File Information
File: 05-lr/acl_arc_1_sum/cleansed_text/xml_by_section/metho/88/c88-2119_metho.xml
Size: 36,552 bytes
Last Modified: 2025-10-06 14:12:05
<?xml version="1.0" standalone="yes"?> <Paper uid="C88-2119"> <Title>A New Strategy for Providing Definitions In Task-Oriented Dialogues</Title> <Section position="3" start_page="0" end_page="0" type="metho"> <SectionTitle> 2 Definition Situations </SectionTitle> <Paragraph position="0"> In its simplest form, a definition-giving dialogue consists of an information-seeker asking &quot;What is an Xf&quot; and an information-provider saying &quot;An X/s a .... &quot; In actual practice, however, there are many ways a definition can he requested and many ways the request cmt be responded to by the information-provider. In order to identify the characteristics of definitign-giving dialogues, we have analyzed transcripts of novice-expert dialogues from a variety of domains, including student/advisor dialogues, recipe-providing dialogues, taxpayer/tax-agent dialogues, and radio talk shows in !which callers 8ought expert advice on investments and real estate. 1 This section describes definition-glving situations identified in this study.</Paragraph> <Paragraph position="1"> An expert may give a definition either in response to a user's request or spontaneously. Occasions for providing definitions arise most obviously when the user asks a question of the form &quot;What is ... ?&quot; or &quot;What is the significance of...?&quot; The question doesn't have to be explicit, however, as illustrated in the exchange below, which is an excerpt from a money-management talk show transcript: null E: &quot;I'd llke to see you put that into two different Southern utilities.&quot; U: &quot;Southern utilities?&quot; As shown in \[Carberry 1985\], such elliptical fragments are often intended to elicit clarification and explanation of the repeated term. In addition to giving definitions in response to a request by the user, the expert may provide a definition as part of correcting a user misconception \[McCoy 1986\], or may generate definitions spontaneously. There are several reasons an expert may give spontaneous definitions. He may provide additional definitional information to justify use of a concept, tie may think it likely that the user doesn't know about the entity being introduced. The expert may want to ensure that he and the user are working with the same definition. The statement below is an example of a spontaneous definition from a recipe-giving dialogue: E: &quot;You use a spring-form pan -- the kind that ,allows you to separate the bottom and the sides once you have prepared your dish.&quot;</Paragraph> </Section> <Section position="4" start_page="0" end_page="568" type="metho"> <SectionTitle> 3 Definitions in Task-Oriented Dialogues </SectionTitle> <Paragraph position="0"> McKeown \[McKeown 1985\] studied definitions in the coutext of requests for information about the objects modeled by a database system. She claimed that humans have mutually known conventions for organizing information and providing definitions, and that a natural language system should make use of these strate* gies in producing explanations. Given a definition request, her TEXT system selected a rhetorical strategy based on the information available. The rhetorical strategy was then responsible for selecting the information to he incorporated into the definition.</Paragraph> <Paragraph position="1"> TEXT treated requests for definitions as isolated queries, whereas we are interested in definitions generated in the course of ongoing task-oriented dialogues.</Paragraph> <Paragraph position="2"> Our analysis of transcripts of naturally occurring interactions indicates that definitions generated in task-oriented dialogues differ significantly .from those generated statically or as a result of isolated definition requests. The differences appear to be the result of several factors: tThese trmascrlpts were provided by the Computer Science Departments of the University of Pen~ylvania and the University of Delaware.</Paragraph> <Paragraph position="3"> 1. In task-oriented dialogues, the information-provider knows something about what the information-seeker is trying to accomplish, and will generate definitions that help the information-seeker achieve his goals. For example, the first response below would be an appropriate definition of baking soda if the information-seeker is baking a cake, whereas the second would be appropriate if he is trying to relieve indigestion.</Paragraph> <Paragraph position="4"> E: &quot;Baking soda is an ingredient that, when heated, releases carbon dioxide, thereby causing the mixture to expand in size.&quot; E: &quot;Baking soda is a substance that, when dissolved in water,produces a chemically basic solution that will counteract acidity.&quot; 2. Whereas static definitions or responses to one-shot requests for defiuit|ons must assume a generic model for the information-seeker, responses to definition requests during an ongoing dialogue can take into account acquired beliefs about the information-seeker's specific domain knowledge. For example, the information-provider might include an analogy to an entity that the information-seeker is already familiar with, as in the following definition of the course CS106: E: &quot;CS106 is like CS105, except that it uses Fortran instead of Pascal and emphasizes scientific applications of computing.