictionary entry common to &quot;issolated variables&quot;. The noun phrase it constructs replaces the x in the constituent tree; the controller then loops thrQugh the cases once more, recursively calling Examine-node on NP3. \]t is now three invocations deep. The dolled line shows its path.</Paragraph> <Paragraph position="12"> spoken: &quot;For any thing, &quot; After processing np3, the controller will leave lhe np and thepp, gO to the next constituent of clause\], use the dictionary entry for implications, and so on, et cettera.</Paragraph> <Paragraph position="13"> The design of this generation component is oriented around the decision making process of the dictionary entries (see \[McDonald 1978b\] for more discussion). The principle reason that the process is deterministic and indelible, for example, is to simplify the conditions that the entries will have Io lest for. A more relevant example here is the use the controller to &quot;pre-calculate&quot; certain relations about the context and make lhem available through the values of recursive stale variables mainlained by Examine-node. For example, the controller keeps pointers to the &quot;current-main-clause&quot;, &quot;current-verb-phrase&quot;, etc.. \]l keeps track of whether it is in a subordinate context, of what the last constituent was, last sentence, and so on.</Paragraph> <Paragraph position="14"> Any of lhese relations could be calculated independantly I~y directly exarninin~ the form of the constituent tree and the annotalions on its nodes and embedded message elements. But the point is more than just efficiency. By maki.ng certain relations readily available and not others, one says that just those relations are the important ones for making linguistic decisions. A one of a kind operation like subject-verb agreement will have a special predicate written for it that &quot;knows&quot; where to find the relevant subject constituent in the constituent tree. But relations that are often Used, particularly those needed for evaluating pronominalizalion, are maintained by the controller, and, as a corollary, are only available in their pre-compuled form when the controller is present at that point in the tree.</Paragraph> <Paragraph position="15"> The design of the controller guarentees that the generation process will have these properties: (1) \]t is done in one pass - the controller never backs up. (2) Therefore decisions, choices of phrasing, must be made correctly the first time. (3) It is incremental. When the first part of the text is being printed out, later parts will be in their internal form. (4) Therefore very specific facts about the linguistic characteristics of earlier parts of the text are available to influence the decisions made about the later parts. (.5) \]n particular, when the time comes to render any particular n~essage element into English, the entire text up to that point will have been generated and typed out to the audience.</Paragraph> <Paragraph position="16"> Heuristics PSor deciding to use a pronoun Virtually any element in a .message could be potentially realized with a pronoun. Accordingly, the heuristics for judginB if a pronoun should be used are abstracted away from the elemenls' individual dictionary entries into a common subroutine. Call it &quot;pronoun?&quot;. Pronoun? operates like a predicate. Eitl~er it finds lhat a pronoun can be used and returns it, or else it relurns nil and the msg-elmt's entry is consulted Io construct a full phrase.</Paragraph> <Paragraph position="17"> By the lime the coniroller reaches the third instance of x in tl~e example, it will have already passed through and processed the earler two instances. Rather than look back through the tree to find lhem, pronoun? will consult a stored record lhat describes their situation. Below is a blowup of part of the controller, showing more of what happens when a message element is processed.</Paragraph> <Paragraph position="18"> Examine-slot-contents ,.. earlier cases...</Paragraph> <Paragraph position="20"> use its dictionary entry i add <msoo-elmt> to discourse-list; I ', lake ts discourse record f ................. &quot;I replace <msg-elmt> with phrase; , loop through cases again i ................................ .__i The discourse-list contains the names of all of the internal elements that have been mentioned so far in the discourse. |f this example message had been the start of the discourse, the contents of discourse-list would be: (man(), .-), X, V) The need for a subse~iuent reference is indicated by the name of tlle message element already being on lhat list when the controller reaches an instance of it in the consitituent tree. After the generated phrase is returned by whatever source, Ihe context of the original msB-elmt and facts about the new phrase are recorded as a special annotation kept with the name of the element. This discourse record is a vector of just those properties which, from the point of view of later routines such as the pronominalization heuristics, are sufficient to characterize that instance of the message element in the discourse. These are the vectors currently created for the first two instances of &quot;x&quot;. How the different items are used is given later.</Paragraph> <Paragraph position="22"> slot \[sub j\] bec arne np strategies-used ( det<-that head<-lhing ) The heuristics governing the use of a pronoun are evahJated in staBes according to how much trouble the proBram must 8o through inorder to Bet the information it needs.</Paragraph> <Paragraph position="23"> First come the &quot;quick checks&quot;: predicates that can be evahJated just on basis on the candidate msg-elmt and the immediate, controller defined linguistic context. These include: Ca) is the rnsE-elrnt on the discourse-list? (b) is it the token for &quot;me&quot; or &quot;you'deg? (c) has it been already marked for (or against) pronominalization by an earlier grammar routine? (d) is it contents of a predicate constituent or a complement constih~ent Or any other constituent which is never given by a prOnoun? If any of these checks decide that a pronoun can be used, a common subroutine will make the actual choice. Otherwise, the checks either rule out the possibility of a pronoun altogether or the pass the msg-elmt lhrough for a more extensive deliberation.</Paragraph> <Paragraph position="24"> The full-scale deliberation first analyzes the relationship of this instance of the msg-elrrd and the lasl instance by comparing the current context, as given by the status variables in the controller, with the past contexl, as read off the msB-elml's entry in the discourse record. This yields a set of derived, descriptive features which are the inlgut to the actual heuristics.</Paragraph> <Paragraph position="25"> The derived features abstract out details which are irrelevant to lhe heuristics. For example, the current set of heuristics look for last instance having been either a proposition, or a &quot;thing&quot; (i.e. by looking at the became item in its discourse record). Whether a &quot;thing&quot; was actually a noun p ~rase, a nominalized clause, or a trace is all the same to the heuristics. The initial analysis into features makes this lest for was-a-thing, vs. was-a-proposition once and for all and makes it unnecessary for the heuristics tidal refer to this distinction to repeatedly include all of the particular cases. For that matter, it is also unnecessary to rewrite the code for the heuristics every lime there is a new definilion for a feature.</Paragraph> <Paragraph position="26"> Other syntactic features currently computed include measures of relative position like same-simplex, same-sentence, or stale, and proceed-and-command, whihc are computed from the several position indexes in the.record. The record of what constiluent slot the last instance was in, in conjunction with the clause indexes, is used to check for features such * as whether the last instance was the previous-subject. Also, parallel positions within conjoined phrases are noted.</Paragraph> <Paragraph position="27"> Once the list of'features is computed, the heuristics are run. At the moment, they are implemented as simple condilionals. Here again, there can be an immediate yes or no decision, or else a yet more involved process is invoked (see below). The grammar forces an immediate decision when proceed-and-command applies. Olherwise, a number oi heuristics will immediately cause a pronoun to be used if there are no &quot;distraclin8&quot; references 1o other object in that vicinity of the discourse. For example, if the last instance of the object was itself realized as a pronoun, this will cause an immediately decision to use one again.</Paragraph> <Paragraph position="28"> In the ease'of this example, lhe third instance of &quot;x&quot; will be described as: same-sentence, last-subject, was-a.~thing As there are no other similar references in the vicinity to dishact the audience, the heuristics will immediately decide that a pronoun should be used. The subr0uline for computing the correct print name for pronouns is then consulted, and the result, &quot;it&quot; is returned to be inserted in the constituent tree and &quot;spoken&quot; on the next loop of l'he controller. Reasoning about distracting references Except when instance and anaphor are in the same simplex clause, syntactic relations alone are never enough to dictate whelher or not a message element should be pronorninalized. The linguislics component must to be able to tell if there are any other elements with which this one might possibly be confused. The problem is, of course, that the &quot;confusion&quot; will be a semantic or pra~',matic one, i.e. it will be based on cognilive facts about the message elements which the linguistics component, per se, knows nothing about.</Paragraph> <Paragraph position="29"> Given an oracle to tell it which message elements would compete wilh current one for the interpretation of.a pronoun in that position, the linguistics component, can use a simple procedure to decide whether to go ahead with the pronoun, namely to run those other elements through the pronorninalization heuristics as well and see which accumulates tile best reasons for being pronominalized.