&quot; 3. Whereas static definitions and responses to one-shot requests for definitions must be generated all at once, dialogue allows the information-provider to produce what he thinks will be an acceptable definition and analyze the information-seeker's response to determine whether to elaborate on the definition.</Paragraph> <Paragraph position="5"> For example, in the following dialogue with a veterinarian about treating a cat with a hyperthyroid condition, the veterinarian (E) provides a definition that he believes will Satisfy the information-seeker's needs, then must elaborate on it when the information-seeker's response reveals multiple goals: to improve the condition of the cat and to have medication that is easy to administer.</Paragraph> <Paragraph position="6"> E: &quot;Tapazole is a drug that decreases the function of the thyroid.&quot; U: &quot;How large are the pills?&quot; &quot; H a system carrying on a task-oriented dialogue is te be viewed by the information-seeker as cooperative, intelligent, and natural, it must take the above factors into account. Otherwise, it will not appear to be directed toward the user's goals (uncooperative), will not appear to make use of what the user already knows (unintelligent), and will not appear to take advantage of the fact that the interaction is ongoing, as opposed to one-shot (unnatural). Our hypothesis is that, instead of using a rhetorical strategy to determine the content of a definition, the system should reason about the user's plans and goals and speclliPS domain knowledge to decide the importance of incorporating individual propositions into the final definition. For this purpose a user model, preferably a dynamically constructed user model, is essential. The choice of a rhetorical strategy should be made on the basis of being able to include into the definition those features deemed most important. Thus beliefs about the appropiiate content of the definition should guide selection of a rhetorical strategy, instead of the choice of a rhetorical strategy determining content.</Paragraph> <Paragraph position="7"> McKeown, Wish, and Matthews \[McKeown et al. 1985\] addressed some of these issues in their work on an expert lystem that could provide explanations tailored to users. They described a method for using a model of the user's goals along with p~built perspectives on the knowledge base to generate appropriate explanations. While they touched on some of the issues that concern us, they took a different approach from the one we are proposing. Their perspectives were built into the domain knowledge base, and their system did not make much use of informaticm available from the system's model of the user's plans and goals. Also, they were concerned with answering can and should questions, whereas we are interested in definition explanations.</Paragraph> </Section> <Section position="5" start_page="568" end_page="569" type="metho"> <SectionTitle> 4 Appropriate Content of a Definition </SectionTitle> <Paragraph position="0"> Our analysis of naturally occurring consultation dialogues indicates that definitions can take many forms. They may be made up of one or more of a set of components, which correspond to rhetorical predicates described in \[Grimes 1975, Williams 1893, McKeown 1985\]. These predicates will be discussed further in Section 5.</Paragraph> <Paragraph position="1"> Since we are studying cooperative dialogues in which the expert's goal is to help the information-seeker solve his problem, we hypothesize that the expert's overriding concern in selecting the information to include is that the response be as useful as possible to the individual user. Intuitively, to be truly useful to the user, the information must be something he doesn't already know but something relevant that he can understand. Our hypothesis, which appears to explain the definitions occurring in our dialogue transcripts, suggests the following Principle of Usefulness: 1. The response should be made at a high enough level that it is meaningful to the user.</Paragraph> <Paragraph position="2"> (a) Don't say something the user won't understand.</Paragraph> <Paragraph position="3"> (b) Don't give information that addresses more detailed aspects of the user's task-related plan than is appropriate for his current focus of attention.</Paragraph> <Paragraph position="4"> 2. The response should be made at a low enough level that it is helpful to the user.</Paragraph> <Paragraph position="5"> (a) Don't inform the user of something he already knows.</Paragraph> <Paragraph position="6"> (b) Don't give information that is unrelated to the user's goals and task-related plan, or is too general for his current focus of attention in the plan.