</Paragraph> <Paragraph position="30"> Consider this example sentence. |magine that the linguistics component has reached the point in brackets and must make the choice whelher to say &quot;her&quot; or &quot;Candy's&quot;. &quot;Candy asAed Carol to reschedule {her, Candy's} meeting for earlier in lhe day&quot; Whether or not two objects will be ambiguous depends on what the audience knows. In this case, an audience that knows who both Candy and Carol are will know that Candy is a graduate student who might well organize a meeting and that Carol is e group secretary, someone who would probably make the arrangements needed for changing a meeting's time. For such an audience, it would be not at all confusin 8 to say &quot;her meeting&quot;. An audience lhat didn't know who they were however would at best be confused and would in fact probably make the wrong choice.</Paragraph> <Paragraph position="31"> This kind of information is much too specific to imagine encoding as part of general purpose dictionary entries. But because of the general unpredictability al the message level of whether an objecl will have subsequent references made to it in lhe eventual text, the linguistics component will have to make its query to the main program &quot;oracle&quot; at lhe very last minute as part of pronominalization heuristics.</Paragraph> <Paragraph position="32"> The oracle will presurnably be some kind of audience model. But for present purposes, we can think of it as a function that takes lhe object we are inlerested in (&quot;Candy&quot;) as its argument and returns a list of those objects lhat appeared in lhis and recent messages which the audience might confuse with it. So, in this case, if the audience knew Candy and Carol, then the oracle would return a null list, and the pronominalization option would go through. If they didn't know them, then it would return &quot;( Carol )&quot;, and a further rouncl of heuristics would be tried.</Paragraph> <Paragraph position="33"> To compare the relative &quot;pronominalizability&quot; of several messaoe elements, Pronoun? runs them separately through the analysis and evaluation procedure. But instead of acting on the evaluation direclly, il makes a list of the names of the individual heuristics that each passes and then compares the two lists. In the current program these would be: \]n this case, the relative number of heuristics alone would indicate lhal Carol would make a &quot;belier&quot; interpretation for a pronoun in lhat position, and that, therefore, the possibility of a using a pronoun for Candy should be rejected. But actually, the different heuristics are given weightings. Same-simplex, for exarnpfe, is much better evidence than same-sentence.</Paragraph> <Paragraph position="34"> Non-pronominal subsequent references Every subsequent reference is first checked for the possibility of using a pronoun. If this check fails, a summary vector of lhe features analysed and of heuristics passed and failed is passed along to the message element's dictionary entry. Entries may have their own idiosyncratic procedures for dealing with these situations, but they may also make use of general procedures packaged by the grammar.</Paragraph> <Paragraph position="35"> As explained in \[McDonald 1978b\], the &quot;thinking&quot; part of a dictionary entry consists of a set of &quot;filters&quot;, which, if their condilions are met, will execute one or more &quot;realization strategies&quot; which assemble the phrase or modifer that the filter set decided upon. Because entries are not evaluated directly but instead are interpreted, it is possible for the interpreter to dynamically add or subtract filter se~s according to the grammatical (or rhetorical - see below) circumstances.</Paragraph> <Paragraph position="36"> One of time more common reasOns for rejecting the use of a pronoun is that it might be missinlerpreled as refering to some other object. The form of subsequent reference eventually choosen in these cases must distinguish the object from the one it is potenlially ambiguous with, but does not have to recapitulate any more delail.</Paragraph> <Paragraph position="37"> In parlicular, one frequent pattern for an initial reference is a noun phrase with the name of a class of objects as its head word, with a series of adjectives, classifiers, or qualifying phrases surounding it. There is a simple formula for constructing a non-pronominal, subsequent reference to follow this kind of NP, namely !o repeat the class name as the head word and use either &quot;that&quot; or &quot;the&quot; as a determiner. Part of an element's discourse record is a list of the realization slrategies that were used in the construction of previous phrases. This is a technique for smoothing over the irrelevant detail of the actual phrase that what used. As the realization strategies are refered to by name, can be annotated with properties describing what they do, and entered into abstraction hierarchies, Routines that have to think about what other routines have done or might do can do so at whatever level of generality is appropriate. In particular, lhis is a way to describe patterns of noun phrase construction so that I~eneral purpose filler sets can recognize them.