</Paragraph> <Paragraph position="7"> Grice \[(\]rice 1975\] stated that contributions should be as informative as required for the exchange, but not more informative than required. Paris \[Paris 1988\] suggested that an answer to a question should be both informative and understandable to the user, based on the user's level of knowledge about the domain of discourse. The Principle of Usefulness formalizes and extends these guidelines for definitions by selecting the appropriate level both in knowledge-related issues (la, 2a) and in plans and goals (lb, 2b). This Principle will be used whenever a selection of appropriate level of information to fill a predicate is called for.</Paragraph> <Paragraph position="8"> For example, consider a plant classification hierarchy.</Paragraph> <Paragraph position="9"> To descrlbe a Cuckoopint as an arum would have no meantm84fo an information-seeker who has never heard of an arnm, while defining it as a thing is too general. The useful level of explanation for the information-seeker with no special knowledge of botany is defining a cuckoopint as a flowering plant. In task-odanted dialogues, addltional care must be taken to avoid providing extra information that is unrelated t0; or too detailed for, the user's current needs. Otherwise, the extra information may lead the user to erroneously assume that the system believes the distinguishing characteristics are important or that the system has mls-identified the aspect of his task on which the user is currently focused.</Paragraph> <Paragraph position="10"> The term rhetorical predicate has taken on several mean lugs in the literature of linguistics and coutputationM linguistics. It ha.s been used to describe relationships ranting from structural to conceptual in uature. Grinms \[Grimes 1.975\] described rhetorical predicates i.hat &quot;relate ~he kinds of informatio~t communica*ed i~t discourse with each other.&quot; One of his predicates was ~he Attribu tive predica.te which &quot;adds qualities or color to sa~other predicaie as center.&quot; Ilobbs \[tIobbs 1979\] chose to use the term coherence *~. lution in pn;ference to rhetorical predicate to place tile emphasis on the coherence between sentential units. McKeown's description of rhetoricM vredicatcs \[McKeown 1985\] imtdied ~ut association with sentential s~ructure, but ia practice the predicates she used, such a~ Constitsency, dealt more with conceptuM relationships.</Paragraph> <Paragraph position="11"> Wc :n'e using predicates to charaPSterize the componeni;s of defiuitio~s i~a terms of relationships between conceptual uuits. Our predicates relate information M)out the entity being defined to the entity itself. This relationship is datuMs-independent mid contentindependent. For exarnple, our Identification predicate is instantiaxed by fiuding iu a generalization hierarchy an entity which is art ancestor of the entity being defined. This usage is close to MeKe. own's, but because of the apparent ambiguity of the term rhctori.. cal pmdicales, we prefer to call the predicates strttte#ic predicates, putting emghasis on the motivation of g~fining ant end (in this case, conveying useful information to the user) ratber than on style.</Paragraph> <Paragraph position="12"> l,Y=om our study of definitions occurring in actual dialogues, we have identified fourteen distiuct predicates that relate to deft-nixies content. Each predicate corresponds to a different type of iah)rntatio~ that can be put into a definition. Although we do not claim lltat the list is complete or unique, we do believe it is sutllcient to generate appropriate definitions in an expert consultatlon system. Some of our predicates (ldeutification, Properties, Analogy, Components) are similar to McKeowu's. Others (Effect, Prerequisites) are paxticular to a task--orieuted environment.</Paragraph> <Paragraph position="13"> Associated witit each predicate alie semantics ~hat indicate how to inst ~utiate it. Foc example, efl~ct information will i~e tbund iu the system's library of plans ~ud ,,~o'ds, aud property information will be f~a,~d ill the generalization bieliarchy. \[a either case, the ~;ystem mm;t *'casaba about, the paFticH\]ar_ ' usea++s plans mid goals in ,~rder to deternfinc a propositiou's relewntce to what the user is ~xyiug h) a.:contplish. When au occasion !br a definition a~iscs, a given predicate laity be lilled one or c, tore times. The propositiotm tiros prod,~ced at'e caudidates for inclusion in the detluitio~,. Siuce our goal i.~ to selecl; !~he informatiou thai; i~; l,tost important to th, 'user, we as~;ociate a me'tsnrc at&quot; signiftcauce with each proposition~ The sigailia:aa:ce metrics will be described in Section 6.</Paragraph> <Paragraph position="14"> In the rent,-finder o\[&quot; this sectiou we will look at three, types of definitio:,t components in some detail to illustrate how the user model influences selection.</Paragraph> <Paragraph position="15"> ,%1 :tfde~tifieation Many naturally occurring definitions contain au Identification component, identification consists (ff ideutifying the entity beiug described as a member (d a generic class in a hierarchicMly structured knowledge base ~- for example, E: &quot;Amaretto is a liqueur.&quot; Th~ system's model of the user dictates what superclass from the generalizaLioa hierarchy to use ia au identification. In order tbr identificati,m to I)e h@fful to the user, it is necessary that the user have knowledge of the pareut category used in making the identitication. Ttds condition corresponds to the first part of tile Prirtcipk ~, ,,; Usefldness. Knowledge of a parent category may not be suhici,mt, however, to cause that parent category to be given in the definition. If the systemh beliefs indicate that the pareut category is w.lated ~,.~ the u~er's pin, Is end goals, then there is stronger reason to mention it. In t\],e cane iu which the entity ha8 severM parents that the n~:e~&quot; haJ; kuowledge of, plans and goals should be u.qed to ~elect the one (or ones) most appropriate lo mention. Suppose, lbr exampl% that a digital systems course is cross-listed as both a Cmapu*er Science and an Elec~ricM Engineering course.</Paragraph> <Paragraph position="16"> U: &quot;What is Digital Systems?&quot; E: &quot;It is a Computer Science course ...&quot; or F,: &quot;It is an F, lectrieal Engineering course ...&quot; The choice of answer depends on whether tim user model indicates that the user is trying to satisfy Coolputer Science or Eleetricefl Fingineering requirements. A third ~dternative is F: &quot;It is both a Computer Scieu(:e course mid an Electrical Engineering course ...&quot; This response might be given if the model indicates laoth parent categories play a role in tim user's plans and goals.</Paragraph> <Paragraph position="17"> Following tile Principle of Usefulness, the appropriate super.</Paragraph> <Paragraph position="18"> class is the lowest level parent category that would have meaning to the user and be relevant to what the system believes al.Ie the user's plans and goals.</Paragraph> <Paragraph position="20"> The user knows what A, B, C are Tim user doesn't know about i) Tim user asks &quot;What i.~ X ?&quot; \]n the cm;e illustrated above, the expert's taleutification a:n.sw~r migllt be &quot;X is a C.&quot; The efl'eci; of an.uwering &quot;X is a D&quot; wo01d be to caaJse the user to ask &quot;What is a D?&quot; .r give up withottt getting meaningful info~'mation. The an~Jwm' &quot;X i'.~ a 11&quot; would miss tile distinguishing features shared lay C :uld ;( but not lay B. If the~e distinguishing features ~Lre not important to the tJ.~el ~ii\[1 wol.l!d \[;i-V(! the false impression that tlle system believes they are. a<W(~v:;~i t~ tile user's task, however~ a higher hwel thnu C shouhi b.'~ selected.</Paragraph> <Section position="1" start_page="568" end_page="569" type="sub_section"> <SectionTitle> 5.2 Properties </SectionTitle> <Paragraph position="0"> A Properties response consists o! naminv~ characteristics of tile entity. These are often expl~ssed i, descriptions Kiwm by humans a~q &quot;adjectival phrases attached to the ldentitlcati(m of the entity.</Paragraph> <Paragraph position="1"> E: &quot;A no-load fired is a mutual fired with no sales charge.&quot; E: &quot;Amaretti are crisp Italian almond-flavored macaroons.&quot; In the TEXT systenl \[McKeown 1985\], attributes whose v;Aues distinguish one sub-type from another axe marked in ~;he knowledge base. In task-oriented dialogues, however, an entity's mo~qt im portant distinguishing attributes are not always static but inul.ead may vary depending on tile inhxrmation..seeker'.q plans and goals.</Paragraph> <Paragraph position="2"> For example, the coarse Computer, Ethics and Society may have several distinguishing properties, including its content, its sub:;tantial writing component, its lack of programmiug projects, and itt+ scheduling at night through continuing education. An information.</Paragraph> <Paragraph position="3"> seeker whose objective is to earn a\]IA degree at night while holding a full-time job would consider its schedtding property of interest ili differentiating it from other computer science courses, whereas aa~ electrical engineering major seeking a technical elective would probably consider its lack of programming projects of particular siguif. icance. Titus, although the properties of an entity are found in the generalization hierarchy, the system's beliefs about the user's plaJls and goals should play a major role in determining which properties of the entity are most appropriate to iuclude in a (lefiuititm.</Paragraph> </Section> <Section position="2" start_page="569" end_page="569" type="sub_section"> <SectionTitle> 5.3 Operation </SectionTitle> <Paragraph position="0"> An Operation response consists of a description of how something works. Paris \[Paris 1988\] has demonstrated that explanations given novices in a domain often take the form of process traces. An Operation definition may take the form of process information or steps in implementation. The difference between the two is that the process information is essentially a chain of cause-andeffect occurrences, while the steps in implementation are sequential, but not necessarily causal, as is shown in the example: U: &quot;Can yon tell me what the money market is?&quot; E: &quot; A money market fund is a group of people getting together -- put their money together in a pool and it is invested by professional investors.