</Paragraph> <Paragraph position="38"> The initial references pattern above is recognized by a filter set thai the entry interpreter can add. The filter's predicate checks for the name of the realization strategy head<-classname being included as one of the &quot;strategies-used&quot; of the anaphor, if it is found, this filter set will lake precedence over any others in the entry. The filter set's action wilt assernble a new noun phrase with the same class name as used for initial references (it is recorded with the entry), and either the or thai as the determiner depending on a heuristic rneasure of the distance between this instance and the last. This is time process operating in a sentencelike: &quot;There is room for a block on a surface iff that surface is a table or has a clear top.&quot; Subsequent references to the same kind of object The controller makes only one pass through constituent tree, turning internal, messa=oe level structures into linguistic .~.tructui'es as it passes. While time amount of information available for material behind time controller is limited only by how much annotation lhe designer cares to record, material in front of the controller is only megerly described. The (potential) linguistic properties of an object embedded in the constituenl tree in front of lhe controller can be explored to a limited extent by &quot;queryinl~&quot; its dictionary entry. However, this is limited as a practical mailer because the interveening lext has not been finished and any fillers in that entry which depended on lime discourse contexl will be undefined.</Paragraph> <Paragraph position="39"> This means thai if you want the realization of two separated objects 1o be coordinated, the coordination has to be planned for well in advance and somehow marked.</Paragraph> <Paragraph position="40"> Otherwise the first object will be realized freely, since it would not be able to &quot;see&quot; that there is even a second object presenl. Time phrases below are examples of where coordination is required. (The first two are from the tic-tac-toe talking program of \[Davey ,1.974\]. He used special purpose routines to handcrafl the pairs.) &quot;...my edge and ),'ours...&quot; &quot;...a corner ...the opposite one...&quot; &quot;...will enclose X's in square brackets and Y's in angle brackets&quot; &quot;...a big block and a littleone&quot; In each of these cases, the two objects were both of the same &quot;sort&quot;: edges, corners, brackets, or blocks. By the usual criteria, this would mean that they share di'ctionary entries, and, indeed, the paired phrases have much in common, and could be seen as only differing in the choice of strategy for their adjectives and/or determiners. This means that the coordinating mark must be something other than the &quot;kind-of&quot; poinler thai links objects with their entries. It will also prohably have to be a lemporary structure, since &quot;the oppo~;i/e corner&quot; is a transient phenomena, defined only at particular moments in each came of tic-tac-toe.</Paragraph> <Paragraph position="41"> The simplest way 1o mark the pairs is with an additional formula in the inpul message, e.g.</Paragraph> <Paragraph position="42"> (all-of-a-set cornerl cornerg) or (contrast-by-size B6 B3) When the message is initially processed, formulas like these are indexed by their arguments so lhat, e.B., lhe dictionary entry for blocks will be able to notice them and choose its strategies accordingly.</Paragraph> <Paragraph position="43"> Indicators like all-el-a-set are a part of the common grammar, and operate in the same way that the earlier filter set for subsequent references by classnames does. The dictionary entry inlerpreter keeps track of the arguments to the formula and when time last of tt~em is being processed, it &quot;inlerupts&quot; and preempts the choice of determiner to insure that it is the, indicating lhal the speaker intends for the audienC/e to appreciate lhat there is no other corner (or whatever) left. (This is a simplification.) Rhetorical context Rhetoric is the arl of persuasion \[Aristotle\]. Stylistic variations in ordering, word choice, use of function words, elipsi~, etc. are potenfially rhetorical techniques, if the speaker program (or rather its designer) knows when their use would have a parlicular desired effect, i.e. when their use would make lhe text more persuasive.</Paragraph> <Paragraph position="44"> The rhetorical conlexl will typically be just an additional pararneler to be noticed by the enlires and ~rammalical routines. The dimension that it adds, however, greatly increases lhe fluency of lhe linguistic component's output. The only problem is that rhetoi'ical phenomena have not been studied much at all - they have been sweep under the rug of &quot;stylir.tic variations&quot;.</Paragraph> <Paragraph position="45"> Goals about !low to express lhe message's content can be specified in lhe message. They will have their own dictionary entries and end up determining part of the rhetorical context thal accompanies the syntactic context. (At this wrilini~, the details of lime slructure of the rhetorical context are still being implemented. What follows is a skelch.)Consider: All of the pronorninalizalion heuristics menlioned earlier were based on syntactic relations. However, there are other relalions governing lhe understanding and generation of texls, which have to do with their &quot;rhelorical&quot; or &quot;discourse&quot; structure, hl particular, each region of text will have a focus loosely speaking lhe objecl or action lhat lhal text is &quot;about&quot; (see \[Sidner 1978\] for an elaboration).