&quot; As with the Properties predicate, the system's beliefs about the user's plans and goals must be taken into consideration. The expert might identify the need for an Operation explanation in a task-oriented dialogue when the entity being explained appears in a step in a plan the user must carry out to meet a goal. For example, if the user is a traveler asking the expert for help planning a car trip and the expert advises the user to follow a &quot;Trip Tik,&quot; the expert should explain how a Trip Tik works if the model of the user indicates lack of familiarity with it. The definitions of baking soda given earlier illustrate a case in which the appropriate Operation explanation depends on the use to which the entity will be put by the information-seeker.</Paragraph> </Section> </Section> <Section position="6" start_page="569" end_page="571" type="metho"> <SectionTitle> 6 Selecting Definition Content </SectionTitle> <Paragraph position="0"> Our strategy assumes a knowledge base consisting of a generalization hierarchy containing domain knowledge, a plan library, and a lexicon. The user model has three components: 1. a model of the user's domain knowledge in the form of markings on the knowledge base showing the pieces with which the user is familiar \[Kass 1987\], 2. a model of the user's underlying t/ak-related plan and current focus of attention in the plan, given by a context tree \[Carberry 1988\], 3. a model of how receptive the user is to various kinds of infor- null mation, given by weightings on strategic predicates. The first two components will be dynamically updated during the dialogue as shown in \[Kass 1987\] and \[Carberry 1988\]. The third component will also be updated dynamically in response to the user's receptivity to types of definitions and his own usage of strategic predicates.</Paragraph> <Section position="1" start_page="569" end_page="569" type="sub_section"> <SectionTitle> 6.1 Weighting Predicates </SectionTitle> <Paragraph position="0"> When a definition occasion arises, a local predicate receptivity model is created. Starting with a copy of the current global weights representing the user's general receptivity to the kinds of information represented by the strategic predicates, as inferred from the preceding dialogue, further adjustments may be made to reflect the appropriateness of the predicates in the particular situation.</Paragraph> <Paragraph position="1"> The question itself and the level of local domain expertise may cause further weighting of predicates. For example, if the user asks &quot;What is XP' where X is an object, the Identification predicate would be more heavily weighted. If X is an action, the Operation predicate would be more heavily weighted. The level of local domain expertise can be ascertained when a definition is requested by looking at the parts of the plan library and generalization hierarchy that contain references to the entity in question. If they are heavily marked with things the user knows, the user can be considered to have a high level of expertise; otherwise, the user will be considered to be a novice. The weights for predicates that have been determined to be appropriate for expert and novice users will then be increased \[Paris 1988\].</Paragraph> </Section> <Section position="2" start_page="569" end_page="571" type="sub_section"> <SectionTitle> 6.2 weighting Propositions </SectionTitle> <Paragraph position="0"> After predicate weighting has been determined, predicates are filled with information from the knowledge base (generalization hierarchy, lexicon, plans and goals) relevant to the concept being defined. The semantics of each individual predicate dictate where to find the information to fill the predicate. For instance, the Identification and Properties predicates are filled with information found in the generalization hierarchy, and Necessity propositions are drawn from the plans of the user. Some predicates may produce several propositions. For example, an entity may have several properties. For others there might not be any corresponding propositions available.</Paragraph> <Paragraph position="1"> Selection of propositions depends on both the weights of the possible predicates and a measure of significance of the information that could be used to fill them. Significance reflects where the proposition fits into the system's model of the user's goals and possible plans for accomplishing them (relevance) and what information in the generalization hierarchy has been marked as known by the user (familiarity).</Paragraph> <Paragraph position="2"> The system's beliefs about the user's underlying task-related plan, as dynamically inferred from the preceding dialogue, are rep+ resented in a tree structure called a context model \[Carberry 1988\]. Each node in this tree represents a goal that the user has investigated achieving. Except for the root, each goal in the context model is a descendant of a higher-level goal whose associated plan, found in the system's plan library, contains the lower-level goal. One node in the tree is marked as the current focus of attention and indicates that aspect of the task on which the user's attention is currently centered. The context model may be expanded to arbitrarily ma~y levels of detail by repeatedly replacing non-prlmitive suhgoals with associated plans which themselves contain constituent subgoals.</Paragraph> <Paragraph position="3"> If pursuing a subgoal in a plan represents a significant shift in focus, it is marked in the plan library as introducing a new focus domain~;~, Within the context model, a focus domain of subgoals that are at approximately the same level of focus is generated by expanding'the plan associated with a subgoai that introduces the focus domain. As long as this plan is expanded by substituting plans for just those subgoals that do not introduce another new focus domain, the subgoals appearing in the expanded plan are part of the same focus domain.</Paragraph> <Paragraph position="4"> Our estimate of relevance is based on distance of the part of the context model in which the definition information is found from the current focus of attention in the context model. This distance is measured as the number of shifts in focus domains. If the plan is at the focus of attention, the information derived from it is of very high relevance. If it is in the immediately surrounding focus domain (one shift), the information is still of high relevance. As the number of focus domain shifts increases, the relevance of information in the plans begins to fall off, but as long as a plan has been activated the information found in it is of some relevance. This situation in which relevance remains high close to the focus of attention, but drops off more rapidly as the distance increases, is modeled by an inverse exponential function, as shown in Figure 1. The equation</Paragraph> <Paragraph position="6"> where r is the relevance rating and d is the number of shifts from the current focus of attention, captures the desired features.</Paragraph> <Paragraph position="8"> Currently, our relevance metric treats all shifts ~xaong focus domains equally. It may be the case, however, that information in a higber-level plan h that led to the current focus of attention is more appropriate to include in a'defiuition than is information extracted from a subplan s appearing in an expansion of the current focused plan, even if the two plans, h and s, represent the same number of shifts from the current focus of attention in the context model. The current fecund plan is part of an expansion of h, so we know that the user is concerned with accomplishing h; therefore, information relevant to h may be more significant to the user than information relevant to details of carrying out the current focused plan. This is an issue that we plan to investigate further.</Paragraph> <Paragraph position="9"> Our measure of familiarity is based on the knowledge the expert believes the user has about the objects, properties, or concepts that could be used in a definition. We are assuming a variant of the user modeling system described by Kass \[Kass&Fiuin 1987\], modified so that each node in the knowledge base is marked with a bellef factor~ ranging in value from O to 1, giving the system's level of belief that the user is familiar with the entity. Because of the importance of giving a definition in terms of something the person receiving the. definition will understand, an entity known to have meaning to the user (belief factor = 1) should be treated as potentially useful to include, even if it is not germane to the hypothesized goals. If it is not believed strongly that the person is fandllar with the entity, however, it is less useful to tie the definition to that entity. Note that since the dialogues under consideration are ongoing, as opposed to one-shot, a definition can include items that the system believes the user is probably familiar with, mad the system can wait for the user's response to decide whether the definition was successful. The heuristic described here is modeled by the function shown in Figure 2. The formula e 6b(2-b) -- 1 f= e e- 1 ' where f is the familiarity rating and b is the belief factor, exhibits an appropriate amount of curvature to reflect the rapid drop-off in usefulness a~ the belief factor decreases.</Paragraph> <Paragraph position="10"> The \]ast step in computing a measure of significance for a piece of information is to form a weighted combination of the relevance rating and the familiarity rating. Since our primary goal is to provide information that will help the user accomplish a task, our ibrmula for combining the two measures weights significance twice as heavily ~ familiarity. Our significance metric, then, is where S is significance, r is the relevance rating, and f is the familiarity rating.</Paragraph> <Paragraph position="11"> The following example from a hypothetical travel domain ifiustrates how propo~itions are weighted according to significance. The dialogue pertains to planning a trip abroad.</Paragraph> <Paragraph position="12"> U: &quot;I need to have enough money with me to pay for anything I buy.&quot; E: &quot;You can carry as much as you like in travelers checks.&quot; U: &quot;Travelers checks?