</Paragraph> <Paragraph position="46"> Pronominalization of subsequent references Io the focused object is almost always obligatory. (There can be exceptions if time last several references to the object were pronominalized, and time intention is to &quot;refresh&quot; the audience's memory.) In the example witll &quot;Candy&quot; and &quot;Carol&quot;, if the previous part of the discourse had been saying thinl~s about Candy, then she would have been established as the focus of that sentence. Then the presence of a current-focus heuristic in Candy's list of sucessful heurislics would have outweighed all of the syntactically based heuristics in Caters list and the pronoun would have been used.</Paragraph> <Paragraph position="47"> The only question is how to mark and monitor focus or any other rhetorical indicator. It is not a natural or even consistantly definable part of a syntactic constituent structure. TI-&quot;&quot;afore it will have to be &quot;tacked on&quot; somehow. The te,::mique |am experimenting with is to implement a focus &quot;register&quot; which is explicitly set and reset by any dictionary entries lhat effect focus. A new message could also effect the focus register via an explicit directive included with it - say, when the topic of conversalion is being changed. An explicitly dictated focus would cause the linguistics component to &quot;lran.~.form&quot; time realization of the conlent parts of the message to insure that time new focus is properly marked as such by the syntactic form of the text.</Paragraph> <Paragraph position="48"> Time rhetorical conlext could be very domain specific.</Paragraph> <Paragraph position="49"> Consider the sentence: &quot;The black queen can now take a pawn.&quot; Notice that it is not necessary to say &quot;a white pawn&quot; because of the irnmediale inference that one makes about what pieces it is legal for a piece of a g, iven color to &quot;take&quot;. Since the criteria for conslructing a relating expression for any chess piece will overlap, they wilt likely share a dictionary entry. Thus we have a sort of subsequent reference phenomena. The enlry for chess pieces will be Iookin8 for the mention of a piece'S color earlier in lhe text. If it finds one, or rather if it finds one of the complementary color, and if the situation is right, it can omit any mention of color from the phrase it has assembled.</Paragraph> <Paragraph position="50"> How to determine that the situation is &quot;right&quot; is a matter for the rhetorical conlext to specify. The problem is the color of contrasting piece can be omitled only if the choice of verb or some other device indicales that, in fact, a constrastin 6 conlexl is presenl. But there are too many suitable verbs to imagine listing them in the entry and explicitly looking for lhern.</Paragraph> <Paragraph position="51"> 7t h~stead, lhe rhetorical context will include a list of &quot;relations&quot; tha! currently hold. What relations there should be is a matter of the rhetorical roles lhat different parts of a me.'..s~se mig,ht play and whether the recog,nition of these roles by the audience could be facilitated by a choice of wording, (i.e. it is a matter of research and experiment). FOr a program that talked about chess g,ames, one of these relations would be: opposing-pieces</Paragraph> <Paragraph position="53"> To decide whether to include the name of a piece's color, the entry looks 1o see if there is an opposinl~-pieces relation holdin8 at lhe moment. If there is, it looks to see if its piece is part of the relation and whether it is the second of the two to be mentioned. If so, it omits the color name.</Paragraph> <Paragraph position="54"> The power of this representational technique is that it compiles its record of the needed facts at the time when they easily determined, i.e. as the messag,e is being, compiled, welt before the relation name has been rendered into Enslish and the simplicity of the relation obscured.</Paragraph> <Paragraph position="55"> This technique should be applicable to many more phenomena titan simply subsequent reference. Consider sentences like these: &quot;Briall also wants to come to the meeting.&quot; &quot;Mitch as a class then and so does Beth.&quot; &quot;The meetin~ might run overtime, but I don't expect it.&quot; The underlined words are not a part of the &quot;literal&quot; content of those sentences. They represent rhetorical relations between parts of the sentence or between the sentence and earlier parts of the discourse.</Paragraph> <Paragraph position="56"> |f the source messag,es for those sentences described only their literal content, it would be impossible to motivate the use of also, so, or but in those ways, yet they are what g,ive the sentences their naturalness. But if those rhetorical relations are inchJded as part of the linguistic context, with their links to specific phrases and dictionary entries, including these &quot;little&quot; words becomes simple.</Paragraph> <Paragraph position="57"> Language Generation&quot; in the proceeding,s of the 2d Annual Meeting, of the CSCSI/SCEIO, Toronto, Canada, July 19-21, 1978.</Paragraph> <Paragraph position="58"> Sidner \[1978\] &quot;The Use of Focus as a Tool for Disambiguation of Definate Noun Phrases, this volume.</Paragraph> </Section> </Section> class="xml-element"></Paper>