&quot; The first statement causes the have-money plants beinfocas. The have-moneyplan has subgoals have-convartlble-funda ((_agent: person) (_amountl: funds)) hart_currency ((_agent: person) (_country: country) (_amount2: funds)).</Paragraph> <Paragraph position="13"> Suppose that the user's elliptical fragment is interpreted as a request for a definition. Figure 3 shows part of the context model. As a result of the expert's preceding response, the focus of attention is now on the have-convertible-funds plan. Suppose further that the other plans shown are in a focus domain at a distance of 1 from the focus of attention.</Paragraph> <Paragraph position="14"> The Operation predicate produces the candidate proposition formed from components of the use-travelers-checks subplazt (not shown) equivalent to the statement &quot;You can buy travelers checks at a bank here and cash them in the currency of the country.&quot; The information comes from the body of the use*travelers-checks subplan, which is at distance d=l from the focus of attention. Assuming that the expert believes that the user is familiar with the concepts of buying, banks, currency, and cashing things in, we have</Paragraph> <Paragraph position="16"> The Analogy predicate is filled by a reference to a sibling with similar properties, equivalent to &quot;Travelers checks are like personal checks.&quot; Suppose the belief factor for personal checks is .9 -- that is, the expert believes it very likely but is not absolutely certain that the user knows about personal checks. Suppose further that the properties of travelers checks that are similar to those of personal checks appear in plans at a distance of two shifts of focus domain from the focus of attention. Iu this case we compute</Paragraph> <Paragraph position="18"> The fact that the first definition component has higher computed significance than the second does not necessarily mean that it will be preferred, however. Recall that weights of candidate propositions must reflect both significance of the information and predicate receptivity.</Paragraph> <Paragraph position="19"> Once weights have been assigned to the candidate propositions, they are then ranked according to weight and put into categories. There are four categories: The higher weight categories receive the higher-weighted propositions; the lower-weighted propositions go into the lower weight categories. Some categories may be empty.</Paragraph> <Paragraph position="20"> When all category assignments have been made, the resulting four groups of propositions axe passed to an answer generator. Construction of this answer generator is a future project. The generator will take the classes of propositions, find a way to say all of the Must Say propositions a~ld as many as possible of the Say if Convenient propositions, using Say if Needed for Coherence propositions whenever they help the construction of the response. We propose to do this task using rules of combination developed to produce an utterance that adheres to common rhetorical practices that people appear to follow.</Paragraph> </Section> </Section> <Section position="7" start_page="571" end_page="571" type="metho"> <SectionTitle> 7 A Comparison </SectionTitle> <Paragraph position="0"> Our strategy will produce different responses tban would current definition systems. For example, consider a request for a definition of amaretti. McKeown's TEXT system would identify the entity and include all based database and distinguishing database attributes, and would produce a definition resembling &quot;Amaretti are macaroons. They are made from apricot kernels, have ahnond flavor, are of Italian origin, and have crisp texture. The most popular brand is made by Lazzaroni and Company.&quot; Our definition module would attempt to pick information appropriate to the individual user. If the user is selecting food items to sell in an international bazaar, it would say &quot;Amaretti are Italian macaroons. The most popular brand is made by Lazzaxoni and Company.&quot; If the user is making Amaretti Amaretto Chocolate Cheesecake, for which amaretti are an ingredient, however, it would say &quot;Amaretti are crisp almond-flauored macaroons.&quot;</Paragraph> </Section> <Section position="8" start_page="571" end_page="571" type="metho"> <SectionTitle> 8 .Future Work </SectionTitle> <Paragraph position="0"> Our continuing research will work out additional details of our strategy for providing definitions in task-oriented dialogues. We need to investigate a strategy for dynamically weighting strategic predicates according to the user's perceived receptivity to different kinds of information, and putting this weighting together with ore' measure of significance for propositions. An answer generator that combines propositions, giving emphasis to including those proposi..</Paragraph> <Paragraph position="1"> tions deemed most important to say, must be designed. This task includes ranking the candidate propositions by weight and combining the most heavily weighted ones in a way that will produce a coherent utterance. Finally, the system must be implemented to test and demonstrate the utility of our definition strategy.</Paragraph> </Section> class="xml-element"></Paper>